JP7284674B2 - Reference image generation device, inspection device, alignment device, and reference image generation method - Google Patents

Description

The present invention relates to a technique for generating a reference image used for comparison with an image of a pattern in the manufacturing process of a substrate having a pattern on its surface.

2. Description of the Related Art Conventionally, in the manufacturing process of semiconductor substrates, printed wiring boards, and the like, visual inspections are performed to determine whether the substrates are good or bad. In visual inspection of semiconductor substrates, for example, defects are detected by comparing a plurality of dies provided on one substrate. Specifically, an image obtained by imaging one die is used as a reference image, an image obtained by imaging another die is used as an image to be inspected, and the image to be inspected is compared with the reference image to determine the difference. To detect. However, this inspection cannot detect the same defect that exists on multiple dies. In some cases, substrates such as photomasks and reticles do not have identical patterns for comparison.

Therefore, in Patent Document 1, regarding a circuit pattern formed on a substrate of a semiconductor wafer, a CAD created from a SEM image obtained by imaging the circuit pattern with a scanning electron microscope (SEM) and design data (CAD data) of the circuit pattern Techniques have been proposed for detecting defects on SEM images by comparing images.

JP 2015-7563 A

By the way, when generating a reference image from design data as described above, it is important to generate the reference image easily in a short time. However, Patent Document 1 describes that a CAD image, which is a reference image for appearance inspection, is created by creating CADPloy data from CAD data to create a CAD image, but does not describe a specific creation method. do not have.

Also, when an engineer tries to create a reference image from CAD data, a skilled engineer needs to build a creation logic based on experience for each of the various patterns indicated by the CAD data. requires a great deal of time (eg, several months to several years). Furthermore, the quality of the generated reference images depends on the skill of the technician.

SUMMARY OF THE INVENTION An object of the present invention is to shorten the lead time until reference image generation.

According to a first aspect of the present invention, there is provided a reference image generating apparatus for generating a reference image used for comparison with an image of the pattern in a manufacturing process of a substrate having a pattern on its surface, the method comprising: By deep learning using an input unit for inputting learning data that is a combination of design data and a learning image obtained by imaging the pattern, and a learning data set that is a collection of the learning data, A learning unit that creates a learned model by learning the relationship between the pattern design data and the learning image, and a reference image generation unit that generates a reference image from the pattern design data using the learned model. .

The invention according to claim 2 is the reference image generation device according to claim 1, wherein the learning data set includes one learning data, design data of the one learning data, and the one learning data. and other training data that is a combination of the training image of the training data with a training image that has been modified in brightness or contrast.

The invention according to claim 3 is the reference image generation device according to claim 1 or 2, wherein the learning data set includes one learning data and design data of the one learning data that is rotated. Alternatively, it includes other learning data that is a combination of the inverted design data and the learning image of the one learning data that is rotated or inverted in the same manner as the design data.

The invention according to claim 4 is the reference image generating device according to any one of claims 1 to 3, wherein each learning data of the learning data set is provided with the pattern on the substrate. It is a combination of the pattern design data and the learning image in a partial area that is a part of the pattern area that is set, and the position of the partial area of each learning data in the pattern area is determined at random.

The invention according to claim 5 is the reference image generating apparatus according to any one of claims 1 to 4, wherein each learning data of the learning data set is provided with the pattern on the substrate. is a combination of the pattern design data and the learning image in a partial area that is a part of the pattern area of the pattern area, and each position of the pattern area corresponds to one of the learning data in the learning data set is included in the partial area to be performed.

The invention according to claim 6 is the reference image generating apparatus according to any one of claims 1 to 5, wherein a plurality of pattern areas each provided with the pattern are arranged on the substrate. and the learning data set includes a plurality of learning data that are combinations of the pattern design data and the learning image in each of the plurality of pattern regions.

The invention according to claim 7 is the reference image generating apparatus according to any one of claims 1 to 6, wherein the learning data set is a plurality of substrates each having the pattern on its surface. It includes a plurality of learning data that are combinations of the pattern design data and the learning image.

According to an eighth aspect of the invention, there is provided an inspection apparatus for inspecting a substrate having a pattern on its surface, comprising: an imaging unit for capturing an image of the pattern on the substrate to obtain an image to be inspected; and the image to be inspected. and an inspection unit that inspects the presence or absence of defects in the substrate by comparing with the reference image of the pattern generated by the reference image generation device according to any one of 1 to 7.

According to a ninth aspect of the invention, there is provided an alignment apparatus for adjusting the position of a substrate having a pattern on its surface, comprising: an imaging unit for capturing an image of the pattern on the substrate to obtain a target image; an alignment unit that acquires the position of the substrate by comparing it with the reference image of the pattern generated by the reference image generation device according to any one of 1 to 7; and the position of the substrate that is acquired by the alignment unit. and a substrate moving mechanism that relatively moves the substrate to adjust the position based on the above.

According to a tenth aspect of the invention, there is provided a reference image generating method for generating a reference image used for comparison with an image of the pattern in a manufacturing process of a substrate having a pattern on its surface, comprising: a) a step of inputting learning data that is a combination of pattern design data and a learning image obtained by imaging the pattern; and b) deep learning using a learning data set that is a set of the learning data. creating a learned model by learning the relationship between the pattern design data and the learning image; and c) using the learned model to generate a reference image from the pattern design data. Prepare.

The invention according to claim 11 is the reference image generation method according to claim 10, wherein the learning data set includes one learning data, design data of the one learning data, and the one learning data. and other training data that is a combination of the training image of the training data with a training image that has been modified in brightness or contrast.

The invention according to claim 12 is the reference image generation method according to claim 10 or 11, wherein the learning data set includes one learning data and design data of the one learning data. Alternatively, it includes other learning data that is a combination of the inverted design data and the learning image of the one learning data that is rotated or inverted in the same manner as the design data.

The invention according to claim 13 is the reference image generation method according to any one of claims 10 to 12, wherein each learning data of the learning data set is provided with the pattern on the substrate. It is a combination of the pattern design data and the learning image in a partial area that is a part of the pattern area that is set, and the position of the partial area of each learning data in the pattern area is determined at random.

The invention according to claim 14 is the reference image generation method according to any one of claims 10 to 13, wherein each learning data of the learning data set is provided with the pattern on the substrate. is a combination of the pattern design data and the learning image in a partial area that is a part of the pattern area of the pattern area, and each position of the pattern area corresponds to one of the learning data in the learning data set is included in the partial area to be performed.

The invention according to claim 15 is the reference image generating method according to any one of claims 10 to 14, wherein a plurality of pattern areas each provided with the pattern are arranged on the substrate. and the learning data set includes a plurality of learning data that are combinations of the pattern design data and the learning image in each of the plurality of pattern regions.

The invention according to claim 16 is the reference image generation method according to any one of claims 10 to 15, wherein the learning data set includes It includes a plurality of learning data that are combinations of the pattern design data and the learning image.

According to the present invention, the lead time until reference image generation can be shortened.

It is a figure which shows the structure of an inspection apparatus. It is a figure which shows the structure of a 1st computer. It is a figure which shows the functional structure implement|achieved by a 1st computer. It is a figure which shows the structure of a 2nd computer. It is a figure which shows the functional structure implement|achieved by the 2nd computer. FIG. 4 is a diagram showing the flow of generation of a reference image; It is a figure which shows the flow of test|inspection of a board|substrate. It is a figure which shows the structure of an alignment apparatus. It is a figure which shows the functional structure implement|achieved by a 1st computer.

FIG. 1 is a diagram showing the configuration of an inspection apparatus 1 according to the first embodiment of the invention. The inspection apparatus 1 is, for example, an apparatus for inspecting the appearance of a semiconductor substrate 9 (hereinafter also simply referred to as "substrate 9"). A pattern is formed on the surface of the substrate 9 .

The inspection apparatus 1 includes an apparatus main body 2 for imaging the substrate 9, a first computer 3, and a second computer 4. As shown in FIG. Each of the first computer 3 and the second computer 4 is a processing device including an arithmetic unit. The first computer 3 also controls the overall operation of the inspection apparatus 1 . The second computer 4 is a reference image generation device that generates a reference image, which will be described later. The apparatus main body 2 has an imaging section 21 , a stage 22 that holds the substrate 9 , and a stage moving mechanism 23 . The imaging unit 21 acquires an image by imaging the pattern on the substrate 9 . The image is, for example, a multi-tone color image. The stage moving mechanism 23 relatively moves the stage 22 with respect to the imaging section 21 .

The imaging unit 21 has an illumination unit 211 that emits illumination light, an optical system 212 , and an imaging device 213 . The optical system 212 guides illumination light to the substrate 9 and guides light from the substrate 9 to the imaging device 213 . The imaging device 213 converts the image of the substrate 9 imaged by the optical system 212 into an electrical signal. The lighting unit 211 includes a lamp such as an LED or a light bulb, and optical elements such as a lens and a reflecting member that adjust the light from the lamp. The optical system 212 includes optical elements such as a plurality of lenses and half mirrors. The imaging device 213 is, for example, a two-dimensional imaging sensor. The imaging device 213 may be a one-dimensional imaging sensor. In this case, imaging is performed while the stage 22 is moved.

A stage moving mechanism 23 is composed of a ball screw, a guide rail, a motor, and the like. Of course, various mechanisms can be employed as the stage moving mechanism 23, and for example, a linear motor can be used. By the first computer 3 controlling the stage moving mechanism 23 and the imaging unit 21, the stage 22 moves in the horizontal direction and a desired area on the substrate 9 is imaged. The stage 22 is a holding portion that holds the substrate 9 . Holding the substrate 9 may be done in various ways. For example, a groove is formed in the stage 22 and the substrate 9 is sucked onto the stage 22 by suction from a suction port formed in the groove. A large number of suction ports may be formed in the stage 22 to suck the substrate 9 . The stage 22 may be formed of a porous material and suction may be applied from the porous material. The stage 22 may hold the substrate 9 by a mechanical mechanism.

FIG. 2 is a diagram showing the configuration of the first computer 3. As shown in FIG. The first computer 3 includes a CPU 31, a ROM 32, a RAM 33, a fixed disk 34, a display 35, an input unit 36, a reader 37, a communication unit 38, a GPU 39, and a bus 30. It has a computer system configuration. The CPU 31 performs various arithmetic processing. The GPU 39 performs various types of arithmetic processing related to image processing. The ROM 32 stores basic programs. The RAM 33 stores various information. The fixed disk 34 stores information. The display 35 displays various information such as images. The input unit 36 includes a keyboard 36a and a mouse 36b that receive inputs from the operator. The reader 37 reads information from a computer-readable recording medium 81 such as an optical disk, magnetic disk, magneto-optical disk, or memory card. A display 35, a keyboard 36a, a mouse 36b and a reader 37 are connected to the bus 30 via an interface I/F. The communication unit 38 transmits and receives signals to and from other components of the inspection apparatus 1 and external devices. Bus 30 is a signal circuit that connects CPU 31 , GPU 39 , ROM 32 , RAM 33 , fixed disk 34 , display 35 , input section 36 , reading device 37 and communication section 38 .

In the first computer 3 , the program 811 is read from the recording medium 81 via the reading device 37 in advance and stored in the fixed disk 34 . Program 811 may be stored on fixed disk 34 via a network. The CPU 31 and GPU 39 execute arithmetic processing while using the RAM 33 and fixed disk 34 according to the program 811 . The CPU 31 and GPU 39 function as arithmetic units in the first computer 3 . A configuration other than the CPU 31 and the GPU 39 may be employed that functions as an arithmetic unit.

FIG. 3 is a diagram showing a functional configuration realized by the first computer 3 executing arithmetic processing and the like according to the program 811. As shown in FIG. These functional configurations include a storage unit 301 , an inspection unit 302 and a control unit 303 . All or part of these functions may be realized by a dedicated electric circuit. Also, these functions may be realized by a plurality of computers. Of the functional configuration shown in FIG. 3, the inspection unit 302 and the control unit 303 are implemented by the CPU 31, GPU 39, ROM 32, RAM 33, fixed disk 34, and their peripheral configuration. Storage unit 301 is mainly implemented by RAM 33 and fixed disk 34 .

The storage unit 301 stores an image of the pattern on the substrate 9 acquired by the imaging unit 21 (hereinafter also referred to as an “inspection image”), a reference image used for inspection of the substrate 9, and the like. The reference image is an image showing a pattern on substrate 9 that is substantially free of defects, and is generated by second computer 4, as will be described later. The inspection unit 302 compares the image to be inspected with the reference image to inspect the presence or absence of defects in the substrate 9 . The control unit 303 controls the imaging unit 21, the stage moving mechanism 23, and the operation of each functional configuration.

FIG. 4 is a diagram showing the configuration of the second computer 4. As shown in FIG. The second computer 4 includes a CPU 41, a ROM 42, a RAM 43, a fixed disk 44, a display 45, an input unit 46, a reader 47, a communication unit 48, and a GPU 49, in substantially the same manner as the first computer 3. , and a bus 40. The CPU 41 performs various arithmetic processing. The GPU 49 performs various kinds of arithmetic processing related to image processing. The ROM 42 stores basic programs. The RAM 43 stores various information. A fixed disk 44 stores information. The display 45 displays various information such as images. The input unit 46 includes a keyboard 46a and a mouse 46b that receive inputs from the operator. The reader 47 reads information from a computer-readable recording medium 82 such as an optical disk, magnetic disk, magneto-optical disk, memory card, or the like. A display 45, a keyboard 46a, a mouse 46b and a reader 47 are connected to the bus 40 via an interface I/F. The communication unit 48 transmits and receives signals to and from other components of the inspection device 1 and external devices. A bus 40 is a signal circuit that connects the CPU 41 , GPU 49 , ROM 42 , RAM 43 , fixed disk 44 , display 45 , input section 46 , reader 47 and communication section 48 .

In the second computer 4 , the program 821 is read from the recording medium 82 via the reader 47 in advance and stored in the fixed disk 44 . Program 821 may be stored on fixed disk 44 via a network. The CPU 41 and GPU 49 execute arithmetic processing while using the RAM 43 and fixed disk 44 according to the program 821 . The CPU 41 and GPU 49 function as arithmetic units in the second computer 4 . A configuration other than the CPU 41 and the GPU 49 that functions as an arithmetic unit may be employed.

FIG. 5 is a diagram showing a functional configuration realized by the second computer 4 executing arithmetic processing and the like according to the program 821. As shown in FIG. These functional configurations include an input unit 401 , a learning unit 402 , a reference image generation unit 403 and a storage unit 404 . All or part of these functions may be realized by a dedicated electric circuit. Also, these functions may be realized by a plurality of computers. Of the functional configuration shown in FIG. 5, the input unit 401, the learning unit 402, and the reference image generation unit 403 are implemented by the CPU 41, GPU 49, ROM 42, RAM 43, fixed disk 44, and their peripheral configuration. Also, the storage unit 404 is mainly implemented by the RAM 43 and the fixed disk 44 .

The input unit 401 inputs learning data to the storage unit 404 . The storage unit 404 stores a learning data set, which is a set of many learning data. The learning data is a combination of pattern design data on the substrate 9 and a learning image obtained by imaging a pattern formed on the substrate 9 that has substantially no defects. . The learning image included in the learning data is, for example, a part of one die among a plurality of dies arranged on the substrate 9 (that is, a plurality of pattern areas each provided with the pattern). It is an image of a partial area of a certain predetermined size. In this case, the design data included in the learning data is the design data of the part included in the partial area corresponding to the learning image in the pattern. The design data is, for example, CAD data which is vector data, vertex image data generated from the CAD data, or run length data generated by rasterizing the vertex image data. The design data may be in other forms of data.

The learning unit 402 causes the initial model to learn the relationship between the pattern design data on the board 9 and the learning image by deep learning (for example, GAN (hostile generation network)) using the learning data set described above. Create a trained model. A trained model is stored in the storage unit 404 . Details of the training data set will be described later. The reference image generation unit 403 uses the learned model stored in the storage unit 404 to generate a reference image (that is, an image showing a pattern of a good product with substantially no defects) from pattern design data. The reference image is stored in the storage section 301 of the first computer 3 .

FIG. 6 is a diagram showing the flow of reference image generation in the second computer 4 . In generating a reference image, first, a learning data set, which is a set of many learning data, is prepared (step S11). As described above, each piece of learning data is a combination of pattern design data on the substrate 9 and a learning image obtained by imaging the pattern. Although the number of learning data included in the learning data set is not limited, it is approximately 10,000, for example.

A plurality of learning data included in the learning data set are prepared, for example, by the following method. First, in the inspection apparatus 1 , the stage 22 holds a non-defective substrate 9 (that is, a learning substrate 9 ). Then, one die is selected from the plurality of dies arranged on the substrate 9, and the imaging unit 21 captures an image of the entire pattern on the selected die. Imaging by the imaging unit 21 is performed by scanning or step-and-repeat, for example. The image of the die captured by the imaging unit 21 is stored in the storage unit 301 of the first computer 3 .

Subsequently, in the first computer 3, the image of the die is equally divided into a plurality of partial images of a predetermined size (for example, 512 pixels×512 pixels) arranged vertically and horizontally in a matrix, and each partial image is used for learning. image. Then, the learning data is created by combining the learning image with the data of the area (that is, the partial area) corresponding to the learning image in the above-described die design data. The plurality of learning images described above are arranged in a matrix without overlapping adjacent learning images, and constitute the entire image of one die. In other words, each position on the die is included in a partial area corresponding to one of the plurality of learning images. Therefore, the entire pattern on the die can be included in the training data set. In addition, each of the plurality of learning images may partially overlap another training image that is adjacent vertically and horizontally. Also, the size of the partial image described above may be changed as appropriate.

A learning data set (that is, a set of a plurality of learning data) prepared in the first computer 3 is sent to the second computer 4 and input to the storage section 404 by the input section 401 (step S12). The image of the die imaged by the imaging unit 21 may be sent to the second computer 4, and the second computer 4 may create learning data (that is, prepare a learning data set).

Subsequently, in the learning unit 402 of the second computer 4, learning of an initial model for generating a reference image is performed by deep learning using the learning data set. The learning unit 402 creates a trained model by making the initial model learn the relationship between the design data of the pattern and the learning image of the pattern (step S13). The learned model is stored in the storage unit 404 . Design data of patterns on the substrate 9 to be inspected by the inspection apparatus 1 is also stored in advance in the storage unit 404 .

When the learned model has been created, the reference image generation unit 403 generates a reference image using the learned model from the design data stored in the storage unit 404 (step S14). The reference image generated in step S<b>14 is sent from the second computer 4 to the first computer 3 and stored in the storage section 301 . The reference image is used for inspection of the board 9 by the inspection section 302 of the first computer 3 .

In the second computer 4, learning by deep learning in the learning unit 402 (step S13) and generation of a reference image in the reference image generation unit 403 (step S14) are performed by, for example, Pix2Pix, PointNet, or a combination thereof. will be In step S13, for example, Adam (Adaptive moment estimation) and error backpropagation are used as methods for updating internal parameters in deep learning. Also, as a reference for the error between the output image and the original image, for example, the L1 error (that is, the sum of the absolute values of the differences between the pixel values), the L2 error (that is, the sum of the squares of the differences between the pixel values), or the intersection Entropy error is used. Updating of the internal parameters is performed using, for example, a mini-batch learning method. The unit of a mini-batch and the number of epochs are not limited, but are 4 and 50, for example. The updating of the internal parameters does not necessarily have to be repeated a predetermined number of times, and the end of updating may be determined based on the error value or transition.

FIG. 7 is a diagram showing the flow of inspection of the board 9 in the inspection apparatus 1. As shown in FIG. In the inspection apparatus 1 , first, the substrate 9 to be inspected is held by the stage 22 . Then, one die is selected from a plurality of dies arranged on the substrate 9, and the entire pattern on the selected die is imaged by the imaging unit 21 (step S21). Imaging by the imaging unit 21 is performed by scanning or step-and-repeat, for example. An image of the die captured by the imaging unit 21 (that is, an image to be inspected) is stored in the storage unit 301 of the first computer 3 .

Then, the inspecting unit 302 compares the image to be inspected (that is, the image of the pattern) stored in the storage unit 301 with the reference image described above, and classifies the image to be inspected having a significant difference as "defective". The other images to be inspected are classified as "no defect" (step S22). For the substrate 9 classified as "defective", the position and size of the defect, defect image data, etc. are acquired and displayed on the display 35 (see FIG. 2) or the like. The comparison between the image to be inspected and the reference image may be performed by various known methods (for example, the difference comparison method and the shake comparison method). In the inspection apparatus 1 , the above inspection is sequentially performed for a plurality of dies on the substrate 9 . Further, when the inspection of one board 9 is completed, the next board 9 is inspected.

In the inspection apparatus 1, in generating the reference image (steps S11 to S14) described above, various learning data may be included in the learning data set in addition to the learning data illustrated above. For example, in step S11, the plurality of learning images are not necessarily obtained by equally dividing the die image into a matrix. The clipped partial image may be used as the learning image described above. In this case, the cutout positions of the plurality of learning images (that is, the positions on the die of the partial regions corresponding to the respective learning images) may be randomly determined. As a result, for various pattern elements included in the pattern on the die, a plurality of learning data with different combinations of pattern element positions on the learning image and pattern elements included in the learning image are stored in the learning data set. can be included. Note that the cutout positions of the plurality of learning images may be determined regularly.

When the cut-out position of the learning image is determined randomly, for example, with one vertex at the upper left of the die as the origin, the x-coordinate and y-coordinate (that is, the position in the horizontal direction and the vertical direction) are randomized using random numbers or the like. is determined by Subsequently, with the determined x-coordinate and y-coordinate as the upper left origin, the partial area of the predetermined size is set on the die image. When the entire partial area is included in the die (that is, the pattern area), a partial image corresponding to the partial area is cut out as a learning image. Then, the clipped image for learning and the design data corresponding to the partial area are combined to create data for learning.

On the other hand, if the partial area protrudes from the die, the partial image corresponding to the partial area is not cut out as a learning image, and learning data is not created. Alternatively, after the position of the partial area is shifted vertically and/or horizontally so that the entire partial area is included in the die, the partial image corresponding to the partial area may be cut out as the learning image. In this case, it is preferable that the amount of shift in the vertical and horizontal directions of the partial area is made as small as possible. Then, the clipped image for learning and the design data corresponding to the partial area are combined to create data for learning.

Further, in step S11, when one learning data that is a combination of the design data and the learning image is created, new learning data may be created using the one learning data. .

For example, a new learning image is created by changing at least one of brightness and contrast of the learning image of the one learning data, and the new learning image and the design data of the one learning data are combined. By combining, new learning data is created. Changing the brightness and contrast of the learning image may be performed by various known methods. The new learning data is included in the learning data set together with the one learning data. As a result, the influence of imaging conditions (for example, individual differences in imaging units and external factors such as temperature and atmospheric pressure) on images, as well as individual differences in dies or substrates (for example, differences caused by subtle changes in process conditions). ), it is possible to generate a reference image with high robustness in consideration of the difference of images due to As a result, even if the brightness and contrast of the inspection image obtained in step S21 fluctuate, the inspection image and the reference image can be compared with high accuracy in step S22.

Further, for example, a new learning image is created by rotating or reversing the learning image of the one learning data described above, and the design data of the one learning data is converted to the learning image in the same manner as the learning image. New design data that is rotated or flipped is created. Then, new design data and new learning images are combined to create new learning data. Rotation and flipping of design data and training images may be performed by various known methods. The new learning data is included in the learning data set together with the one learning data. As a result, it is possible to create a trained model capable of generating reference images corresponding to patterns facing various directions with high accuracy.

In step S11, a plurality of dies on the substrate 9 may be imaged by the imaging unit 21, and a learning image may be obtained from each of the images of the plurality of dies to create a plurality of learning data. In other words, the learning data set includes a plurality of learning data that are combinations of pattern design data and learning images for each of a plurality of dies (that is, a plurality of pattern regions). Thereby, it is possible to acquire a plurality of learning images corresponding to the same design data from a plurality of dies located at different positions on the substrate. As a result, it is possible to create a plurality of learning data in which one piece of design data is combined with a plurality of learning images having different brightness, contrast, line widths of pattern elements, and the like.

Further, in step S11, images of the plurality of substrates 9 may be captured by the imaging unit 21, and learning images may be obtained from the images of the plurality of substrates to create a plurality of learning data. In other words, the learning data set includes a plurality of learning data that are combinations of pattern design data and learning images for each of the plurality of substrates 9 . As a result, it is possible to acquire a plurality of learning images corresponding to the same design data from a plurality of substrates 9, for which there is a possibility that the process conditions or the like at the time of manufacturing have changed subtly. As a result, it is possible to create a plurality of learning data in which one piece of design data is combined with a plurality of learning images having different brightness, contrast, line widths of pattern elements, and the like.

As explained above, the second computer 4 is a reference image generation device that generates a reference image. The reference image is used for comparison with the image of the pattern in the manufacturing process (the inspection process in the above example) of the substrate 9 having the pattern on its surface. The reference image generation device includes an input unit 401 , a learning unit 402 and a reference image generation unit 403 . The input unit 401 inputs learning data that is a combination of pattern design data on the substrate 9 and a learning image obtained by imaging the pattern. The learning unit 402 creates a trained model by learning the relationship between pattern design data and a learning image by deep learning using a learning data set, which is a collection of learning data. A reference image generation unit 403 generates a reference image from pattern design data using a learned model.

As a result, preparation for reference image generation can be completed in a very short period of time (for example, one day) compared to the case where engineers create logic for generating reference images from design data (work period: several months to several years). can be completed. That is, it is possible to greatly shorten the lead time until reference image generation. As a result, the reference image can be easily generated in a short time.

The reference image generation method described above includes a step of inputting learning data that is a combination of pattern design data on the substrate 9 and a learning image obtained by imaging the pattern (step S12); A step of creating a trained model by learning the relationship between pattern design data and a learning image by deep learning using a learning data set that is a set of (step S13); and generating a reference image from the pattern design data (step S14). As a result, the lead time until the reference image is generated can be greatly shortened, as in the above case.

As described above, the learning data set includes one learning data, design data of the one learning data, and a learning image obtained by changing the brightness or contrast of the learning image of the one learning data. and other learning data that is a combination. By changing the luminance, it is possible to learn in consideration of the luminance fluctuation of the learning image caused by the uneven illuminance of the illumination unit 211 of the imaging unit 21, the difference in the sensitivity characteristics of the imaging device 213, and the fluctuation of temperature and atmospheric pressure. Become. In addition, by changing the contrast, it is possible to perform learning in consideration of contrast variations between pattern elements and contrast variations between the pattern elements and the background in the learning image due to variations in pattern film thickness and the like. Therefore, as described above, it is possible to generate a reference image that is highly robust and capable of improving the uniformity of comparison results. Moreover, since a plurality of pieces of learning data can be created from one learning image, the number of pieces of learning data included in the learning data set can be easily increased. As a result, a highly accurate reference image can be generated.

As described above, the learning data set includes one learning data, design data obtained by rotating or inverting the design data of the one learning data, and a learning image of the one learning data as the design data. and other training data that is a combination of similarly rotated or flipped training images. As a result, it is possible to create a trained model capable of generating reference images corresponding to patterns facing various directions with high accuracy. Moreover, since a plurality of pieces of learning data can be created from one learning image, the number of pieces of learning data included in the learning data set can be easily increased. As a result, a highly accurate reference image can be generated.

As described above, each learning data in the learning data set includes pattern design data and learning data in a partial area that is a part of a pattern area (in the above example, the die) on which a pattern is provided on the substrate 9 . In combination with an image, it is preferable that the positions of the partial areas of each learning data in the pattern area are randomly determined. As a result, for various pattern elements included in patterns on the pattern area, a plurality of learning data having different positions and combinations of pattern elements on the learning image can be included in the learning data set. As a result, it is possible to generate a reference image that is highly robust and capable of improving the uniformity of comparison results.

As described above, each learning data in the learning data set includes pattern design data and learning data in a partial area that is a part of a pattern area (in the above example, the die) on which a pattern is provided on the substrate 9 . It is a combination with an image, and each position of the pattern area is preferably included in a partial area corresponding to any learning data of the learning data set. Thereby, it is possible to generate a reference image that can be appropriately compared with any part of the pattern area.

As described above, when a plurality of pattern areas (in the above example, dies) each having a pattern are arranged on the substrate 9, the learning data set includes patterns in each of the plurality of pattern areas. preferably includes a plurality of training data that are combinations of design data and training images. Thereby, it is possible to acquire a plurality of learning images corresponding to the same design data from a plurality of pattern regions at different positions on the substrate. Therefore, it is possible to create a plurality of learning data in which one piece of design data is combined with a plurality of learning images having different brightness, contrast, line widths of pattern elements, and the like. As a result, it is possible to generate a reference image that is highly robust and capable of improving the uniformity of comparison results.

As described above, the learning data set preferably includes a plurality of learning data that are combinations of pattern design data and learning images for each of the plurality of substrates 9 having patterns on their surfaces. As a result, it is possible to acquire a plurality of learning images corresponding to the same design data from a plurality of substrates 9, for which there is a possibility that the process conditions or the like at the time of manufacturing have changed subtly. Therefore, it is possible to create a plurality of learning data in which one piece of design data is combined with a plurality of learning images having different brightness, contrast, line widths of pattern elements, and the like. As a result, it is possible to generate a reference image that is highly robust and capable of improving the uniformity of comparison results.

As described above, the inspection device 1 includes the imaging section 21 and the inspection section 302 . The imaging unit 21 captures an image of the pattern on the substrate 9 to obtain an inspection image. The inspection unit 302 compares the image to be inspected with the reference image of the pattern generated by the reference image generation device (that is, the second computer 4) to inspect the substrate 9 for defects. As described above, the reference image generation device can shorten the lead time until reference image generation. Therefore, in the inspection apparatus 1, the defect inspection of the substrate 9 can be performed quickly. In addition, the reference image generation device can generate a reference image that is highly robust and capable of improving the uniformity of comparison results. Therefore, in the inspection apparatus 1, defect inspection of the substrate 9 can be performed with high accuracy.

In the inspection apparatus 1, the learned model may be re-learned when the lot of the board 9 to be inspected is changed. In the re-learning of the learned model, for example, a non-defective board 9 is extracted from a new lot to be inspected, and a new data set for learning is prepared by imaging the board 9 (FIG. 6: step S11 ). Then, the learned model is re-learned by a procedure substantially similar to steps S12 to S14 described above. As a result, the defect inspection of the substrate 9 can be performed with higher accuracy. The same applies to the alignment device 1a described below.

FIG. 8 is a diagram showing the configuration of an alignment device 1a according to the second embodiment of the present invention. The alignment device 1a is a device for adjusting the position of a substrate 9 having a pattern on its surface. Alignment apparatus 1a is included in, for example, a processing apparatus that performs various processes on substrate 9 . The processing apparatus is, for example, an inspection apparatus that compares a plurality of dies provided on one substrate 9 to detect defects, or a drawing apparatus that irradiates the substrate 9 with light to perform drawing. The processing apparatus includes, for example, a processing head that performs various processes on the substrate 9 .

The alignment apparatus 1 a has substantially the same configuration as the inspection apparatus 1 except that the functional configuration realized by the first computer 3 is different. In the following description, the configurations of the alignment device 1a corresponding to the configurations of the inspection device 1 are given the same reference numerals. The alignment apparatus 1 a includes an apparatus main body 2 , a first computer 3 and a second computer 4 . The configurations of the device main body 2, the first computer 3 and the second computer 4, and the functional configurations realized by the second computer 4 are substantially the same as those shown in FIGS.

FIG. 9 is a diagram showing a functional configuration realized by the first computer 3 of the alignment apparatus 1a executing arithmetic processing and the like according to the program 811 (see FIG. 2). These functional configurations include a storage section 301 , an alignment section 304 and a control section 303 . All or part of these functions may be realized by a dedicated electric circuit. Also, these functions may be realized by a plurality of computers. Of the functional configuration shown in FIG. 9, the alignment unit 304 and the control unit 303 are implemented by the CPU 31, GPU 39, ROM 32, RAM 33, fixed disk 34 (see FIG. 2), and their peripheral configuration. Storage unit 301 is mainly implemented by RAM 33 and fixed disk 34 .

The storage unit 301 stores an image of the pattern on the substrate 9 (hereinafter also referred to as a “target image”) acquired by the imaging unit 21 (see FIG. 8), a reference image used for alignment of the substrate 9, and the like. Remember. The reference image is an image of the pattern on the substrate 9 used for alignment (hereinafter also referred to as "alignment pattern"), and is generated by the second computer 4 as described later. The alignment pattern may be a part of the circuit pattern or the like on the substrate 9, or may be a mark dedicated to alignment. The alignment unit 304 acquires the position of the substrate 9 by comparing the target image with the reference image. The control unit 303 controls the imaging unit 21, the stage moving mechanism 23, and the operation of each functional configuration.

In the second computer 4, similarly to the above, a learned model is created by deep learning using a learning data set that is a set of learning data (that is, a combination of alignment pattern design data and learning images). be. Then, using the trained model, a reference image is generated from the design data of the alignment pattern (steps S11 to S14). In steps S11 to S14, the reference image of the alignment pattern (that is, the alignment template image) can be generated from the design data. can easily obtain a reference image. The reference image is sent from the second computer 4 to the first computer 3 and stored in the storage section 301 .

In the first computer 3, the alignment unit 304 compares the target image and the reference image stored in the storage unit 301, and extracts an alignment pattern corresponding to the alignment pattern of the reference image from the target image. Subsequently, the position of the alignment pattern in the target image is obtained. Then, the deviation between the position of the alignment pattern in the target image and the position of the desired alignment pattern (that is, the design position) is obtained. The controller 303 controls the stage moving mechanism 23 based on the deviation, thereby moving the substrate 9 so that the alignment pattern on the substrate 9 is positioned at a desired position. Note that the stage moving mechanism 23 does not necessarily have to move the substrate 9 , and may move the above-described processing head that processes the substrate 9 . That is, the stage moving mechanism 23 is a substrate moving mechanism that adjusts the relative position of the substrate 9 by relatively moving the substrate 9 with respect to the processing head.

As described above, the alignment apparatus 1a includes the imaging unit 21, the alignment unit 304, and the substrate moving mechanism (the stage moving mechanism 23 in the above example). The imaging unit 21 captures an image of the pattern on the substrate 9 to acquire a target image. The alignment unit 304 acquires the position of the substrate 9 by comparing the target image with the pattern reference image generated by the above-described reference image generation device (that is, the second computer 4). The substrate moving mechanism adjusts the position by relatively moving the substrate 9 based on the position of the substrate 9 obtained by the alignment section 304 . As described above, the reference image generation device can shorten the lead time until reference image generation. Therefore, alignment of the substrate 9 can be performed quickly in the alignment apparatus 1a. In addition, the reference image generation device can generate a reference image that is highly robust and capable of improving the uniformity of comparison results. Therefore, the alignment device 1a can align the substrate 9 with high accuracy.

Various modifications can be made to the above-described reference image generation device, reference image generation method, inspection device 1, and alignment device 1a.

For example, the learning data set prepared in step S11, including acquisition of learning images, may be created outside the inspection device 1 and input to the inspection device 1 via a recording disk or network. The same applies to the alignment device 1a.

The learning data set described above does not necessarily include learning data for each of the plurality of substrates 9 . Also, the learning data set described above does not necessarily include learning data for each of the plurality of pattern regions (die in the above example) on the substrate 9 . Note that the plurality of pattern areas may be other than the die. Moreover, it is not always necessary to arrange a plurality of pattern areas on the substrate 9 .

In the learning data set described above, each position of the pattern area does not necessarily have to be included in a partial area corresponding to any learning data (that is, an area that is part of the pattern area). Further, each piece of learning data does not necessarily have to be a combination of pattern design data and a learning image in a partial area of the pattern area. For example, a combination of pattern design data and a learning image in the entire pattern area may be included in the learning data set as one piece of learning data.

The training data set described above does not necessarily include training data obtained by changing the brightness or contrast of the training image. Also, the training data set does not necessarily include training data obtained by rotating or flipping the training image.

The substrate 9 handled by the reference image generation device, the inspection device 1 and the alignment device 1a described above is not limited to a semiconductor substrate, and may be a flat panel display device such as a liquid crystal display device or an organic EL (Electro Luminescence) display device. ) or glass substrates used in other display devices. Further, the substrate 9 may be an optical disk substrate, a magnetic disk substrate, a magneto-optical disk substrate, a photomask substrate, a ceramic substrate, a solar cell substrate, or the like.

In the inspection apparatus 1 and the alignment apparatus 1a, the first computer 3 and the second computer 4 may be housed inside the housing of the apparatus main body 2. FIG.

The second computer 4 may be included in an apparatus other than the inspection apparatus 1 and the alignment apparatus 1a. Also, the second computer 4 may be used alone as a reference image generation device.

The configurations in the above embodiment and each modified example may be combined as appropriate as long as they do not contradict each other.

1 inspection device 1a alignment device 4 second computer 9 substrate 21 imaging unit 23 stage movement mechanism 302 inspection unit 304 alignment unit 401 input unit 402 learning unit 403 reference image generation unit S11 to S14, S21 to S22 steps

Claims (16)

A reference image generating device for generating a reference image used for comparison with an image of the pattern in a manufacturing process of a substrate having a pattern on its surface,
an input unit for inputting learning data that is a combination of pattern design data on a substrate and a learning image obtained by imaging the pattern;
a learning unit that creates a trained model by learning the relationship between the pattern design data and the learning image by deep learning using a learning data set that is a collection of the learning data;
a reference image generation unit that generates a reference image from pattern design data using the learned model;
A reference image generation device comprising: The reference image generation device according to claim 1,
The learning data set is
one training data;
Other learning data that is a combination of the design data of the one learning data and a learning image obtained by changing the brightness or contrast of the learning image of the one learning data;
A reference image generation device comprising: The reference image generation device according to claim 1 or 2,
The learning data set is
one training data;
Design data obtained by rotating or reversing the design data of the one learning data and a learning image obtained by rotating or reversing the learning image of the one learning data in the same manner as the design data training data;
A reference image generation device comprising: The reference image generation device according to any one of claims 1 to 3,
each learning data of the learning data set is a combination of design data of the pattern and a learning image in a partial area that is a part of the pattern area in which the pattern is provided on the substrate;
The reference image generation device, wherein the positions of the partial areas of the learning data in the pattern area are randomly determined. The reference image generation device according to any one of claims 1 to 4,
each learning data of the learning data set is a combination of design data of the pattern and a learning image in a partial area that is a part of the pattern area in which the pattern is provided on the substrate;
The reference image generation device, wherein each position of the pattern area is included in the partial area corresponding to one of the learning data in the learning data set. The reference image generation device according to any one of claims 1 to 5,
A plurality of pattern regions each provided with the pattern are arranged on the substrate,
The reference image generation device, wherein the learning data set includes a plurality of learning data that are combinations of the pattern design data and the learning image in each of the plurality of pattern regions. The reference image generation device according to any one of claims 1 to 6,
The reference image generating apparatus, wherein the learning data set includes a plurality of learning data that are combinations of design data and learning images of the patterns for each of a plurality of substrates having the patterns on their surfaces. . An inspection apparatus for inspecting a substrate having a pattern on its surface,
an imaging unit that captures an image of the pattern on the board to obtain an image to be inspected;
an inspection unit that compares the image to be inspected with a reference image of the pattern generated by the reference image generation device according to any one of claims 1 to 7, and inspects the presence or absence of defects in the substrate;
An inspection device comprising: An alignment apparatus for adjusting the position of a substrate having a pattern on its surface, comprising:
an imaging unit that captures an image of a pattern on a substrate to obtain a target image;
an alignment unit that acquires the position of the substrate by comparing the target image with a reference image of the pattern generated by the reference image generating device according to any one of claims 1 to 7;
a substrate moving mechanism that relatively moves and adjusts the position of the substrate based on the position of the substrate obtained by the alignment unit;
An alignment device comprising: A reference image generation method for generating a reference image used for comparison with an image of the pattern in a manufacturing process of a substrate having a pattern on its surface, comprising:
a) inputting learning data that is a combination of pattern design data on a substrate and a learning image obtained by imaging the pattern;
b) creating a learned model by learning the relationship between the pattern design data and the learning image by deep learning using the learning data set, which is a collection of the learning data;
c) generating a reference image from pattern design data using the trained model;
A reference image generation method, comprising: A reference image generation method according to claim 10,
The learning data set is
one training data;
Other learning data that is a combination of the design data of the one learning data and a learning image obtained by changing the brightness or contrast of the learning image of the one learning data;
A reference image generation method, comprising: The reference image generation method according to claim 10 or 11,
The learning data set is
one training data;
Design data obtained by rotating or reversing the design data of the one learning data and a learning image obtained by rotating or reversing the learning image of the one learning data in the same manner as the design data training data;
A reference image generation method, comprising: A reference image generation method according to any one of claims 10 to 12,
each learning data of the learning data set is a combination of design data of the pattern and a learning image in a partial area that is a part of the pattern area in which the pattern is provided on the substrate;
A reference image generating method, wherein positions of the partial areas of the learning data in the pattern area are randomly determined. A reference image generation method according to any one of claims 10 to 13,
each learning data of the learning data set is a combination of design data of the pattern and a learning image in a partial area that is a part of the pattern area in which the pattern is provided on the substrate;
A reference image generation method, wherein each position of the pattern area is included in the partial area corresponding to any one of the learning data in the learning data set. A reference image generation method according to any one of claims 10 to 14,
A plurality of pattern regions each provided with the pattern are arranged on the substrate,
The reference image generating method, wherein the learning data set includes a plurality of learning data that are combinations of the pattern design data and the learning image in each of the plurality of pattern regions. A reference image generating method according to any one of claims 10 to 15,
The reference image generation method, wherein the learning data set includes a plurality of learning data that are combinations of design data and learning images of the patterns for each of a plurality of substrates having the patterns on their surfaces. .

Images