JP2023143726A - Image processing apparatus, reading device, image forming apparatus, data management system, and method - Google Patents

Abstract

To generate image data that can display a specified color intended to be displayed as a visible image.SOLUTION: An image processing apparatus according to the present invention has: an input unit that receives input of visible image data obtained by reading a subject with a sensor having sensitivity to light from a light source in a visible wavelength range and invisible image data obtained by reading the subject with a sensor having sensitivity to light from the light source in an invisible wavelength range; and an image processing unit that generates image data that displays, in a specified color, a portion of the visible data corresponding to a specified area being a portion having a predetermined absorptance or more in the invisible image data.SELECTED DRAWING: Figure 1

Description

The present invention relates to an image processing device, a reading device, an image forming device, a data management system, and a method.

Conventionally, there is an optical character recognition (OCR) technology that automatically extracts character information from scanned images. If the company name printed on the document has a stamp stamped on it, the color dropout function is used to remove the specific color in order to remove the stamp impression, and then OCR is performed.

Patent Document 1 also discloses a technique in which character areas are determined using infrared light reading and visible light reading information, black areas are determined using visible light information, and black characters are determined based on these results.

However, if the seal impression is removed using a specific color, the black text will also be colored in the specific color due to the overlapping of the seal impressions, causing the problem that it will be removed together.

The present invention has been made in view of the above, and includes an image processing device, a reading device, an image forming device, a data management system, and a data management system capable of generating image data that can display a specified color to be displayed as a visible image. The purpose is to provide a method.

In order to solve the above-mentioned problems and achieve the objects, an image processing device according to the present invention provides visible image data of a subject read by a sensor sensitive to light from a light source in the visible wavelength range, and visible image data of the subject read by a sensor sensitive to light from a light source in the visible wavelength range. an input section into which invisible image data read by a sensor sensitive to light from a light source is input; and a portion of the visible image data that corresponds to a designated area that is a portion of the invisible image data that has a predetermined absorption rate or higher; An image processing unit that generates image data to be displayed in a designated color.

According to the present invention, it is possible to generate image data that can display a designated color that is desired to be displayed as a visible image.

FIG. 1 is a diagram showing an example of the configuration of an image processing apparatus according to the first embodiment. FIG. 2 is a diagram showing an example of using near-infrared light as invisible light. FIG. 3 is a diagram showing the light absorption characteristics of coloring materials. FIG. 4 is a diagram showing an example of the configuration of a reading device. FIG. 5 is a diagram showing an example of the configuration of a control block of the reading device. FIG. 6 is a diagram schematically showing a configuration for correcting black characters when removing shadows. FIG. 7 is an explanatory diagram of an image processed by the achromatic section. FIG. 8 is a diagram illustrating an example of the configuration of a reading device according to Modification 1 of the embodiment. FIG. 9 is a diagram illustrating an example of the configuration of a reading device according to a second modification of the embodiment. FIG. 10 is a diagram illustrating an example of the configuration of a reading device according to modification 3 of the embodiment. FIG. 11 is a diagram showing an example of an embodiment to which Modification 3 is applied. FIG. 12 is an explanatory diagram of a black character area determination unit according to modification example 4. FIG. 13 is an explanatory diagram for determining a threshold value in the black character area determination unit according to modification 5. FIG. 14 is an explanatory diagram of a configuration for determining a threshold value in a black character area determining section. FIG. 15 is a diagram illustrating an example of the configuration of a black character area determining section according to modification example 6. FIG. 16 is a diagram illustrating an example of processing in the achromatic processing unit according to Modification Example 7. FIG. 17 is a diagram illustrating an example of a UI setting screen for adjusting the brightness component of the achromatic process. FIG. 18 is an explanatory diagram of a configuration for removing designated colors such as ruled lines. FIG. 19 is a diagram illustrating an example of the configuration of an image correction section according to modification example 8. FIG. 20 is a diagram illustrating an example of a configuration according to modification example 9. FIG. 21 is a diagram illustrating an example of a configuration according to modification 10. FIG. 22 is a diagram illustrating an example of the configuration of a system including the image processing device according to the second embodiment. FIG. 23 is a diagram illustrating an example of the configuration of an image forming apparatus according to the third embodiment. FIG. 24 is a comparison diagram when specific colors are removed using the conventional method.

Embodiments of an image processing device, a reading device, an image forming device, a data management system, and a method will be described in detail below with reference to the accompanying drawings.

(First embodiment)
FIG. 1 is a diagram showing an example of the configuration of an image processing apparatus according to the first embodiment. The image processing device 00 includes an input section 1a, an image processing section 2a, a specifying section 3a, and an output section 4a.
The input unit 1a inputs a subject image. The subject image includes visible image data D1 of the subject and invisible image data D2 of the subject. The specifying unit 3a specifies a black character area based on the invisible image data D2 input from the input unit 1a. Note that the "black text area" corresponds to the "designated area" and will be described as an area in which black (designated color) text is used to make the explanation easier to understand. The "black text area" is not limited to this as long as it is an area printed in black.
The image processing unit 2a generates image data D3 for displaying a portion of the visible image data D1 corresponding to the black text area in black based on the visible image data D1 input from the input unit 1a and the black text area specified by the specifying unit 3a. generate. The output unit 4a outputs image data D3. The output destination of the output unit 4a may be determined as appropriate, such as the display unit of the image processing device 00 or an external device connected to the image processing device 00.
As a first embodiment, an example will be shown in which the image processing device 00 is applied to a reading device. First, the overall configuration of the reading device will be shown, and the process of generating image data D3 for displaying in black the portion corresponding to the black character area of the visible image data D1 of the subject in the reading device will be explained.
Note that in the reading device, the imaging section corresponds to the input section 1a. The configuration of the reading device shown here is an example, and any reading device may be used as long as it reads a subject image by irradiating the subject with light from a light source and capturing the light from the subject with an imaging unit.

Further, the processing by the image processing section 2a and the identifying section 3a corresponds to processing for removing a seal imprint from a subject image, which will be described later. Part or all of this processing may be performed within the reading device, or may be performed by an image processing device provided separately from the reading device, by inputting the subject image read by the reading device. . If the image processing device performs all the processing, the image processing device may input a subject image stored in a server or memory. Although this embodiment shows an example in which an image processing device is applied to a reading device, the image processing device can be provided separately from the reading device.

In the following, the subject may be referred to as a reading target. The object to be read is one in which the object to be removed, such as a seal imprint, overlaps a black character area where black characters are printed. As an example, paper documents such as various certificates, documents, or forms with stamps are shown, but the object to be removed is not limited to seal impressions. Furthermore, the object to be read is not limited to paper manuscripts.

Furthermore, "visible image data" refers to image data read by a sensing device such as an image sensor that is sensitive to light from a light source in the visible wavelength range (visible light). Furthermore, "invisible image data" refers to image data read by a sensing device such as an image sensor that is sensitive to light from a light source in an invisible wavelength range such as infrared (including near-infrared) and ultraviolet rays. Although near-infrared image data (hereinafter simply referred to as near-infrared image) will be shown below as an example of "invisible image data," it is not limited to near-infrared images. As an example, an example in which near-infrared light is used as invisible light is shown (see FIG. 2). As shown in FIG. 2, a typical silicon image sensor has sensitivity in the near-infrared region (around 750 nm to 1100 nm). Therefore, since a conventionally used general-purpose image sensor can be used, it is possible to realize a simple configuration.
Black ink, black toner, or black pencil used for black text contains carbon. Carbon has the characteristic of absorbing light in the visible and infrared regions. Therefore, it can be read as black even in the visible and infrared regions. On the other hand, color inks and CMY color toners have the characteristic of transmitting light in the infrared region. This feature is shown in FIG. The horizontal axis shows the wavelength of light, and the vertical axis shows the light absorption rate. In Figure 3, black is the color of the material containing carbon as described above, gray is the color printed while thinning out with gray ink or black toner, and color mixture is the color created by mixing CMY colors (hereinafter referred to as The color mixture is black). Color mixed black absorbs light in the visible region, but transmits light in the near-infrared region, so it can be read as blank white in the near-infrared region. Here, a portion (pixel) where the absorption rate is equal to or higher than a predetermined value across the visible region and the invisible region (near infrared region) is defined as a “designated region”. As an example, a color (pixel) with an absorption rate of 40% or more is set as a designated area (black area).

FIG. 4 is a diagram showing an example of the configuration of a reading device. The main body 10 of the reading device 1 has a contact glass 11 on the top surface, and has an imaging section inside the main body 10. Inside the main body 10, a light source 13, a first carriage 14, a second carriage 15, a lens unit 16, an image sensor 17, and the like are provided. The first carriage 14 has a light source 13 and a reflection mirror 14-1, and the second carriage 15 has reflection mirrors 15-1 and 15-2. The main body 10 also includes a control board. The control board is the control unit 300 shown in FIG. 5, and controls the entire reading device 1.

While moving the first carriage 14 and the second carriage 15, the control board irradiates light from the light source 13 and sequentially reads reflected light from the reading target placed on the contact glass 11 using the image sensor 17. . Due to the irradiation of light from the light source 13, the light reflected from the object to be read is reflected by the mirror 14-1 of the first carriage 14 and the mirrors 15-1 and 15-2 of the second carriage 15, and enters the lens unit 16, where it enters the lens unit 16. The light emitted from the unit 16 forms an image on the image sensor 17. The image sensor 17 receives reflected light from the object to be read and outputs an image signal. The image sensor 17 is, for example, an image sensor such as a CCD (Charge Coupled Device) or a CMOS (Complementary MOS), and corresponds to a reading unit that reads an image to be read.

The light source 13 is provided with a visible light source and a near-infrared light source. The image sensor 17 is a first image sensor that receives reflected light of visible light irradiated onto the reading target and outputs an image, and a first image sensor that receives reflected light of near-infrared light irradiated onto the read target and outputs an image. and a second image sensor. An image received by irradiating a reading object with visible light is called a visible image, and an image received by irradiating a reading object with near-infrared light is called a near-infrared image. Note that although a visible light source and a near-infrared light source are separately provided as light sources, a single light source may be used.

The first image sensor and the second image sensor may be configured as a single image sensor as long as they can each output a visible image and a near-infrared image, or each image sensor may be configured individually. may be provided.

The reference white plate 12 is a member for white correction.

The reading device 1 shown in FIG. 4 is equipped with an ADF (Automatic Document Feeder) 20. When one side of the ADF 20 is lifted upward, it opens upward and the surface of the contact glass 11 is exposed. The user sets the object to be read on the contact glass 11, lowers the ADF 20, and presses the ADF 20 against the surface of the contact glass 11 from the back side of the object to be read. When the scan start button is pressed, the first carriage 14 and the second carriage 15 are driven in the main scanning direction and the sub-scanning direction, and the entire object to be read is read.

In addition to the method of setting and reading the object to be read on the contact glass 11, the following method can also be used to read the object. The ADF 20 is also capable of reading the object to be read using a sheet-through method. In the ADF 20, a pickup roller 22 separates the bundle of objects to be read one by one from the tray 21 of the ADF 20, and by controlling various conveyance rollers 24, etc., reads one or both sides of the object to be read that is conveyed through a conveyance path 23 and discharges the sheet. It is discharged onto the tray 25.

The ADF 20 reads the object using the sheet-through method through the reading window 19 . In this example, the first carriage 14 and the second carriage 15 are moved to a predetermined home position and fixed, and when the object to be read passes between the reading window 19 and the background part 26, it is directed toward the reading window 19 side. The image is read by illuminating the surface of the object to be read with light from the light source 13. The reading window 19 is a slit-shaped reading window provided in a part of the contact glass 11. Further, the background portion 26 is a background member.

When performing double-sided reading of the object to be read using the ADF 20, after the object to be read passes through the reading window 19, the back side is read by the reading module 27 of the second reading means provided on the back side of the object to be read. The reading module 27 includes an irradiation unit including a light source and a contact type image sensor as a second reading unit, and reads reflected light of the light irradiated onto the second surface with the contact type image sensor. Note that this light source may also be provided with a visible light source and a near-infrared light source so that visible images and near-infrared images can be read. The background member 28 is a density reference member.

Next, the configuration of the control block of the reading device 1 will be explained.
FIG. 5 is a diagram showing an example of the configuration of a control block of the reading device 1. As shown in FIG. As shown in FIG. 5, the reading device 1 includes a control section 300, an operation panel 301, various sensors 302, a scanner motor 303, various conveyance path motors 304, a drive motor 305, an output section 306, and an imaging section 40. Various other control objects are also connected. Various sensors 302 are sensors that detect objects to be read. The scanner motor 303 is a motor that drives the first carriage 14 and the second carriage 15 of the main body 10. The various motors 304 of the conveyance path are various motors provided in the ADF 20. The output unit 306 corresponds to an output interface through which the output unit 4a outputs image data to an external device. The output interface may be an interface such as a USB or a communication interface connected to a network.

The operation panel 301 is, for example, a touch panel type liquid crystal display device. The operation panel 301 receives input operations such as various settings and reading execution (scan start) from the user using operation buttons, touch input, etc., and transmits corresponding operation signals to the control unit 300. Further, the operation panel 301 displays various display information from the control unit 300 on the display screen. For example, the operation panel 301 includes various setting buttons for the user to remove the imprint of a seal stamped on a subject, etc., and instructs the control unit 300 to make settings when the setting button is inputted. It may be possible to select whether or not to remove the seal imprint on the setting screen of the display screen. Further, the setting may be such that the removal of the seal imprint is always executed when the scan execution button is operated. Further, various data used for removing the seal impression may be stored in an external memory or output to an external device.

The imaging section 40 corresponds to the input section 1a. The imaging unit 40 includes a light source unit 401, a sensor chip 402, an amplifier 403, an A/D 404, an image correction processing unit 405, a frame memory 406, an output control circuit 407, and an I/F circuit 408. The image read from the object to be read is output frame by frame from the output control circuit 407 to the control unit 300 via the I/F circuit 408. Each sensor chip 402 is a pixel sensor of the image sensor 17. The light source section 401 is the light source 13.

The imaging unit 40 is driven by a controller 307. For example, the imaging unit 40 turns on the light source unit 401 based on a lighting signal from the controller 307, and irradiates the reading target with visible light and near-infrared light at set timings. Further, the imaging unit 40 converts the light from the object to be read, which is imaged on the sensor surface of the image sensor 17, into an electrical signal using each sensor chip 402, and outputs the electrical signal.

The imaging unit 40 amplifies the pixel signal output from each sensor chip 402 using an amplifier 403, converts the analog signal into a digital signal using an A/D 404, and outputs a pixel level signal. The image correction processing unit 405 performs image correction processing on the output signal from each pixel. For example, the image correction processing unit 405 performs shading correction and the like on the output signal from each pixel.

After the image correction processing, each data is accumulated in the frame memory 406, and the accumulated read image is transferred to the control unit 300 via the output control circuit 407 and I/F circuit 408.

The control unit 300 includes a CPU (Central Processing Unit), a memory, and the like, and the CPU controls the entire apparatus to perform a reading operation on a reading target and processing such as seal imprint removal on a read image obtained by the reading operation.
The control section 300 includes a processing section 30 and a black character area determination section 32. The processing section 30 and the black character area determination section 32 can be realized by functional sections that are performed by the CPU by executing a predetermined program. In addition, it can also be realized by hardware such as an ASIC (Application Specific Integrated Circuit).

(About seal imprint removal)
Next, seal imprint removal will be explained in detail. A document or the like is exemplified as an object to be read, and a configuration and method for removing a seal imprint from a read image obtained by scanning the document or the like using a specified color removal function that removes a specific color will be described. Note that the black ink, black toner, or black pencil used for black characters contains carbon. Carbon has the characteristic of absorbing light in the infrared region. On the other hand, color inks and CMY color toners have the characteristic of transmitting light in the infrared region. Colors other than black, such as color ink and CMY color toner, are sometimes referred to as "color ***", such as color ink and color toner.

Therefore, when near-infrared light is irradiated onto the object to be read and a near-infrared image is read, the near-infrared light is transmitted through the areas formed by the color components on the paper medium, and the near-infrared light is transmitted through the paper medium. Since the light is reflected by the medium, the paper medium is read as a bright color such as white with a large luminance value.

On the other hand, in the black printed area, both visible light and near-infrared light are absorbed. Since near-infrared light is absorbed in the black text area, the amount of reflected light is small and the area is read as black with a small luminance value. Near-infrared light also passes through the black text area where the seal impressions overlap, but near-infrared light is absorbed in the black text area where the seal impressions overlap, so the color appears reddish under visible light. It is also read as black in near-infrared images. Further, in the black text area, the part where the seal impression does not overlap can be read as black even with visible light.

FIG. 6 is a diagram schematically showing a configuration for correcting black characters when removing shadows. The imaging unit 40 includes the visible light source 13-1 and the visible image sensor 17-1, and the near-infrared light source 13-2 and the near-infrared image sensor 17-2, respectively, described in FIG. The imaging unit 40 irradiates the object to be read with light from the visible light source 13-1, receives reflected light from the object to be read by the visible image sensor 17-1, and outputs a visible image (an RGB image, for example). The imaging unit 40 also irradiates the same object to be read with light from the near-infrared light source 13-2, receives reflected light from the object to be read by the near-infrared image sensor 17-2, and generates a near-infrared image (NIR image). ) is output. The imaging unit 40 can simultaneously read both a visible image and a near-infrared image from the same reading target. Note that if the object to be read is the same, the imaging unit 40 does not need to read both the visible image and the near-infrared image at the same time, and they may be read at different timings as long as the positions of the respective objects to be imaged match.

The processing section 30 includes an achromatic processing section 31 and a black character area determination section 32. The achromatic processing section 31 and the black character area determination section 32 are collectively shown as an achromatic section 30-1. In this configuration, the achromatic processing section 31 of the processing section 30 corresponds to the image processing section 2a (see FIG. 1), and the black character area determination section 32 corresponds to the identification section 3a (see FIG. 1).
The achromatic unit 30-1 receives the near-infrared image captured by the imaging unit 40 as input. The black text area determination unit 32 specifies a black text area from the near-infrared image, and outputs the position of the pixel in the specified black text area to the achromatic processing unit 31. The achromatic processing unit 31 performs a process of achromaticizing the color pixels at the corresponding position on the visible image based on the position of the pixel in the black text area specified by the black text area determination unit 32, thereby determining whether the pixel corresponds to the black text area. As image data D3 for displaying a portion in black, an R'G'B' image in which the target color pixels are achromatic is output. The R'G'B' image corresponds to the first processed image.

Here, the RGB images are an R (Red) version image, a G (Green) version image, and a B (Blue) version image, and the achromatic processing unit 31 processes the R version image, the G version image, and the B version image. For each image, target color pixels are neutralized. The R'G'B' images are an R' version image, a G' version image, and a B' version image.

Here, pixels corresponding to chromatic colors other than achromatic colors are called color pixels. When a seal imprint overlaps a black character, the color tone changes, so by making the color pixels achromatic, the black character part whose color tone has changed is restored to black. As a result, it is possible to seamlessly restore the black text in the areas where the seal impressions overlap and the areas where the seals do not overlap.

FIG. 7 is an explanatory diagram of an image processed by the achromatic unit 30-1. As an example, a document is used as a reading target, in which a part of the black text "Seal Imprint Sample Co., Ltd." is overlapped with a vermilion seal impression.

FIG. 7(a) shows a visible image M10 input to the achromatic unit 30-1. In the visible image M10, the state is the same as when the original document is viewed with the human eye under visible light, that is, the vermilion stamp t2 still overlaps a part of the black text "Seal Imprint Sample Co., Ltd." t1, and the black text area is The area where the seal impression t2 overlaps has a vermilion tint due to the seal impression t2. In this state, even if OCR is performed, it is not possible to distinguish all the characters in "Seal Imprint Sample Co., Ltd.".

FIG. 7(b) is a near-infrared image M20 input to the achromatic unit 30-1. In the near-infrared image M20, "Seal Imprint Sample Co., Ltd." t1 in black letters, which is the same as in the visible image M10, is shown entirely in black and raised. The black text portion where the seal imprint t2 overlaps stands out in black like the other black text portions by irradiation with near-infrared light. By using the near-infrared image M20, the black text area determination unit 32 can identify the black text area where the seal imprint t2 overlaps as a black text area as well as other black text areas.

FIG. 7(c) shows an image after the color pixels in the black text area of “Seal Imprint Sample Co., Ltd.” t1, which has a vermilion tinge due to the overlap of the seal impression t2 of the visible image M10, are achromatic, that is, the first processed image M11 It is. In the visible image M10, the black text portion of "Inkaku Sample Co., Ltd." t1, which overlaps with the seal imprint t2, was tinged with vermilion, but it turned black due to achromatization, and as in the first processed image M11, the black text part of "Inkaku Sample Co., Ltd." t1 overlapped with the seal imprint t2 was tinged with vermillion. "t1 is restored in black without interruption, both in the areas where the seal impressions overlap and in the areas where they do not overlap.

FIG. 7D shows an image M12 after the seal imprint has been removed when the specific color is removed using the first processed image M11. By removing the vermilion color of the seal impression t2, the seal impression t2 is removed, but the black letter "Seal Imprint Sample Co., Ltd." t1 remains clean without any fading or loss.

Note that when specific colors are removed using the conventional method, this does not happen, and the black text "Seal impression sample" will be blurred or missing, making OCR recognition of that part difficult (Figure 24 reference).

As described above, in this embodiment, the achromatic processing unit 31 and the black character area determination unit 32 are provided, and the black character area is determined from the near-infrared image obtained by simultaneous reading with the visible image, and the black character area is determined. Color pixels at the same position on the visible image determined to be achromatic.

As a result, black characters colored due to overlapping seal impressions are restored to black, so even when seal impression removal is performed by removing a specific color in subsequent processing, it is possible to suppress blurring and loss of black characters. Therefore, the OCR recognition rate can also be improved.

(Modification 1 of the embodiment)
A case will be described in which a neutralized RGB image is output to an external device outside the reading device 1. Note that the same applies to other forms and modifications described later, but explanations that overlap with the embodiment will be omitted as appropriate, and different parts will be mainly explained.

Here, the connection between the reading device 1 and the external device may be a wired connection or a wireless connection. Further, the reading device 1 and an external device may be connected by a connection cable such as a USB, or may be connected via a communication network using a communication interface.

Further, the external device is, for example, an information processing device having a computer configuration such as a user PC, or a server device. It is equipped with a CPU, and the CPU executes a predetermined program to remove a seal imprint from a neutralized RGB image, perform OCR processing, etc. The output unit 306 (see FIG. 5) outputs the signal to the external device.

FIG. 8 is a diagram illustrating an example of the configuration of a reading device according to Modification 1 of the embodiment. An image correction section 33 is provided in the processing section 30. The image correction section 33 performs filter processing, color correction processing, etc. on the R'G'B' image output from the achromatic section 30-1, and outputs the outR'G'B' image to an external device. functions. The image output to the external device is data before the seal impression is removed by removing a specific color.

In this way, with the configuration of Modification 1, the reading device 1 can output an outR'G'B' image that can be treated in the same manner as a normal RGB scanner image. The outR'G'B' image has been subjected to achromatic processing for the black text area where the seal impression overlaps, so even if post-processing is performed at a later stage, the external device at the later stage will be able to detect the area where there is no seal impression in the first place. It can be treated in the same way as an RGB scanner image such as a document image. Furthermore, since the outR'G'B' image is outputted with a quality comparable in appearance to that of a normal RGB scanner image, it can be used as an image for storage purposes.

When performing OCR with an external device as post-processing, the black characters where the seal impression overlaps are achromatized, so even after the seal impression is removed by removing a specific color, the characters may become blurred. It is less likely to be missing, and it is possible to suppress erroneous recognition by OCR.

(Modification 2 of embodiment)
A configuration for outputting a neutralized RGB image to the outside as an OCR-dedicated image will be described. FIG. 9 is a diagram illustrating an example of the configuration of a reading device according to a second modification of the embodiment.

As shown in FIG. 9, the image correction section 33 is provided with a seal imprint removal section 34 and a monochrome processing section 35. The seal imprint removing unit 34 performs seal imprint removal by removing a specific color from the R'G'B' image that has been subjected to the achromatic process. The monochromatic processing unit 35 performs K monochromatic processing on the R''G''B'' image after the seal imprint has been removed to facilitate OCR recognition. The image after the K monochrome processing is output from the image correction section 33 to the outside. The image after the monochromatic processing corresponds to a "second processed image."

In the configuration of the second modification, seal imprint removal can be performed on the achromatic R'G'B' image using the optimum removal parameters within the same system. Therefore, for example, it is possible to use a removal parameter that facilitates color determination on the premise that black characters are achromatic, and even slightly dull seal impressions can be targeted for removal. Therefore, in the configuration of Modification 2, it is expected that the accuracy of removing the seal impression will be improved.

(Variation 3 of the embodiment)
When performing OCR on a form, there are cases where the original form is stored as evidence. In that case, information such as the impression of the seal stamped on the form must also be preserved. Images that have been processed to the optimum level for OCR have unnecessary information other than text removed, so they are not suitable as images to be saved as evidence.

Therefore, in the third modification, a configuration is shown in which not only the monochromatic OCR image shown in the second modification, but also the original image that has not been subjected to OCR processing, can be output.

FIG. 10 is a diagram illustrating an example of the configuration of a reading device according to modification 3 of the embodiment. As shown in FIG. 10, the RGB image output from the visible image sensor 17-1 is output to both a processing unit for outputting an image for storage and a processing unit for outputting an image for OCR. be done. The processing unit for outputting the storage image corresponds to the second image processing unit 36 in FIG. The second image processing unit 36 performs image correction processing for storage on the RGB image output from the visible image sensor 17-1, and outputs an RGB image for storage. The configuration of the processing unit for outputting the OCR image is similar to the configurations of the achromatic unit 30-1 and the image correction unit 33 shown in FIG. 9, and therefore a description thereof will be omitted.

In the configuration of Modification 3, for one reading target, both the storage image and the OCR image are output in one reading. As a result, the user can obtain both the storage image and the OCR image using a PC device or the like, thereby saving the user the trouble of obtaining the storage image and the OCR image separately.

Note that in FIG. 10, the configuration of the achromatic unit 30-1 and image correction unit 33 shown in FIG. 9 is applied to the processing unit for outputting the OCR image, but this is just an example. Yes, but not limited to this configuration. For example, the configuration shown in FIG. 8 may be used to output an outR'G'B' image. The outR'G'B' image is an image that has been subjected to achromatic processing, but no specific color has been removed.

(Example of modification 3)
Next, an example to which Modification 3 is applied will be shown. FIG. 11 shows a data management system to which the device configuration shown in FIG. 10 is applied. The PC or server is equipped with a storage device, and stores and manages the storage image data and OCR image data sent from the processing unit 30 as one set. The storage image data and the OCR image data are managed in a common storage device with names linked to each other so that the relationship can be understood. By using this data management system, it is possible to prevent the image data that is the original of OCR image data from being lost, and the common management facilitates management.

(Modification 4 of embodiment)
Next, as a fourth modification, a modification of the determination method in the black character area determination section when a seal impression stands out faintly in a near-infrared image will be described.

FIG. 12 is an explanatory diagram of the black character area determination unit 32 according to the fourth modification. As shown in FIG. 12A, the black character area determination section 32 includes a binarization processing section 3000. FIG. 12(b) is an example of a near-infrared image in which a seal imprint appears faintly. As shown in FIG. 12(b), the seal imprint t2 stands out faintly in the near-infrared image. As already explained, the black text portion absorbs near-infrared light and the amount of light received by the near-infrared sensor is small, so it is represented in black. On the other hand, although a colored part such as a seal impression has a small amount of absorption of near-infrared light, it has a small amount of absorption characteristic, so it may be represented in light gray as shown in FIG. 12(b).

In such a case, it is difficult to specify the black text area t1 using the near-infrared image. Therefore, binarization processing is performed. The binarization processing unit 3000 shown in FIG. 12(a) compares the pixel values of the input infrared image with a threshold value, and selects pixels with values on the black side, pixels on the black text area, pixels on the white side, etc. Binarization processing is performed in which pixels that take a value are pixels in a non-black character area other than black characters. Since the pixels of the seal impression t2 are not white, a threshold is set between the pixel values of the black character area t1 and the pixel values of the seal impression t2, so that pixels consisting only of the seal impression t2 are classified into the non-black character area. Note that this threshold value can also be used to distinguish from black, which is a mixture of three colors.

The black character area determination unit 32 performs the binarization process in this way and outputs the results of black character pixels and non-black character pixels to the achromatic processing unit 31.

In this way, when the binarization process is used to determine the black text area, it becomes easy to distinguish between the black text area and the colored part such as a seal impression.

(Variation 5 of the embodiment)
Next, as a fifth modification, a modification in which a threshold value is determined in a black character area determination section will be described.

FIGS. 13 and 14 are explanatory diagrams of a configuration for determining a threshold value in the black character area determination unit 32 according to the fifth modification.

FIG. 13(a) is an example of a document in which black characters and seal impressions overlap. The overlap between the black text and the seal impression is shown enlarged. 13(b) is an image of an RGB visible image of the original in FIG. 13(a), and FIG. 13(c) is an image of a near-infrared image of the original in FIG. 13(a).

The reading device 1 reads both the RGB image and the near-infrared image using the same optical system (lenses, mirrors, etc.). Therefore, when adjustments are made in accordance with the image quality of the RGB image, the near-infrared image becomes more blurred than the RGB image, as shown in FIGS. 13(b) and 13(c).

In other words, as shown in FIG. 13(d), when looking at pixel changes near the edges of black characters, the near-infrared image shows more rounded pixel value changes than the RGB image. In this case, if the binarization threshold for determining the black character area in the near-infrared image is set near the area where the change from the background level of the document occurs, the position of the edge of the black character in the near-infrared image and the RGB image will be It can be seen that there is a shift. In the near-infrared image, the black character area is determined to be thicker, and as a result, there is a possibility that a part of the seal impression outside the edge of the black character area in the RGB image becomes achromatic.

Therefore, as shown in FIG. 14(a), a background level setting section 37-1, a black level setting section 37-2, and a threshold value determining section 3500 are provided.

The system holds setting values for the background level and black level in advance as settings and design values on the user interface (UI), and the threshold value determination unit 3500 sets the background level setting unit 37-1 and the black level setting unit 37-. The threshold value is determined based on each setting value of 2.

As shown in FIG. 14(b), when an edge changes from a certain background level to a certain black level, in the intermediate region of the amount of level change between them, the position remains constant regardless of the degree of blurring of the image. Become. Therefore, by setting the threshold between the background level and the black level, it is possible to minimize the error in the position of the black text area determined from the near-infrared image and the black text area from the RGB image with different degrees of blur. .

(Variation 6 of the embodiment)
Next, as a sixth modification, a second modification in which a threshold value is determined in a black character area determination section will be described. In modification 5, the threshold value was determined using the setting value and design value set from the UI. However, the background level and the black level of characters differ depending on the input image. Even on a single document, the color and density of the background and the density of black characters may vary depending on the position. With the preset values, there are cases where the background level is darker than the expected level and cannot be handled, such as being detected as black text. Therefore, in modification example 6, the system automatically determines the background level and black level from the image. A configuration for detecting and determining a threshold value is shown.

FIG. 15 is a diagram illustrating an example of the configuration of the black character area determination section 32 according to modification 6. As shown in FIG. 15, the black character area determination section 32 is provided with a background level detection section 3600 and a black level detection section 3700.

The background level detection unit 3600 sets a pixel of interest in a near-infrared image, refers to surrounding pixels in an arbitrary range with respect to the pixel of interest, and detects the background level near the pixel of interest.

The black level detection unit 3700 refers to surrounding pixels in an arbitrary range with respect to the pixel of interest, and detects the black level of a black character existing in the vicinity of the pixel of interest.

The threshold determining section 3500 determines a threshold using the background level and black level detected by the background level detecting section 3600 and the black level detecting section 3700. The binarization processing unit 3000 performs binarization processing using the threshold value.

With this configuration, the background level and black level are detected for each input image, so even if the background level and black level of characters differ depending on the input image, an appropriate threshold value can be used depending on the input image. It can be binarized.
Furthermore, with this configuration, it is also possible to detect the background level and black level for each area in one image. By performing this for each area, it becomes possible to perform binarization using an optimal threshold value for each area, and it becomes possible to extract black text areas with high accuracy.

(Modification 7 of embodiment)
Next, as a seventh modification, an example of processing by the achromatic processing section 31 will be described.

FIG. 16 is a diagram illustrating an example of processing in the achromatic processing unit 31 according to Modification Example 7. As shown in FIG. 16, the achromatic processing unit 31 performs RGB to YUV conversion 3101, achromatic processing 3102, and YUV to RGB conversion 3103. Here, the RGB to YUV conversion 3101 corresponds to a "luminance and color difference conversion section", and the YUV to RGB conversion 3103 corresponds to an "RGB conversion section".

In the RGB to YUV conversion 3101, the input RGB image is converted into a YUV signal (luminance color difference signal).

In the achromatic processing 3102, the input YUV signal is achromatized by correcting the UV signal for pixels at the position of the black character area with reference to the result of the black character area determination. On the other hand, pixels located in non-black character areas are output without being achromatic.

In the YUV to RGB conversion 3103, an inverse conversion is performed to return the achromatic YUV signal to an RGB image, and an achromatic R'G'B' image is output to the subsequent stage.

(Example of calculation process)

An example of calculation processing by the achromatic processing unit 31 is shown below.
Black character area: out_Y = in_Y, out_U=0, out_V=0
Non-black character area: out_Y = in_Y, out_U=in_U, out_V=in_V

In this process, once converted to a luminance color difference signal such as YUV, it is possible to adjust only the saturation to achromatic while maintaining the luminance component.This allows the intensity of black characters in the input image to be adjusted It becomes possible to maintain image achromatic processing.

Note that although an example of conversion to a YUV signal is shown here, the present invention is not limited to this. The format may be other than YUV, for example, YCbYCr, etc., as long as the image can be processed using luminance and color difference converted images.

(Adjustment of brightness component)
Luminance component adjustment in the achromatic processing 3102 will be explained. When performing the achromatic process, the achromatic processing unit 31 may switch the luminance component according to settings from the user.

FIG. 17 is a diagram showing an example of a UI setting screen for adjusting the brightness component of the achromatic processing 3102. The UI setting screen 1000 has a setting confirmation tab 1001, and when the setting confirmation button 1001 is touched, the setting information displayed in FIG. 17 is displayed.

In the setting information, settings corresponding to the mode setting of character 1002 are displayed. Adjustment information 1003 is adjustment information for adjusting the luminance component.

The adjustment information 1003 includes adjustment buttons for adjusting the brightness of black characters or non-black characters, such as keeping them as they are, making them lighter, or making them darker. The brightness component is adjusted when the user wants to emphasize the blackness of black characters.

The UI setting screen 1000 accepts settings for brightness components of black characters and non-black characters using these adjustment buttons, and sets the settings in the achromatic processing unit 31 when the start button 1004 is touched.

For example, if black characters are set to be "dark" and non-black characters are set to be "light", the output value is adjusted by multiplying the Y component by a coefficient as in the following example of calculation processing.

(Example of calculation process)
Black character area: out_Y = in_Y*0.9, out_U=0, out_V=0
Non-black character area: out_Y = in_Y*1.1, out_U=in_U, out_V=in_V

This adjustment information makes it possible not only to make the text achromatic, but also to adjust black characters and non-black characters to the darkness intended by the user.

(Modification 8 of embodiment)
Next, as a modified example 8, a configuration for removing designated colors such as ruled lines will be described.

FIGS. 18 and 19 are explanatory diagrams of a configuration for removing specified colors such as ruled lines. As shown in FIG. 18(a), ruled lines t3 are often drawn on the form to make entry fields clear. Due to a misalignment in the printing position of typefaces or a misalignment in the input position of handwriting, the black character area t1 of the written black character may overlap the ruled line t3. If OCR is performed in this state, the ruled line t3 will get in the way, making it impossible to properly extract character information. Therefore, as shown in FIG. 18(b), a setting section 1003 is provided on the UI setting screen 1000 to instruct removal of the specified color. A setting section 1003 is a setting section for specifying a color that the user wants to remove. In the example shown in FIG. 18(b), color specification buttons such as chromatic colors, red, green, blue, cyan, magenta, and yellow are provided, and the user selects the color to be removed from among them. Note that the types of colors and the method of specifying colors are not limited to these, and may be modified as appropriate.

FIG. 19 is a diagram illustrating an example of the configuration of the image correction section 33 according to Modification Example 8. As shown in FIG. 19, the image correction section 33 is provided with a specified color removal section 38.

The designated color removing unit 38 performs a removal process on the R′G′B′ image that has been achromatic by the achromatic unit 30-1, regarding the designated color that the UI 50 has received from the user via the UI setting screen 1000. .

For example, when removing a ruled line, the user specifies a color corresponding to the color of the ruled line in the setting unit 1003, and removes the specified color by removing the ruled line.

Such a configuration makes it possible to remove ruled lines and the like, and has the effect of suppressing character recognition errors during OCR recognition.

(Modification 9 of embodiment)
A configuration is shown in which an image after monochrome processing is output as a multivalued image when outputting an image for OCR.

FIG. 20 is a diagram illustrating an example of a configuration according to modification example 9. As shown in FIG. 20, when outputting a monochrome image from the monochrome processing unit 35, a multi-valued monochrome image is output instead of a binary image. The monochromatic image of other values is, for example, a grayscale image.

By outputting multiple values in this way, it is possible to pass the data to the subsequent OCR software without losing detailed information around the characters, and the subsequent OCR software can perform advanced binarization processing. If there is, it becomes possible to take advantage of that processing, leading to further improvement in the OCR recognition rate.

Further, although FIG. 20 shows a configuration for outputting a single image of only a monochrome image, it is also applicable to outputting a multi-image image including RGB images as shown in FIG.

(Modification 10 of the embodiment)
A configuration is shown in which, when outputting an image for OCR, binarization processing is performed on the image after monochrome processing and output as a binary image.

FIG. 21 is a diagram illustrating an example of a configuration according to modification 10. As shown in FIG. 21, the image correction section 33 is provided with a binarization processing section 39.

The binarization processing unit 39 performs binarization processing on the monochrome-processed image output from the monochrome processing unit 35, and outputs a binary image as a monochrome image.

Outputting a binary image in this way has the effect of reducing the amount of data. Further, by performing the binarization process in the image correction unit 33, it is possible to perform the binarization using parameters suitable for the reading device. In this case, even if the binarization process provided by the subsequent OCR software is a low-accuracy method, the reading device performs the binarization and passes the data, so the accuracy of the binarization provided by the OCR software cannot be improved. However, it is possible to improve the OCR recognition rate.

Further, although FIG. 21 also shows a configuration for outputting a single image of only a monochrome image, it is also applicable to outputting a multi-image image including RGB images as shown in FIG.

(Second embodiment)
A part or all of the process for removing a seal imprint from a visible image, which is performed by the reading device 1 or the external device shown in the first embodiment, may be performed by an image processing device.

FIG. 22 is a diagram illustrating an example of the configuration of a system including the image processing device according to the second embodiment. The image processing device 2 inputs the visible image and the invisible image output by the reading device 1 and performs processing for removing the seal impression. Further, the image processing device 2 may acquire the visible image and the invisible image stored in the server SS and perform processing for removing the seal impression. Further, the image processing device 2 may read a visible image and an invisible image from a portable storage medium DA such as a semiconductor memory, and perform processing for removing the seal impression.

The image processing device 2 includes a CPU, and the CPU executes a predetermined program to perform various functions such as the processing section 30 and the black character area determination section 32, as well as removing seal impressions from images, OCR processing, etc. be able to perform its functions. Note that some or all of the various functions may be realized by hardware such as an ASIC (Application Specific Integrated Circuit). The image processing device 2 outputs various images from an output unit to an external device such as a PC.

Since the various functions have already been explained using the reading device and the external device as examples in the first embodiment, further explanation will be omitted here.

(Third embodiment)
The reading device shown in the first embodiment and the image processing device shown in the second embodiment may be installed in an image forming apparatus.

FIG. 23 is a diagram illustrating an example of the configuration of an image forming apparatus according to the third embodiment. FIG. 23 shows an example of an image forming apparatus 3 generally referred to as a multifunction peripheral (MFP). The image forming apparatus 3 shown in FIG. 23 includes a reading device (reading device main body 10 and ADF 20) on the top. Since the configuration of the reading device is a repetition of the description of the first embodiment, detailed description thereof will be omitted here.

The image forming apparatus 3 shown in FIG. 23 has an image forming section 80 and a paper feeding section 90 below the reading device main body 10.

The image forming unit 80 prints the read image read by the reading device main body 10 on recording paper, which is an example of a recording medium. The read image is a visible image or a near-infrared image.

The image forming section 80 includes an optical writing device 81, a tandem image forming unit (Y, M, C, K) 82, an intermediate transfer belt 83, a secondary transfer belt 84, and the like. In the image forming section 80, an optical writing device 81 writes an image to be printed on the photosensitive drum 820 of the image forming unit 82, and transfers the toner image of each plate from each photosensitive drum 820 onto the intermediate transfer belt 83. Transcribe. The K plate is formed with K toner containing carbon black.

The image forming unit (Y, M, C, K) 82 has four rotatable photoreceptor drums (Y, M, C, K) 820, and around each photoreceptor drum 820, a charging roller and a developing roller are arranged. Each image forming element includes an image forming apparatus, a primary transfer roller, a cleaner unit, and a static eliminator. An image is formed on each photoreceptor drum 820 by each image forming element operating in a predetermined image forming process around each photoreceptor drum 820, and the image formed on each photoreceptor drum 820 is transferred to the primary transfer roller. As a result, each toner image is transferred onto the intermediate transfer belt 83 as a toner image.

The intermediate transfer belt 83 is disposed in a nip between each photoreceptor drum 820 and each primary transfer roller, and is stretched between a driving roller and a driven roller. The toner image that has been primarily transferred to the intermediate transfer belt 83 is secondarily transferred to the recording paper on the secondary transfer belt 84 by a secondary transfer device as the intermediate transfer belt 83 runs. The recording paper is conveyed to a fixing device 85 by the running of the secondary transfer belt 84, and the toner image is fixed on the recording paper. Thereafter, the recording paper is ejected to a paper ejection tray outside the machine.

Note that the recording paper is, for example, fed by the paper feed section 90 from paper feed cassettes 91 and 92 that store recording paper of different paper sizes, and transported by a conveying means 93 consisting of various rollers for secondary transfer. It is supplied to the belt 84.

Note that the image forming section 80 is not limited to one that forms images using the electrophotographic method as described above, but may also form images using an inkjet method.
Further, the image forming apparatus is not limited to an MFP. The image forming device may be, for example, a printer that receives image data generated by a separate image processing device via communication and prints the received image data.

Although the embodiments and modified examples of the present invention have been described above, each embodiment and modified example are presented as examples, and are not intended to limit the scope of the invention. These novel embodiments and modifications can be implemented in various other forms, and various omissions, substitutions, and changes can be made without departing from the gist of the invention. Each of these embodiments and modifications are included within the scope and gist of the invention, as well as within the scope of the invention described in the claims and its equivalents.

Aspects of the present invention are, for example, as follows.
<1> An input into which visible image data of the subject is read by a sensor sensitive to light from a light source in the visible wavelength range and invisible image data is read by a sensor sensitive to the light of the light source in the invisible wavelength range. Department and
an image processing unit that generates image data that causes a portion of the visible image data that corresponds to a designated area, which is a portion of the invisible image data that has an absorption rate of at least a predetermined value, to be displayed in a designated color;
An image processing device having:
<2> The image processing device according to <1>, further comprising an output unit that outputs the image data generated by the image processing unit to an external device.
<3> The image processing device according to <2>, wherein the output unit outputs the visible image data of the subject and the image data generated by the image processing unit to the external device.
<4> a designated color removal unit that removes a designated color from the image data generated by the image processing unit;
a monochrome processing unit that performs monochrome processing on the image data after the specified color has been removed;
It further has
The image processing device according to <2> or <3>, wherein the output unit outputs the image data after the monochrome processing to the external device.
<5> The image processing device according to <4>, wherein the specified color removal unit removes a specified color set by a user from the image data generated by the image processing unit.
<6> The image processing device according to <4> or <5>, wherein the image data monochromated by the monochromatic processing section is output as multivalued image data.
<7> The image processing device according to <4> or <5>, which outputs binary image data obtained by binarizing image data monochromated by the monochromatic processing section.
<8> A specifying unit that specifies a portion having a predetermined absorption rate or more as a designated area based on the invisible image data,
The image processing device according to any one of <1> to <7>, wherein the specifying unit determines the designated area by binarizing the invisible image data.
<9> The specific part is
It has a threshold value determination unit that determines a threshold value based on the set background level and black level,
The image processing device according to <8>, wherein the binarization process is performed based on the threshold determined by the threshold determining unit.
<10> The threshold value determination unit includes:
a background level detection unit that detects a background level of visible image data of the subject;
a black level detection unit that detects a black level of visible image data of the subject;
The image processing according to <9>, wherein the threshold value corresponding to each region of the visible image data of the subject is determined based on the background level detected by the background level detection unit and the black level detected by the black level detection unit. Device.
<11> The image processing unit includes:
It has a luminance-chrominance conversion unit that converts RGB image data into luminance-chrominance data,
The apparatus includes an RGB conversion unit that performs processing on the luminance color difference signal to display a portion of the visible image data that corresponds to the specified area in the specified color, and converts the processed signal data into RGB image data again. The image processing device according to any one of items 1> to <10>.
<12> The image processing device according to <11>, wherein the image processing unit adjusts the output value of the brightness component of the brightness signal according to a brightness component adjustment setting value set by the user.
<13> The image processing unit sets the designated color for displaying the portion of the visible image data that corresponds to the designated area to be black.
The image processing device according to any one of <1> to <12>.
<14> The image processing device according to any one of <1> to <13>;
a visible light source that irradiates the subject with light of a visible wavelength;
an invisible light source that irradiates the subject with light of an invisible wavelength;
a first image sensor that receives visible wavelength reflected light from the subject and outputs visible image data;
a second image sensor that receives reflected light of an invisible wavelength from the subject and outputs invisible image data;
A reading device having a
<15> The image processing unit includes:
The reading device according to <14>, wherein the invisible image data output by the second image sensor and the visible image data output by the first image sensor are input.
<16> The image processing device according to any one of <1> to <13>, or the reading device according to <14> or <15>,
an image forming unit that forms an image based on the image data generated by the image processing unit;
An image forming apparatus having:
<17> The image processing device according to <3> or <4>;
an information processing device that links and manages the visible image data transmitted from the image processing device and the image data generated by the image processing unit;
A data management system with
<18> A method of image processing visible image data obtained by reading a subject with a sensor sensitive to light from a light source in the visible wavelength range,
inputting the visible image data of the subject and invisible image data obtained by reading the subject with a sensor sensitive to light from a light source in an invisible wavelength range;
generating image data for displaying a portion of the visible image data that corresponds to a designated area, which is a portion of the invisible image data that has an absorption rate of at least a predetermined value, in a designated color;
method including.
<19> An input into which visible image data of the subject is read by a sensor sensitive to light from a light source in the visible wavelength range and invisible image data is input in which the subject is read by a sensor sensitive to light from a light source in the invisible wavelength range. Department and
an image processing unit that generates image data that causes a portion of the visible image data that corresponds to a designated area of the invisible image data that is an image containing carbon as a material to be displayed in a designated color;
An image processing device having:

00 Image processing device 1a Input section 2a Image processing section 3a Specification section 4a Output section 13-1 Visible light source 13-2 Near-infrared light source 17-1 Visible image sensor 17-2 Near-infrared image sensor 30-1 Achromatic section 31 Achromatic processing unit 32 Black character area determination unit 40 Imaging unit D1 Visible image data D2 Invisible image data D3 Image data

Japanese Patent Application Publication No. 11-205618

Claims (19)

an input section into which visible image data of the subject is read by a sensor sensitive to light from a light source in the visible wavelength range and invisible image data read by a sensor sensitive to the light of the light source in the invisible wavelength range are input;
an image processing unit that generates image data that causes a portion of the visible image data that corresponds to a designated area, which is a portion of the invisible image data that has an absorption rate of at least a predetermined value, to be displayed in a designated color;
An image processing device having: The image processing apparatus according to claim 1, further comprising an output section that outputs the image data generated by the image processing section to an external device. The image processing device according to claim 2, wherein the output unit outputs the visible image data of the subject and the image data generated by the image processing unit to the external device. a designated color removal unit that removes a designated color from the image data generated by the image processing unit;
a monochrome processing unit that performs monochrome processing on the image data after the specified color has been removed;
It further has
The image processing device according to claim 2, wherein the output unit outputs the image data after the monochromatic processing to the external device. The image processing apparatus according to claim 4, wherein the specified color removal section removes a specified color set by a user from the image data generated by the image processing section. The image processing apparatus according to claim 4, wherein the image data monochromated by the monochromatic processing section is outputted as multivalued image data. 5. The image processing apparatus according to claim 4, wherein the image processing unit outputs binary image data obtained by binarizing the monochromatic image data in the monochromatic processing section. a specifying unit that specifies a portion having an absorption rate of a predetermined value or higher as a designated area based on the invisible image data;
The image processing device according to claim 1, wherein the specifying unit determines the designated area by binarizing the invisible image data. The specific part is
It has a threshold value determination unit that determines a threshold value based on the set background level and black level,
The image processing device according to claim 8, wherein the binarization process is performed based on the threshold determined by the threshold determining unit. The threshold value determination unit includes:
a background level detection unit that detects a background level of visible image data of the subject;
a black level detection unit that detects a black level of visible image data of the subject;
The image processing according to claim 9, wherein the threshold value corresponding to each region of the visible image data of the subject is determined based on the background level detected by the background level detection unit and the black level detected by the black level detection unit. Device. The image processing unit includes:
It has a luminance-chrominance conversion unit that converts RGB image data into luminance-chrominance data,
The apparatus further comprises an RGB conversion unit that performs processing on the luminance color difference signal to display a portion of the visible image data that corresponds to the specified area in the specified color, and converts the processed signal data into RGB image data again. Item 1. The image processing device according to item 1. The image processing device according to claim 11, wherein the image processing unit adjusts the output value of the brightness component of the brightness signal according to a brightness component adjustment setting value set by a user. The image processing unit sets the specified color for displaying a portion of the visible image data that corresponds to the specified area to be black.
The image processing device according to claim 1. An image processing device according to any one of claims 1 to 13;
a visible light source that irradiates the subject with light of a visible wavelength;
an invisible light source that irradiates the subject with light of an invisible wavelength;
a first image sensor that receives visible wavelength reflected light from the subject and outputs visible image data;
a second image sensor that receives reflected light of an invisible wavelength from the subject and outputs invisible image data;
A reading device having a The image processing unit includes:
The reading device according to claim 14, wherein the invisible image data output by the second image sensor and the visible image data output by the first image sensor are input. An image processing device according to any one of claims 1 to 13;
an image forming unit that forms an image based on the image data generated by the image processing unit;
An image forming apparatus having: An image processing device according to claim 3 or 4;
an information processing device that links and manages the visible image data transmitted from the image processing device and the image data generated by the image processing unit;
A data management system with A method of image processing visible image data obtained by reading a subject with a sensor sensitive to light from a light source in the visible wavelength range,
inputting the visible image data of the subject and invisible image data obtained by reading the subject with a sensor sensitive to light from a light source in an invisible wavelength range;
generating image data for displaying a portion of the visible image data that corresponds to a designated area, which is a portion of the invisible image data that has an absorption rate of at least a predetermined value, in a designated color;
method including. an input section into which visible image data of the subject is read by a sensor sensitive to light from a light source in the visible wavelength range and invisible image data read by a sensor sensitive to the light of the light source in the invisible wavelength range are input;
an image processing unit that generates image data that causes a portion of the visible image data that corresponds to a designated area of the invisible image data that is an image containing carbon as a material to be displayed in a designated color;
An image processing device having:

Images