Nothing Special   »   [go: up one dir, main page]

CN111972700A - Cigarette appearance detection method and device, equipment, system and medium thereof - Google Patents

Cigarette appearance detection method and device, equipment, system and medium thereof Download PDF

Info

Publication number
CN111972700A
CN111972700A CN201910430854.6A CN201910430854A CN111972700A CN 111972700 A CN111972700 A CN 111972700A CN 201910430854 A CN201910430854 A CN 201910430854A CN 111972700 A CN111972700 A CN 111972700A
Authority
CN
China
Prior art keywords
cigarette
image
noise
target area
panoramic image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201910430854.6A
Other languages
Chinese (zh)
Other versions
CN111972700B (en
Inventor
朱轶
钟英
邢伟标
曹毅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Shengqi Electromechanical Equipment Co ltd
Shanghai Tobacco Group Co Ltd
Original Assignee
Shanghai Shengqi Electromechanical Equipment Co ltd
Shanghai Tobacco Group Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Shengqi Electromechanical Equipment Co ltd, Shanghai Tobacco Group Co Ltd filed Critical Shanghai Shengqi Electromechanical Equipment Co ltd
Priority to CN201910430854.6A priority Critical patent/CN111972700B/en
Publication of CN111972700A publication Critical patent/CN111972700A/en
Application granted granted Critical
Publication of CN111972700B publication Critical patent/CN111972700B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • AHUMAN NECESSITIES
    • A24TOBACCO; CIGARS; CIGARETTES; SIMULATED SMOKING DEVICES; SMOKERS' REQUISITES
    • A24CMACHINES FOR MAKING CIGARS OR CIGARETTES
    • A24C5/00Making cigarettes; Making tipping materials for, or attaching filters or mouthpieces to, cigars or cigarettes
    • A24C5/32Separating, ordering, counting or examining cigarettes; Regulating the feeding of tobacco according to rod or cigarette condition
    • A24C5/34Examining cigarettes or the rod, e.g. for regulating the feeding of tobacco; Removing defective cigarettes
    • A24C5/3412Examining cigarettes or the rod, e.g. for regulating the feeding of tobacco; Removing defective cigarettes by means of light, radiation or electrostatic fields
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30Computing systems specially adapted for manufacturing

Landscapes

  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Toxicology (AREA)
  • Image Processing (AREA)

Abstract

According to the cigarette appearance detection method, the device, the equipment, the system and the medium, a panoramic image scanned by 360 degrees on the outer surface of the cigarette to be detected is obtained; preprocessing the panoramic image to remove noise, and segmenting the preprocessed panoramic image to find a target area; and comparing the corresponding image in the target area with the standard image to obtain corresponding similarity so as to generate appearance quality evaluation and defect information corresponding to the cigarette to be detected. This application can reduce the image distortion, improves and detects the accuracy, need not to shoot many photos or need many cameras to shoot to can the time detect cigarette outward appearance and embossed seal and provide more automatic evaluation result.

Description

Cigarette appearance detection method and device, equipment, system and medium thereof
Technical Field
The invention relates to the technical field of cigarette quality detection, in particular to a cigarette appearance detection method, a device, equipment, a system and a medium thereof.
Background
In the production process of cigarettes, the defects of cigarette surface or the defects of printed steel seal are often caused by human or equipment reasons, and become a major problem of the largest ratio of the quality of finished cigarettes. The existing cigarette appearance detection is mainly used for shooting static pictures, or shooting pictures at a plurality of different angles, or shooting through a plurality of cameras, and comparing another picture with a standard sample, so that the comparison can not be performed at one time, or more automatic evaluation results can not be provided for cigarette appearance and steel seal detection.
Disclosure of Invention
In view of the above-mentioned shortcomings in the prior art, the present application is directed to a method, device, system and medium for detecting the appearance of cigarettes, so as to solve the problems in the prior art.
In order to achieve the above objects and other related objects, the present application provides a cigarette appearance detecting method, including: acquiring a panoramic image scanned by 360 degrees on the outer surface of a cigarette to be detected; preprocessing the panoramic image to remove noise, and segmenting the preprocessed panoramic image to find a target area; and comparing the corresponding image in the target area with the standard image to obtain corresponding similarity so as to generate appearance quality evaluation and defect information corresponding to the cigarette to be detected.
In an embodiment of the present application, the method for segmenting the preprocessed panoramic image to find the target area includes: obtaining a linear decision function by training a multilayer perceptron based on a neural network; classifying pixels of the panoramic image by using the decision function to obtain one or more non-overlapping subregions; and finding the target area from all the sub-areas according to preset target data.
In an embodiment of the present application, the method for comparing the corresponding image in the target region with the standard image to obtain the corresponding similarity includes: when the target area is a steel seal, comparing the standard graph corresponding to the steel seal with each pixel point of the corresponding image in the target area; if the pixel points are equal to the pixel points, marking as similar points; and counting the proportion of the number of the similar points to the number of all the pixels to obtain the similarity.
In an embodiment of the present application, the method for comparing the corresponding image in the target region with the standard image to obtain the corresponding similarity includes: when the target area is a seam, calculating a key position corresponding to the target area according to a black point in a corresponding image in the target area; and comparing the key position corresponding to the target area with the key position of the standard graph corresponding to the seam to obtain the similarity.
In an embodiment of the present application, the targeted noise includes: any one or more of additive noise, multiplicative noise, quantization noise, gaussian noise, impulse noise, rayleigh noise, gamma noise, exponential noise, and uniform noise.
In an embodiment of the present application, the preprocessing method includes: any one or more of spatial domain filtering, transform domain filtering, partial differential equations, variational methods, and morphological noise filters.
In order to achieve the above objects and other related objects, the present application provides a cigarette appearance detecting device, the device includes: the acquisition module is used for acquiring a panoramic image scanned by 360 degrees on the outer surface of the cigarette to be detected; the processing module is used for preprocessing the panoramic image to remove noise and segmenting the preprocessed panoramic image to find a target area; and comparing the corresponding image in the target area with the standard image to obtain corresponding similarity so as to generate appearance quality evaluation and defect information corresponding to the cigarette to be detected.
In order to achieve the above objects and other related objects, the present application provides a cigarette appearance detecting apparatus, the apparatus comprising: a memory, and a processor; the memory is used for storing a computer program; the processor runs the computer program to realize the cigarette appearance detection method.
In order to achieve the above objects and other related objects, the present application provides a cigarette appearance detecting system, the system comprising: the cigarette appearance detection equipment and the image acquisition device are used for detecting the appearance of the cigarette; the image acquisition device includes: a rotary clamping mechanism, a camera, and a pair of light sources; the rotary clamping mechanism is used for fixing and rotating a cigarette to be tested, and the rotary clamping mechanism, the camera and the pair of light sources are synchronously started to acquire a panoramic image scanned by 360 degrees on the outer surface of the cigarette to be tested.
To achieve the above and other related objects, the present application provides a computer storage medium storing a computer program, where the computer program is executed to execute the cigarette appearance detecting method.
As described above, according to the cigarette appearance detection method, the device, the equipment, the system and the medium, a panoramic image scanned by 360 degrees on the outer surface of the cigarette to be detected is obtained; preprocessing the panoramic image to remove noise, and segmenting the preprocessed panoramic image to find a target area; and comparing the corresponding image in the target area with the standard image to obtain corresponding similarity so as to generate appearance quality evaluation and defect information corresponding to the cigarette to be detected.
Has the following beneficial effects:
can reduce the image distortion, improve and detect the accuracy, need not to shoot many photos or need many cameras to shoot to can the time detect cigarette outward appearance and embossed seal and provide more automatic evaluation result.
Drawings
Fig. 1 is a schematic flow chart illustrating a cigarette appearance inspection method according to an embodiment of the present disclosure.
Fig. 2 is a schematic view of a scene of an image capturing device according to an embodiment of the present disclosure.
Fig. 3 is a model diagram illustrating a neural network segmentation method according to an embodiment of the present invention.
Fig. 4 is a model diagram illustrating a binarization process and a transformation 01 matrix according to an embodiment of the present invention.
Fig. 5 is a schematic diagram of a comparison model between a standard graph and a matching graph according to an embodiment of the present application.
FIG. 6 is a model diagram illustrating the calculation of the seam center position according to an embodiment of the present invention.
Fig. 7 is a schematic block diagram of a cigarette appearance inspection device according to an embodiment of the present disclosure.
Fig. 8 is a schematic structural diagram of a cigarette appearance inspection apparatus according to an embodiment of the present disclosure.
Fig. 9 is a schematic structural diagram of a cigarette appearance inspection system according to an embodiment of the present disclosure.
Detailed Description
The following description of the embodiments of the present application is provided by way of specific examples, and other advantages and effects of the present application will be readily apparent to those skilled in the art from the disclosure herein. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present application. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present application, and the drawings only show the components related to the present invention rather than the number, shape and size of the components in practical implementation, and the type, amount and ratio of the components in practical implementation can be changed freely, and the layout of the components may be more complicated.
Fig. 1 is a schematic flow chart of a cigarette appearance detection method according to an embodiment of the present application. As shown, the method comprises:
step S101: acquiring a panoramic image of 360-degree scanning of the outer surface of the cigarette to be detected.
In this embodiment, with many different angle pictures of common needs shooting, or the way of shooting through a plurality of cameras is different, this application only needs a camera to only need an image (360 degrees scanned panoramic image) can realize a cigarette outward appearance and detect.
In this embodiment, the 360-degree scanned panoramic image may also be a 360-degree scanned panoramic image formed of a plurality of video frames obtained by capturing a video.
In an embodiment of the present application, obtaining a panoramic image of the outer surface of the cigarette to be tested by 360 degrees may be accomplished through a scene schematic diagram of an image capturing device shown in fig. 2. As shown, the image capture device includes a rotary clamping mechanism, a pair of light sources, and a camera.
During image acquisition, start image acquisition device adds the rotating part of holding the mechanism by the rotation according to synchronous phase pulse signal, drives the portion of holding that adds of fixed cigarette through the belt and rotates, and the light source is polished simultaneously, and the camera carries out the surface of synchronous pair cigarette and scans the formation of image (including video or image). Compared with the prior art, the method has the advantages that a flat color image can be obtained after scanning and recording, image distortion is reduced, accuracy is higher, and post-processing is facilitated.
Specifically, as shown in the image capturing device in fig. 2, the holding portion of the rotary holding mechanism for holding the cigarette may be further divided into an upper chuck plate or a lower chuck plate. The rotation of upper chuck is in order to corresponding image that obtains a cigarette lower half, perhaps, the rotation of lower chuck is in order to obtain the image of a cigarette first, then the image of a cigarette lower half splices with the image of a cigarette first to obtain the panoramic picture of the 360 degrees scans of a cigarette surface that awaits measuring.
It should be noted that the image capturing device shown in fig. 2 is also a component of the cigarette appearance detecting system in the present application.
In another embodiment of the present application, a cigarette can also be fixed by a fixed part, the light source and the camera remain relatively fixed, through making light source and camera relative to a cigarette is rotatory to acquire the panoramic picture of a cigarette surface 360 degrees scans. For example, a circular slide rail may be provided, the light source and the camera are relatively fixed on the circular slide rail, when the acquisition is started, the light source and the camera move according to a track of the circular slide rail, and the light source and the camera always face the cigarette to be detected; or, the bottom of the device of fixed cigarette is equipped with the bearing, and the bearing can be relative the cigarette props up and rotates, on the bearing with light source and camera are fixed through a connecting rod, when beginning to shoot, the bearing is rotatory and drives light source and camera rotate in order to realize around a cigarette. Above two kinds of modes all can acquire the panoramic picture of the 360 degrees scans of a cigarette surface that awaits measuring.
Certainly, this application the panoramic picture of the 360 degrees scans of cigarette surface that awaits measuring can also be that other modes obtain, in this application, step S101 mainly emphasizes what to obtain is panoramic picture, does not emphasize in this step, panoramic picture' S the acquisition mode or utilized which device, for example, can also utilize the present panoramic picture that the photo of many different angles or the photo concatenation of a plurality of cameras shooting different angles of different angles forms.
Step S102: and preprocessing the panoramic image to remove noise, and segmenting the preprocessed panoramic image to find a target area.
In an embodiment of the present application, the targeted noise includes: any one or more of additive noise, multiplicative noise, quantization noise, gaussian noise, impulse noise, rayleigh noise, gamma noise, exponential noise, and uniform noise.
By the method, the obtained panoramic image of the outer surface of the cigarette to be detected scanned by 360 degrees can include, but is not limited to, the noise listed above, so that the panoramic image also needs to be subjected to denoising pretreatment.
The additive noise is uncorrelated with the image signal strength, e.g., the noise of the scanned image from a television camera that "channel noise" introduced by the image during transmission.
The multiplicative noise and image signal are correlated and tend to vary with changes in the image signal, such as noise in a flying spot scan image, television scan raster, film grain causes, and the like.
The quantization noise is the main noise source of the digital image, and the size of the noise shows the difference between the digital image and the original image, and the best method for reducing the noise is to adopt the optimization measure of selecting the grade according to the gray-scale probability density function.
Impulse noise (salt and pepper noise), such noises as white dots on a black image caused by image segmentation, black dot noise on a white image, errors introduced in a transform domain, transform noise caused by inverse transformation of an image, and the like.
From the probability of noise, the noise may be classified into gaussian noise, rayleigh noise, gamma noise, exponential noise, and uniform noise. They are expressed in terms of Probability Density (PDF) and are classified mainly as follows: 1) gaussian noise; 2) impulse noise (salt and pepper noise); 3) rayleigh noise; 4) gamma noise; 5) exponentially distributed noise; 6) and (4) uniform noise.
In order to remove the noise, the corresponding preprocessing method comprises the following steps: any one or more of spatial domain filtering, transform domain filtering, partial differential equations, variational methods, and morphological noise filters.
In this embodiment, the pretreatment method includes, but is not limited to, the above-mentioned methods.
1) Spatial domain filtering
The spatial filtering is to directly perform data operation on the original image and process the gray value of the pixel. Common space domain image denoising algorithms include a neighborhood averaging method, median filtering, low-pass filtering and the like.
2) Transform domain filtering
The image transformation domain denoising method is to transform an image into a transformation domain from a space domain, process a transformation coefficient in the transformation domain, and transform the image into the space domain from the transformation domain by inverse transformation, so as to achieve the purpose of removing image noise. There are many transformation methods for converting an image from a spatial domain to a transform domain, such as fourier transform, walsh-hadamard transform, cosine transform, K-L transform, wavelet transform, and the like. Fourier transform and wavelet transform are common transformation methods for image denoising.
3) Partial differential equation
The method mainly aims at low-layer image processing and obtains good effect. The edge is well maintained while removing noise. The application of partial differential equations can be mainly divided into two types, namely a basic iteration format, in which images gradually approach to the desired effect through updating along with time, and subsequent work after the images are improved. This method has the ability to smooth the image and sharpen the edges. The partial differential equation obtains a good effect in the image processing with low noise density, but the denoising effect is not good when the image with high noise density is processed, and the processing time is obviously much longer.
4) Variation method
The other method for denoising the image by using mathematics is based on the idea of a variational method, determines an energy function of the image, and enables the image to reach a smooth state by minimizing the energy function, so that a fully-variational TV model which is widely applied is the same. The key of the method is to find a proper energy equation, ensure the stability of evolution and obtain an ideal result.
5) Morphological noise filter
The combination of open and close can be used for filtering noise, firstly, the open operation is carried out on the image with noise, the size of the structure element matrix can be selected to be larger than that of the noise, and therefore, the result of the open operation is to remove the background noise; and performing closed operation on the image obtained in the previous step to remove noise on the image. Therefore, the method is suitable for the image types that the sizes of objects in the images are large, and the images have no tiny details, so that the image denoising effect is good.
In an embodiment of the present application, the method for segmenting the preprocessed panoramic image for finding the target area includes: obtaining a linear decision function by training a multilayer perceptron based on a neural network; classifying pixels of the panoramic image by using the decision function to obtain one or more non-overlapping subregions; and finding the target area from all the sub-areas according to preset target data.
In this embodiment, after processing the good noise of the panoramic image, we need to segment the target region in the whole image, and divide the video image into a plurality of non-overlapping sub-regions, so that each sub-region has a certain similarity, and different sub-regions have a relatively obvious difference. Video image segmentation is the basic preprocessing work of tasks such as image recognition, scene understanding, object detection and the like.
In this embodiment, a segmentation method based on a neural network is adopted, a linear decision function is obtained by training a multi-layer perceptron, and then the decision function is used to classify pixels to achieve the purpose of segmentation. Fig. 3 is a schematic model diagram of a neural network segmentation method. Through training, the purpose of segmentation can be achieved by defining or labeling the pixels and realizing classification.
For a general optical image, some pixels are extracted to be used for expressing an object, which can be regarded as a classification problem, that is, each pixel is labeled to find out the pixel corresponding to the label of the interested type; it may also be a clustering problem, i.e. the labels of the pixels are not known, but the pixels can be classified by some features.
In this embodiment, the target area is found from all the sub-areas according to the preset target data by the above-mentioned denoising and dividing of the panoramic image. For example, through training, a pixel corresponding to a steel seal is set as a target area (a steel seal pixel outline or a shape), and then the target area is found by presetting the corresponding steel seal pixel as target data. The level of this classification is often not for pixels, but for some given classification, or defined object, or image itself.
Step S103: and comparing the corresponding image in the target area with the standard image to obtain corresponding similarity so as to generate appearance quality evaluation and defect information corresponding to the cigarette to be detected.
It should be noted that, in the present application, for differences of the target regions, corresponding comparison and corresponding similarity obtaining methods are also slightly different, and the details are described in the following description.
In an embodiment of the present application, the method for comparing the corresponding image in the target region with the standard image to obtain the corresponding similarity includes:
A. and when the target area is the steel seal, comparing the standard graph corresponding to the steel seal with each pixel point of the corresponding image in the target area.
In this embodiment, after the target area (steel seal) is obtained, the degree of recognition of the image is obtained by comparing the images, and since the image obtained in the scanning mode is used in the early stage, which is a 1:1 image, the comparison of the pixels is used for the comparison of the images of the steel seal.
B. If the pixel point is equal to the pixel point, the pixel point is marked as a similar point.
C. And counting the proportion of the number of the similar points to the number of all the pixels to obtain the similarity.
In this embodiment, binarization processing may be performed on the pixel points in the image corresponding to the target region, and then the pixel points are converted into a 01 matrix, as shown in fig. 4, so as to compare the pixel points with a standard graph. Or, the standard map is also binarized and converted into 01 matrix in advance.
It should be noted that, the design of the embossed seal on the cigarette usually needs very simple and not very complex figures or patterns, such as vector diagrams (clear when arbitrarily enlarged or reduced), so that the corresponding image and/or standard diagram in the target area is converted into a 01 matrix, which greatly facilitates the comparison with the standard diagram.
Then comparing the standard image with each pixel point of the corresponding image in the target area, wherein the standard image and each pixel point are processed into a 01 matrix, and the number of the similar points between the two images can be obtained by directly comparing the two images through scanning, as shown in fig. 5, the number of the similar points is obtained by dividing the total number of the similar points by the number of the similar points, and the number is the similarity between 0 and 1.
In this embodiment, a qualified threshold is set, so as to obtain the appearance quality evaluation of the cigarette to be tested according to whether the similarity reaches the qualified threshold, and meanwhile, if the similarity is not qualified, it can be known where the defect occurs, or the comparison result is used as data to form defect information.
In an embodiment of the present application, the method for comparing the corresponding image in the target region with the standard image to obtain the corresponding similarity includes:
A. and when the target area is a seam, calculating the key position corresponding to the target area according to the black point in the corresponding image in the target area.
B. And comparing the key position corresponding to the target area with the key position of the standard graph corresponding to the seam to obtain the similarity.
In this embodiment, for cigarette seams, the present application mainly uses the center of gravity method to obtain the seam position.
Specifically, the alignment of the positions is mainly performed. The center of gravity can be calculated to determine in which area the black dots are mainly concentrated.
Each black point is cyclically scanned and their abscissa and ordinate are summed to obtain the sum of the abscissa and the ordinate. And dividing the number of the points by the number of the points to obtain an average horizontal coordinate and an average vertical coordinate. And dividing the total length of the horizontal and vertical coordinates by the total length of the horizontal and vertical coordinates to obtain two numbers in the interval of 0-1, which represents the gravity center of the joint, and the gravity center can be basically determined as the position of the center point of the joint, as shown in fig. 6.
In conclusion, the 360-degree panoramic image of the detected cigarette is compared and analyzed, and then the qualified judgment rule of the standard cigarette is referred, so that whether the cigarette is qualified or not and the reason of the unqualified cigarette are finally obtained. And evaluating the quality results of the steel seal and the appearance of the current cigarette to be tested by extracting and comparing each outline of the image to generate corresponding quality evaluation and defect data.
Fig. 7 is a schematic block diagram of a cigarette appearance inspection device according to an embodiment of the present invention. As shown, the apparatus 700 includes:
the acquisition module 701 is used for acquiring a panoramic image scanned by 360 degrees on the outer surface of the cigarette to be detected;
a processing module 702, configured to pre-process the panoramic image to remove noise, and segment the pre-processed panoramic image to find a target area; and comparing the corresponding image in the target area with the standard image to obtain corresponding similarity so as to generate appearance quality evaluation and defect information corresponding to the cigarette to be detected.
It can be understood that the cigarette appearance detection device 400 can implement the cigarette appearance detection method shown in fig. 1 through the operation of the modules.
It should be noted that the division of the modules of the above apparatus is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity, or may be physically separated. And these units can be implemented entirely in software, invoked by a processing element; or may be implemented entirely in hardware; and part of the modules can be realized in the form of calling software by the processing element, and part of the modules can be realized in the form of hardware. For example, the processing module 702 may be a separate processing element, or may be integrated into a chip of the apparatus, or may be stored in a memory of the apparatus in the form of program code, and a processing element of the apparatus calls and executes the functions of the processing module 702. Other modules are implemented similarly. In addition, all or part of the modules can be integrated together or can be independently realized. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.
For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), among others. For another example, when one of the above modules is implemented in the form of a Processing element scheduler code, the Processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).
Fig. 8 is a schematic structural view of a cigarette appearance inspection apparatus according to an embodiment of the present invention. As shown, the cigarette appearance detecting apparatus 800 includes: a memory 801, and a processor 802; the memory 801 is used for storing computer programs; the processor 802 runs a computer program to implement the cigarette appearance detection method as shown in fig. 1.
The Memory 801 may include a Random Access Memory (RAM), and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory.
The Processor 802 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
Fig. 9 is a schematic structural view of a cigarette appearance inspection system according to an embodiment of the present invention. As shown, the cigarette appearance detecting system 900 includes: a cigarette appearance detecting device 910 shown in fig. 8, and an image collecting device 920 shown in fig. 2.
The image capture device 920 includes: a rotary clamping mechanism 921, a camera 922, and a pair of light sources 923; rotatory adding mechanism 921 is used for fixing and the rotatory cigarette that awaits measuring, through synchronous start rotatory adding mechanism 921, camera 922 and a pair of light source 923 to acquire the panoramic picture of the 360 degrees scans of a cigarette surface that awaits measuring.
Specifically, the clamping portion of the rotary clamping mechanism 921 for clamping the cigarette may be an upper chuck or a lower chuck. The rotation of upper chuck is in order to corresponding image that obtains a cigarette lower half, perhaps, the rotation of lower chuck is in order to obtain the image of a cigarette first, then the image of a cigarette lower half splices with the image of a cigarette first to obtain the panoramic picture of the 360 degrees scans of a cigarette surface that awaits measuring.
In another embodiment of this application, image acquisition device can also be through a fixed part fixed cigarette, the light source keeps relatively fixed with the camera, through make light source and camera for cigarette rotation to acquire the panoramic picture of a cigarette surface 360 degrees scans. For example, a circular slide rail may be provided, the light source and the camera are relatively fixed on the circular slide rail, when the acquisition is started, the light source and the camera move according to a track of the circular slide rail, and the light source and the camera always face the cigarette to be detected; or, the bottom of the device of fixed cigarette props up is equipped with the bearing, and the bearing can be relative the cigarette props up and rotates, on the bearing with light source and camera are fixed through a connecting rod, when beginning to shoot, the bearing is rotatory and drives light source and camera rotate in order to realize around a cigarette to acquire the panoramic picture of the 360 degrees scans of a cigarette surface that awaits measuring.
In an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program is executed by a processor to implement the cigarette appearance detecting method as shown in fig. 1.
The computer-readable storage medium, as will be appreciated by one of ordinary skill in the art: the embodiment for realizing the functions of the system and each unit can be realized by hardware related to computer programs. The aforementioned computer program may be stored in a computer readable storage medium. When the program is executed, the embodiment including the functions of the system and the units is executed; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
In summary, the cigarette appearance detection method, the device, the equipment, the system and the medium thereof provided by the application acquire a panoramic image scanned by 360 degrees on the outer surface of the cigarette to be detected; preprocessing the panoramic image to remove noise, and segmenting the preprocessed panoramic image to find a target area; and comparing the corresponding image in the target area with the standard image to obtain corresponding similarity so as to generate appearance quality evaluation and defect information corresponding to the cigarette to be detected.
The application effectively overcomes various defects in the prior art and has high industrial utilization value.
The above embodiments are merely illustrative of the principles and utilities of the present application and are not intended to limit the invention. Any person skilled in the art can modify or change the above-described embodiments without departing from the spirit and scope of the present application. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present application.

Claims (10)

1. A cigarette appearance detection method is characterized by comprising the following steps:
acquiring a panoramic image scanned by 360 degrees on the outer surface of a cigarette to be detected;
preprocessing the panoramic image to remove noise, and segmenting the preprocessed panoramic image to find a target area;
and comparing the corresponding image in the target area with the standard image to obtain corresponding similarity so as to generate appearance quality evaluation and defect information corresponding to the cigarette to be detected.
2. The cigarette appearance detection method according to claim 1, wherein the method for segmenting the preprocessed panoramic image to find the target area comprises:
Obtaining a linear decision function by training a multilayer perceptron based on a neural network;
classifying pixels of the panoramic image by using the decision function to obtain one or more non-overlapping subregions;
and finding the target area from all the sub-areas according to preset target data.
3. The cigarette appearance detection method according to claim 1, wherein the method for comparing the corresponding image in the target area with the standard image to obtain the corresponding similarity comprises:
when the target area is a steel seal, comparing the standard graph corresponding to the steel seal with each pixel point of the corresponding image in the target area;
if the pixel points are equal to the pixel points, marking as similar points;
and counting the proportion of the number of the similar points to the number of all the pixels to obtain the similarity.
4. The cigarette appearance detection method according to claim 1, wherein the method for comparing the corresponding image in the target area with the standard image to obtain the corresponding similarity comprises:
when the target area is a seam, calculating a key position corresponding to the target area according to a black point in a corresponding image in the target area;
And comparing the key position corresponding to the target area with the key position of the standard graph corresponding to the seam to obtain the similarity.
5. The cigarette appearance detection method according to claim 1, wherein the aimed noise includes: any one or more of additive noise, multiplicative noise, quantization noise, gaussian noise, impulse noise, rayleigh noise, gamma noise, exponential noise, and uniform noise.
6. The cigarette appearance detection method according to claim 1, wherein the pretreatment method comprises the following steps: any one or more of spatial domain filtering, transform domain filtering, partial differential equations, variational methods, and morphological noise filters.
7. A cigarette outward appearance detection device, its characterized in that, the device includes:
the acquisition module is used for acquiring a panoramic image scanned by 360 degrees on the outer surface of the cigarette to be detected;
the processing module is used for preprocessing the panoramic image to remove noise and segmenting the preprocessed panoramic image to find a target area; and comparing the corresponding image in the target area with the standard image to obtain corresponding similarity so as to generate appearance quality evaluation and defect information corresponding to the cigarette to be detected.
8. A cigarette appearance inspection apparatus, comprising: a memory, and a processor; the memory is used for storing a computer program; the processor runs a computer program to realize the cigarette appearance detection method according to any one of claims 1 to 6.
9. A cigarette appearance inspection system, comprising: the cigarette appearance inspection apparatus according to claim 8, and an image acquisition device; the image acquisition device includes: a rotary clamping mechanism, a camera, and a pair of light sources; the rotary clamping mechanism is used for fixing and rotating a cigarette to be tested, and the rotary clamping mechanism, the camera and the pair of light sources are synchronously started to acquire a panoramic image scanned by 360 degrees on the outer surface of the cigarette to be tested.
10. A computer storage medium, characterized in that a computer program is stored, and when executed, the computer program performs the cigarette appearance detection method according to any one of claims 1 to 6.
CN201910430854.6A 2019-05-22 2019-05-22 Cigarette appearance detection method and device, equipment, system and medium thereof Active CN111972700B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910430854.6A CN111972700B (en) 2019-05-22 2019-05-22 Cigarette appearance detection method and device, equipment, system and medium thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910430854.6A CN111972700B (en) 2019-05-22 2019-05-22 Cigarette appearance detection method and device, equipment, system and medium thereof

Publications (2)

Publication Number Publication Date
CN111972700A true CN111972700A (en) 2020-11-24
CN111972700B CN111972700B (en) 2023-04-25

Family

ID=73436009

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910430854.6A Active CN111972700B (en) 2019-05-22 2019-05-22 Cigarette appearance detection method and device, equipment, system and medium thereof

Country Status (1)

Country Link
CN (1) CN111972700B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113439870A (en) * 2021-06-29 2021-09-28 国家烟草质量监督检验中心 Cigar appearance classification method and cigar appearance classification device
CN114568741A (en) * 2022-04-01 2022-06-03 郑州市卓旺机电设备有限公司 Cigarette quality online detection device of cigarette making machine and use method thereof
CN115553491A (en) * 2022-11-11 2023-01-03 湖北中烟工业有限责任公司 Window cigarette missing detection method and device and electronic equipment
IT202100023954A1 (en) * 2021-09-17 2023-03-17 Gd Spa Assembly apparatus and assembly method for producing multi-component smoking articles.
IT202100023942A1 (en) * 2021-09-17 2023-03-17 Gd Spa Method and system for inspecting smoking articles
CN116210953A (en) * 2023-04-17 2023-06-06 浙江中烟工业有限责任公司 Asymmetric sectional control method and device for cigarette weight

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103868935A (en) * 2014-02-14 2014-06-18 中国科学院合肥物质科学研究院 Cigarette appearance quality detection method based on computer vision
CN107527422A (en) * 2017-07-03 2017-12-29 深圳怡化电脑股份有限公司 A kind of offset printing is to print detection method, device, terminal device and readable storage medium storing program for executing
CN107543828A (en) * 2017-08-25 2018-01-05 广东工业大学 A kind of Surface Flaw Detection method and system
CN108107054A (en) * 2017-12-08 2018-06-01 云南昆船设计研究院 A kind of online cigarette defective vision detecting system and method
CN108647677A (en) * 2018-05-14 2018-10-12 山东师范大学 The ammeter appearance and performance intelligent detecting method and device that view-based access control model calculates
CN108982512A (en) * 2018-06-28 2018-12-11 芜湖新尚捷智能信息科技有限公司 A kind of circuit board detecting system and method based on machine vision
CN109242853A (en) * 2018-11-05 2019-01-18 南京信息工程大学 A kind of PCB defect intelligent detecting method based on image procossing
CN109583489A (en) * 2018-11-22 2019-04-05 中国科学院自动化研究所 Defect classifying identification method, device, computer equipment and storage medium

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103868935A (en) * 2014-02-14 2014-06-18 中国科学院合肥物质科学研究院 Cigarette appearance quality detection method based on computer vision
CN107527422A (en) * 2017-07-03 2017-12-29 深圳怡化电脑股份有限公司 A kind of offset printing is to print detection method, device, terminal device and readable storage medium storing program for executing
CN107543828A (en) * 2017-08-25 2018-01-05 广东工业大学 A kind of Surface Flaw Detection method and system
CN108107054A (en) * 2017-12-08 2018-06-01 云南昆船设计研究院 A kind of online cigarette defective vision detecting system and method
CN108647677A (en) * 2018-05-14 2018-10-12 山东师范大学 The ammeter appearance and performance intelligent detecting method and device that view-based access control model calculates
CN108982512A (en) * 2018-06-28 2018-12-11 芜湖新尚捷智能信息科技有限公司 A kind of circuit board detecting system and method based on machine vision
CN109242853A (en) * 2018-11-05 2019-01-18 南京信息工程大学 A kind of PCB defect intelligent detecting method based on image procossing
CN109583489A (en) * 2018-11-22 2019-04-05 中国科学院自动化研究所 Defect classifying identification method, device, computer equipment and storage medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
彭瑞云,李杨主编: "《形态计量与图像分析学》", 31 December 2012 *

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113439870A (en) * 2021-06-29 2021-09-28 国家烟草质量监督检验中心 Cigar appearance classification method and cigar appearance classification device
IT202100023954A1 (en) * 2021-09-17 2023-03-17 Gd Spa Assembly apparatus and assembly method for producing multi-component smoking articles.
IT202100023942A1 (en) * 2021-09-17 2023-03-17 Gd Spa Method and system for inspecting smoking articles
WO2023042112A3 (en) * 2021-09-17 2023-04-27 G.D S.P.A. Method and system for inspecting smoking articles
WO2023042113A3 (en) * 2021-09-17 2023-04-27 G.D S.P.A. Assembling apparatus and assembling method for producing multicomponent smoking articles
CN114568741A (en) * 2022-04-01 2022-06-03 郑州市卓旺机电设备有限公司 Cigarette quality online detection device of cigarette making machine and use method thereof
CN115553491A (en) * 2022-11-11 2023-01-03 湖北中烟工业有限责任公司 Window cigarette missing detection method and device and electronic equipment
CN115553491B (en) * 2022-11-11 2023-11-24 湖北中烟工业有限责任公司 Window cigarette white leakage detection method and device and electronic equipment
CN116210953A (en) * 2023-04-17 2023-06-06 浙江中烟工业有限责任公司 Asymmetric sectional control method and device for cigarette weight

Also Published As

Publication number Publication date
CN111972700B (en) 2023-04-25

Similar Documents

Publication Publication Date Title
CN111972700A (en) Cigarette appearance detection method and device, equipment, system and medium thereof
Ahmed Comparative study among Sobel, Prewitt and Canny edge detection operators used in image processing
CN106934803B (en) method and device for detecting surface defects of electronic device
JP5443435B2 (en) Tire defect detection method
RU2653461C2 (en) Glare detection in the image data frame
RU2659745C1 (en) Reconstruction of the document from document image series
KR20130030220A (en) Fast obstacle detection
CN114998314B (en) PCB defect detection method based on computer vision
CN112288726B (en) Method for detecting foreign matters on belt surface of underground belt conveyor
CN114494259A (en) Cloth defect detection method based on artificial intelligence
CN104408707A (en) Rapid digital imaging fuzzy identification and restored image quality assessment method
WO2017120796A1 (en) Pavement distress detection method and apparatus, and electronic device
CN110189375A (en) A kind of images steganalysis method based on monocular vision measurement
Liang et al. Deep bilateral retinex for low-light image enhancement
Kumar et al. A comparative study of various filtering techniques
US9094617B2 (en) Methods and systems for real-time image-capture feedback
Apdilah et al. A study of Frei-Chen approach for edge detection
CN116843611A (en) Hardware surface flaw detection system based on difference and graph neural network
CN115184362B (en) Rapid defect detection method based on structured light projection
CN116958058A (en) Lens dirt detection method and device and image detection equipment
CN115908399A (en) Magnetic sheet flaw detection method based on improved visual attention mechanism
Joodi et al. A proposed 3-stage CNN classification model based on augmentation and denoising
CN118275449B (en) Copper strip surface defect detection method, device and equipment
CN118628500B (en) Method and system for detecting vacuum coating defects of watch case based on image processing
Mol et al. A survey on restoration of paintings

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant