Artificial intelligence-based material defect detection system and method considering the type and distribution of actual defect images

Abstract

A multi-sensor handover system capable of tracking a moving object and a method of providing a parking service therein are disclosed. A computing device used in the handover system includes a communication unit which is a communication connection path between a first sensor monitoring a first handover area and a second sensor monitoring a second handover area, and a handover unit which acquires a first image from the first sensor, acquires a second image from the second sensor, detects an exit of a moving object from the first handover area through the acquired first image, detects an entry of a moving object into the second handover area through the acquired second image, and determines whether a moving object that has entered the second handover area through the detected exit and entry of the moving object is the same moving object that has exited the first handover area. Here, the second handover area is an area that is matched with the first handover area.

Description

[Technical Field]

[0001] The present invention relates to an artificial intelligence-based material defect detection system and method that takes into account the type and distribution of actual defect images. [Background technology]

[0002] Recently, with the development of artificial intelligence technology, the application of artificial intelligence to automated defect detection has been rapidly increasing. For example, S. Marino, A. Smolarz, and P. Beauseroy, “Potato defects classification and localization with convolutional neural networks,” in Fourteenth International Conference on Quality Control by Artificial Vision, vol. 11472, 2019, pp. 110-117. and H. Lin, B. Li, X. Wang, Y. Shu, and S. Niu, “Automated defect inspection of LED chips using deep convolutional neural networks,” Journal of Intelligent Manufacturing, vol. 30, pp. 2525-2534, 2019., used a deep learning technique called Class Activation Mapping (CAM) to automatically detect defects in potatoes and LED substrates, respectively. CAM is a technique that visualizes which regions of the input image an artificial neural network trained with a classifier observed to derive its classification results. In the above example, an artificial neural network is trained to classify good / defective products, and CAM is used as a tool to locate defects.

[0003] In order to train an artificial neural network for conventional automatic defect detection, a large number of images of good and defective products are required, but due to the characteristics of defects, it is difficult to acquire images of defects (for example, defects occur in the ppm range in semiconductors), which creates a data imbalance problem with images of good products, which are relatively easy to acquire.In addition, information on good and defective products is a trade secret, making it difficult to disclose, and there is also the problem of high difficulty in building a dataset. Summary of the Invention [Problem to be solved by the invention]

[0004] The present invention provides an artificial intelligence based material defect imaging method and defect detection system.

[0005] The present invention also provides an artificial intelligence-based material defect image generation method and defect detection system that can generate a large number of virtual images of good products and defects from a small number of defect images to build a training data set.

[0006] In addition, the present invention provides an artificial intelligence-based material defect image generation method and defect detection system that, when a defect image is input by photographing a virtual training data set, generates a non-defective product image that accurately corresponds to the defect image and is capable of training an artificial neural network.

[0007] Furthermore, the defect detection system of the present invention generates virtual defect images / virtual good product images with as diverse and uniform a distribution as possible, taking into account the types and distribution of actual defect images. A model trained using the virtual defect / good product images eliminates the problem of data imbalance depending on the type of defect image, and exhibits uniform performance in various situations that may be encountered in actual use. [Means for solving the problem]

[0008] To achieve the above-mentioned object, a defect detection system according to an embodiment of the present invention includes a training data generation unit that generates a plurality of virtual good product images or a plurality of virtual defect images using defect images, a learning unit that trains a model for defect detection using the generated virtual good product images or the generated virtual defect images, and a defect detection unit that detects the presence or absence of defects in an input image using the trained model, wherein the training data generation unit analyzes the types or distribution of the defect images to detect defect forms or background forms, and generates the virtual good product images or the virtual defect images with different types, numbers, or resolutions depending on the detected defect forms or background forms.

[0009] According to another embodiment of the present invention, a defect detection system includes a learning data generator that generates a plurality of virtual non-defect images or a plurality of virtual defect images using defect images, a learning unit that trains a model for defect detection using the generated virtual non-defect images or the generated virtual defect images, and a defect detection unit that detects the presence or absence of defects in an input image using the trained model. Here, the learning data generator determines the types, number, or resolution of the generated virtual non-defect images or virtual defect images by analyzing the types or distribution of the defect images using artificial intelligence, and determines different types, number, or resolutions of the generated virtual non-defect images or virtual defect images upon request from a user.

[0010] A defect detection method according to an embodiment of the present invention includes generating a plurality of virtual good product images or a plurality of virtual defect images using defect images, training a model for defect detection using the generated virtual good product images or the generated virtual defect images, and detecting the presence or absence of defects in an input image using the trained model, wherein the defect types or distributions of the defect images are analyzed to detect defect forms or background forms, and the types, number, or resolutions of the virtual good product images or the virtual defect images are varied depending on the detected defect forms or background forms. [Effects of the Invention]

[0011] According to an embodiment of the present invention, an artificial intelligence-based material defect detection system and method that takes into account the type and distribution of actual defect images is provided, thereby generating a good product image that accurately corresponds to an input defect image and effectively detecting unpredicted defect areas.

[0012] Furthermore, since the present invention is related to unsupervised learning in which learning can be performed without annotation information, it has the advantage of reducing the labor required in the process of generating annotation information.

[0013] Furthermore, the present invention has the advantage of reducing problems caused by data imbalance and insufficient number of data because it generates a large number of virtual good / defective images from a small number of defect images.

[0014] Furthermore, the present invention generates virtual images so that virtual defect images / virtual good product images have as diverse a variety and uniform distribution as possible, taking into account the types and distribution of actual defect images, and therefore the model trained with the corresponding virtual images can exhibit uniform performance in various situations that may be encountered in actual use. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a block diagram that schematically illustrates a defect detection system in accordance with an embodiment of the present invention; [Figure 2] 1 is a diagram illustrating an example of types and distributions of defect images; [Figure 3] 1 is a diagram illustrating a process of generating a virtual non-defective image using a defect image according to an embodiment of the present invention; [Figure 4] 1 is a diagram illustrating a process of generating a virtual non-defective image using a non-defective image according to an embodiment of the present invention; [Figure 5] 1 is a diagram illustrating a process of generating a virtual defect image using a defect image according to an embodiment of the present invention; [Figure 6] 10 is a diagram illustrating a process of converting a randomly generated virtual low-resolution defect image into a high-resolution defect image. [Figure 7] 1 is a diagram illustrating a defective area detection process according to an embodiment of the present invention; [Figure 8] 10 is a diagram illustrating a defect image generated by modifying the type and position of a defect in an original defect image according to another embodiment of the present invention; [Figure 9] 1 is a flowchart illustrating a model learning process according to an embodiment of the present invention. [Figure 10] 1 is a flowchart illustrating a defect detection method according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0016] As used herein, singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as "comprise" or "include" should not be interpreted as including all of the components or steps described in the specification, but should be interpreted as including some components or steps not included, or as including additional components or steps. Furthermore, terms such as "unit," "module," etc. used in the specification refer to a unit that processes at least one function or operation, and may be implemented in hardware or software, or a combination of hardware and software.

[0017] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. Figure 1 is a block diagram illustrating a defect detection system according to an embodiment of the present invention, Figure 2 is a diagram illustrating an example of the types and distribution of defect images, Figure 3 is a diagram illustrating a process of generating a virtual non-defective image using a defect image according to an embodiment of the present invention, Figure 4 is a diagram illustrating a process of generating a virtual non-defective image using a non-defective image according to an embodiment of the present invention, Figure 5 is a diagram illustrating a process of generating a virtual defect image using a defect image according to an embodiment of the present invention, Figure 6 is a diagram illustrating a process of converting a randomly generated virtual low-resolution defect image into a high-resolution defect image, Figure 7 is a diagram illustrating a defect area detection process according to an embodiment of the present invention, and Figure 8 is a diagram illustrating a defect image generated by modifying the type and position of defects in an original defect image according to another embodiment of the present invention.

[0018] Referring to FIG. 1, a defect detection system 100 according to an embodiment of the present invention includes a training data generation unit 110, a training unit 115, an image generation model 120, a defect detection unit 125, a memory 130, and a processor 135.

[0019] The learning data generating unit 110 analyzes the types and distributions of a small number of stored defect images, and generates a large number of virtual defect images or a large number of virtual non-defective product images based on the analysis results.

[0020] The learning data generation unit 110 includes an image type and distribution analysis unit 112, a non-defective image generation unit 114, and a defective image generation unit .

[0021] The image type and distribution analysis unit 112 analyzes the type and distribution of the input defect image and determines the type, number, resolution, etc. of the required virtual defect image or virtual non-defective image.

[0022] For example, assume that a defect image is input as an input image as shown in FIG. The image type and distribution analysis unit 112 classifies the defect shape and background shape in the input defect image and analyzes that there are two types of defects and three types of background. When analyzing the defect shape and background shape, the image type and distribution analysis unit 112 extracts hand-crafted features such as Haar-like features and histogram of oriented gradient from the input image and then uses clustering. The algorithm for analyzing the defect shape and background shape is not limited to the method using hand-crafted features and clustering.

[0023] Meanwhile, the image type and distribution analysis unit 112 can analyze the defect type and background type of one input image, or can analyze the defect type and background type of multiple input images as a whole. Here, the input image is an actual image, not a virtual image. The input image also includes an actual image detected as defective using the virtual non-defective image or virtual defective image of the present invention.

[0024] The non-defective image generating unit 114 uses the input defect images to generate the number of virtual non-defective images determined by the image type and distribution analyzing unit 112. In this case, the non-defective image generating unit 114 may generate different numbers of virtual non-defective images based on the analyzed defect shape, may generate different numbers of virtual non-defective images based on the analyzed background shape, or may generate different numbers of virtual non-defective images based on the analyzed defect shape and the analyzed background shape.

[0025] For example, the good image generator 114 removes the defect area from the defect image and then generates a virtual good image through a patch matching technique.

[0026] This will be explained in more detail. For example, assume that defect images are input as shown in Fig. 3. The non-defective image generating unit 114 removes the defect area from each of the input defect images to generate a virtual non-defective image.

[0027] For example, the good image generator 114 generates a good image based on the defect image using a patch matching technique. Specifically, the good image generator 114 generates the good image by removing a defect area from the defect image and restoring the defect area using information about the defect area. As shown in FIG. 3, the defect image does not include the same defect area but includes defects of various types.

[0028] Therefore, the good image generator 114 applies different imaging techniques according to the defect pattern to remove the defective area and then generates a good image.

[0029] As another example, the good-quality image generating unit 114 can generate a number of virtual good-quality images using the input good-quality images.

[0030] According to another embodiment, the good-quality image generating unit 114 may generate a virtual good-quality image by using both the defect image and the good-quality image. For example, the virtual good-quality image may be generated by removing a defect area from the defect image and then replacing the removed defect area with an area in the good-quality image corresponding to the removed defect area.

[0031] According to another embodiment, the good image generator 114 may generate a virtual good image using information about the vicinity of the defective area in the defective image or information about the area in the good image depending on the state of the defective area. For example, if the size of the defective area is large or if the surrounding area is also damaged, the virtual good image is generated by replacing the removed defective area with an area in the good image. If the size of the defective area is small, the virtual good image is generated using the information about the vicinity of the defective area.

[0032] This will be explained with reference to FIG. For example, the non-defective image generating unit 114 generates a non-defective image having a resolution equal to or greater than the reference resolution of the input non-defective image, and then randomly cuts out the image to generate a large number of virtual non-defective images.

[0033] For example, the good-quality image generating unit 114 generates a good-quality image having a resolution equal to or higher than the reference resolution using PSGAN, and then randomly crops the image as shown in FIG. 4 to generate a virtual good-quality image.

[0034] As another example, the non-defective image generating unit 114 may enlarge a virtual non-defective image generated from a defective image and then randomly cut it out to generate a number of non-defective images.

[0035] In summary, the non-defective product image generating unit 114 generates a large number of virtual non-defective product images using a small number of defect images. The defect image generator 116 generates a large number of virtual defect images using a small number of defect images.

[0036] For example, assume that a defect image as shown in FIG. 5 is input. The defect image generator 116 generates multiple virtual defect images using DCGAN. Here, DCGAN randomly generates images from latent variables. Since the result of DCGAN is limited to 64 x 64, to create a defect image with higher resolution, a super-resolution defect image is generated using CycleGAN, an artificial neural network capable of performing a super-resolution function. CycleGAN is an artificial neural network that performs unpaired image-to-image translation. By training one domain with low-resolution images and the other domain with high-resolution images, an artificial neural network that performs a super-resolution function can be obtained (see FIG. 6).

[0037] That is, the defect image generator 116 converts an input low-resolution defect image into a high-quality high-resolution defect image using DCGAN and CycleGAN, and then generates a plurality of virtual defect images through a random image conversion process. Of course, the algorithm is not limited to DCGAN and CycleGAN as long as it generates virtual defect images.

[0038] In Figure 5, the defect positions in the input image (defect image) and the defect positions in the generated virtual defect image are the same or similar. However, the defect positions in the virtual defect image may differ from the defect positions in the input image (see Figure 8). Also, the size or shape of the defect in the virtual defect image may differ from the size or shape of the defect in the input image.

[0039] For example, assuming that contaminants may be attached to the edge region of a substrate during a deposition process in semiconductor manufacturing, the defect image generator 116 uses an input image having a defect with contaminants attached to the center of the edge region of one side of the substrate to generate various virtual defect images having defects with contaminants attached to the center of the edge region of another side or on a non-center edge side, etc. In this case, it is assumed in advance that the contaminants may be attached to various locations on the edge during the process.

[0040] As another example, if the impact applied to the substrate during the process and the magnitude or range of the resulting cracks are preset, the defect image generator 116 generates multiple defect images with different crack depths, lengths, or positions from an input image of the substrate having cracks.

[0041] That is, the defect image generator 116 of the present invention can generate a virtual defect image having the same position, shape, or size as the defect in the input image, as well as a virtual defect image having a different position, shape, or size from the defect in the input image.

[0042] In addition, if the defect is a contaminant, the defect image generator 116 may generate a defect image having a contaminant different from the contaminant of the input image. In this case, the shape or size of the contaminant adhering to the substrate may vary depending on the contaminant.

[0043] Although the above description has been given of generating a virtual defect image for a single defect, it is also possible to generate a virtual defect image by combining a plurality of different types of defects. For example, by receiving an image of a defect with contaminants and an image of a defect with cracks, a virtual defect image in which contaminants or cracks are formed at various positions is generated.

[0044] According to another embodiment, the defect image generator 116 may generate a virtual defect image using not only a defect image but also a good product image. For example, various virtual defect images may be generated by extracting defects from the defect image and displaying the extracted defects at various positions in the good product image.

[0045] In summary, the training data generator 110 generates a large number of virtual training data sets for model training using a small number of defect images, and the large number of virtual training data sets are at least one of a large number of virtual good product images and virtual defect images.

[0046] Meanwhile, the learning data generating unit 110 may automatically operate the good product image generating unit 114 and the defect image generating unit 116 selectively or both depending on the defect type or background type of the defect image, or may operate the good product image generating unit 114 and the defect image generating unit 116 selectively or both depending on a user's request. For example, the learning data generating unit 110 may generate the number of virtual good product images or virtual defect images determined by the artificial intelligence, or the user may arbitrarily determine the number of virtual good product images or virtual defect images regardless of the number determined by the artificial intelligence.

[0047] In this way, once the training data set is generated by the training data generation unit 110, it is used to train a model. The learning unit 115 learns the image generation model 120 using at least one of the plurality of virtual non-defective images and the plurality of virtual defective images.

[0048] The learning unit 115 learns the model using at least one of a large number of virtual good product images and virtual defect images, so that the image generation model 120 is trained to generate good product images using defect images.

[0049] The image generation model 120 is trained by the learning unit 115 using a training dataset (at least one of a number of virtual good product images and virtual defect images), and then generates a comparison image (good product image or defect image) corresponding to the input image during the defect detection process.

[0050] For example, the image generation model 120 is trained using a large number of virtual good product images and virtual defect images, so that when a defect image is input, it can generate a corresponding good product image.

[0051] The defect detection unit 125 is a means for detecting the presence or absence of defects using an input image and a comparison image. For example, if the input image is a defective image, the comparison image is a virtual non-defective image corresponding to the defective image. Therefore, the defect detection unit 125 derives a difference image between the input image and the comparison image to detect a defective area.

[0052] The defective area detection process will be described in more detail with reference to FIG. For example, assuming that the input image is a defect image 610, a virtual good image as shown at 620 in Fig. 7 is generated through the learned image generation model 120. Then, the defect detection unit 125 derives a difference image between the defect image 610 and the virtual good image 620, and then detects a defect area through a hysteresis threshold and a morphology operation.

[0053] However, image generation model 120 generates an appropriate number of virtual good product images taking into account the defect shape or background shape of defect image 610. For example, image generation model 120 generates 10,000 virtual good product images having various backgrounds but the same or similar defects as those in defect image 610, and 5,000 virtual good product images having various defects but the same or similar backgrounds as those in defect image 610. As another example, image generation model 120 may generate 10,000 virtual good product images for type A defects and 3,000 virtual good product images for type B defects. In other words, image generation model 120 may generate different numbers of virtual good product images depending on the shape, type, or number of defects in defect image 610, and may also generate different numbers of virtual good product images depending on the shape, type, or background of defect image 610.

[0054] The memory 130 is a means for storing instructions (program codes) required to perform a defect detection method according to an embodiment of the present invention. The processor 135 is a means for controlling the internal components of the defect detection system 100 according to one embodiment of the present invention (e.g., the training data generation unit 110, the training unit 115, the image generation model 120, the defect detection unit 125, the memory 130, etc.).

[0055] In addition, at least one of the image of the defect detected by the defect detection unit 125 or the virtual non-defective image and the virtual defect image generated by the image generation model 120 is reused for training the image generation model 120.

[0056] According to another embodiment, when the input image is a defect image, a virtual good product image and a virtual defect image are generated through the trained image generation model 120. In this case, a defect area is detected by comparing the defect image with the virtual good product image, and a type, pattern, etc. of the defect is detected by comparing the defect image with the virtual defect image.

[0057] FIG. 9 is a flowchart illustrating a model learning process according to one embodiment of the present invention. In step S900, the defect detection system 100 generates at least one of a large number of virtual good product images and virtual defect images using a small number of defect images.

[0058] According to one embodiment, the defect detection system 100 uses a small number of defect images to generate a large number of virtual good product images.

[0059] As another example, the defect detection system 100 utilizes a small number of defect images to generate a large number of virtual defect images.

[0060] As yet another example, the defect detection system 100 uses a small number of good product images to generate a large number of good product images.

[0061] As yet another example, the defect detection system 100 may use a small number of defect images to generate a large number of virtual good product images and virtual defect images.

[0062] In this way, the defect detection system 100 uses a small number of input images to generate a training data set for training the image generation model 120. This is similar to what has been explained with reference to FIGS. 1 to 5, so a duplicated explanation will be omitted.

[0063] In step S902, the defect detection system 100 trains the image generation model 120 using at least one of a large number of virtual good product images and virtual defect images.

[0064] The image generation model 120 is an image generation model that uses artificial intelligence and generates a comparison image corresponding to an input image.

[0065] For example, if the input image is a defect image, the image generation model 120 generates a non-defective image corresponding to the defect image.

[0066] For this purpose, the image generation model 120 may be pre-trained using a training data set consisting of virtual defect images and virtual non-defective product images. The training process of an artificial intelligence model is obvious to those skilled in the art, and therefore a separate description thereof will be omitted.

[0067] In general, when it comes to artificial intelligence models, it is difficult to obtain a sufficient training dataset for model training, which leads to insufficient training for the actual model and many difficulties in application. In one embodiment of the present invention, a small number of defect images are used to generate a large number of virtual non-defective product images and virtual defect images required for model training, and these images are used to train the model.

[0068] The advantage of model training using many training datasets is that it can further improve the accuracy of the model.

[0069] A method for detecting actual defects using a model that has completed learning will be described with reference to FIG. Fig. 10 is a flowchart showing a defect detection method according to an embodiment of the present invention. The following description will be given on the assumption that the image generation model 120 has been trained using the training dataset as described in Fig. 10.

[0070] In step S1000, the defect detection system 100 acquires an input image. In step S1002, the defect detection system 100 applies the input image to the trained image generation model 120 to generate a comparison image.

[0071] For example, if the input image is a defective image, the comparison image is a non-defective image in which the defective area has been removed from the defective image.

[0072] When an input image is applied to the trained image generation model 120, the trained image generation model 120 generates and outputs a virtual non-defective image as a comparison image in which the defective area has been removed from the input image, that is, the defective image.

[0073] In step S1004, the defect detection system 100 derives a difference image between the input image and the comparison image, and detects a defect area using the difference image.

[0074] For example, the defect detection system 100 can set a defect image as the comparison image, can set a non-defective image, or can set both a non-defective image and a defect image.

[0075] The defect detection system 100 can determine the presence or absence of a defect after deriving a difference image between the input image and the defect image set as a comparison image.

[0076] As another example, the defect detection system 100 may detect a defect area after deriving a difference image between an input image and a non-defective image set as a comparison image. Of course, depending on the implementation method, the defect detection system 100 can set both a defect image and a non-defective image as the comparison image, and determine the presence or absence of a defect by comparing the input image with the defect image.

[0077] The defect detection system 100 can also use the comparison video for model learning as described in FIG.

[0078] As described above, according to one embodiment of the present invention, a large number of virtual training data sets are generated using a small number of input images (defect images, good product images), and then the data sets are used to train a model to improve accuracy, which can then be used in defect inspection, thereby improving defect detection performance.

[0079] Meanwhile, in the above example, due to a shortage of learning datasets, virtual defect images and virtual good product images were generated and used as learning datasets. However, if a large number of actual defect images and good product images are obtained through an iterative defect detection process, the number of virtual defect images / virtual good product images can be reduced and used for learning.

[0080] Therefore, the defect detection system checks the number of actual defect images / virtual good product images, and appropriately generates virtual defect images / virtual good product images according to the checked number of actual defect images / virtual good product images to use for learning. For example, if the number of actual defect images / virtual good product images is 1,000 or less, 20,000 virtual defect images / virtual good product images are generated to learn a model, and if up to 5,000 actual defect images and good product images are obtained through the iterative defect detection process, 15,000 virtual defect images / virtual good product images are generated.

[0081] That is, the AI ​​can not only detect defects by generating virtual defect images / virtual good product images and training a model, but also generate virtual defect images / virtual good product images by taking into account the number of actual defect images / virtual good product images that have been secured, and train a model accordingly. As a result, as the defect detection process is repeated, the number of virtual defect images / virtual good product images decreases, and more actual defect images / virtual good product images are used, thereby improving the accuracy of the image generation model. In this case, the rate of increase in the number of actual defect images / virtual good product images and the rate of decrease in the virtual defect images / virtual good product images may be the same, but it is more efficient if they are different.

[0082] On the other hand, the components of the above-described embodiments can be easily understood from a process perspective, i.e., each component can be understood as a respective process, and the processes of the above-described embodiments can be easily understood from the perspective of the components of the device.

[0083] The above technical content may be embodied in the form of program instructions executed by various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiments, or may be known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program instructions, such as ROMs, RAMs, and flash memories. Examples of program instructions include not only machine language code, such as that produced by a compiler, but also high-level language code executed by a computer using an interpreter, etc. A hardware device may be configured to operate as one or more software modules to perform the operations of the embodiments, or vice versa.

[0084] The above-described embodiments of the present invention have been disclosed for illustrative purposes, and those skilled in the art having ordinary skill in the art may make various modifications, changes, and additions within the spirit and scope of the present invention, and such modifications, changes, and additions should be considered to fall within the scope of the following claims. [Explanation of symbols]

[0085] 100 Defect Detection System 110 Learning data generation unit 112 Video Type and Distribution Analysis Unit 114 Good Image Generation Unit 115 Learning Department 116 Defect image generation unit 120 Video Generation Model 125 Defect detection unit 130 memory 135 processors 610 Defective Image 620 Virtual Good Product Video

Claims

1. a learning data generation unit that generates a large number of virtual non-defective product images or a large number of virtual defect images using the defect images; a learning unit that learns a model for defect detection using the generated virtual non-defective product image or the generated virtual defective image; a defect detection unit that detects the presence or absence of a defect in an input image using the learned model, the learning data generating unit analyzes a type or distribution of the defect image to detect a defect form or a background form, and generates the virtual non-defective image or the virtual defect image with different types, numbers, or resolutions depending on the detected defect form or background form; The learning data generation unit an image type and distribution analysis unit that analyzes the type and distribution of the defect image to detect the defect type or the background type; a non-defective image generating unit that generates the virtual non-defective image in accordance with the detected defect form or the detected background form; a defect image generating unit that generates the virtual defect image in accordance with the detected defect form or the detected background form.

2. 2. The defect detection system of claim 1, wherein the learning data generator extracts hand-crafted features, such as Haar-like features or a histogram of oriented gradients, from the defect image and then detects the defect shape or the background shape using clustering.

3. The defect detection system of claim 1, wherein when a user specifies the type, number, or resolution of the virtual good product image or the virtual defect image, the good product image generation unit or the defect image generation unit is operated to generate a virtual good product image or virtual defect image of the specified type, number, or resolution regardless of the type, number, or resolution determined by artificial intelligence by the image type and distribution analysis unit.

4. 2. The defect detection system according to claim 1, wherein the non-defective image generating unit generates the virtual non-defective image by removing a defect area from the defect image and then filling the corresponding area with an appropriate background.

5. the defect image generating unit generates a plurality of the virtual defect images by modifying a defect area in the defect image or by converting a resolution of the defect image into a reference resolution, 2. The defect detection system of claim 1, wherein at least one of a position, a size, and a shape of the defect in the virtual defect image is different from a position, a size, or a shape of the defect in the defect image.

6. 2. The defect detection system of claim 1, wherein the defect detection unit generates a comparison image in which defects are removed from the input image using the model, and compares the generated comparison image with the input image to detect defects.

7. a learning data generation unit that generates a large number of virtual non-defective product images or a large number of virtual defect images using the defect images; a learning unit that learns a model for defect detection using the generated virtual non-defective product image or the generated virtual defective image; a defect detection unit that detects the presence or absence of a defect in an input image using the learned model, the learning data generation unit determines the types, number, or resolution of the virtual non-defective image or the virtual defect image to be generated by analyzing the types or distribution of the defect images using artificial intelligence; A defect detection method characterized by determining different types, numbers, or resolutions of the virtual good product images or virtual defect images to be generated when a user requests different types, numbers, or resolutions of the virtual good product images or virtual defect images than those determined by the artificial intelligence.

8. 8. The defect detection method of claim 7, wherein the learning data generation unit analyzes the type or distribution of the defect image to detect a defect form or a background form, and generates the virtual good product image or the virtual defect image with different types, numbers, or resolutions depending on the detected defect form or background form.

9. 8. The defect detection method according to claim 7, wherein the non-defective image generating unit generates the virtual non-defective image by removing a defect area from the defect image and then filling the corresponding area with an appropriate background.

10. the defect image generating unit generates a plurality of the virtual defect images by modifying a defect area in the defect image or by converting a resolution of the defect image into a reference resolution, 8. The defect detection method of claim 7, wherein at least one of a position, a size, and a shape of the defect in the virtual defect image is different from a position, a size, or a shape of the defect in the defect image.

11. generating a plurality of virtual non-defective images or a plurality of virtual defect images using the defect images; a step of training a model for defect detection using the generated virtual non-defective product image or the generated virtual defective image; and detecting the presence or absence of defects in the input image using the learned model; analyzing the type or distribution of the defect image to detect a defect form or a background form, and generating the virtual good product image or the virtual defect image with different types, numbers, or resolutions depending on the detected defect form or background form; The step of generating the plurality of virtual good product images or the plurality of virtual defect images includes: analyzing the type and distribution of the defect image to detect the defect form or the background form; generating the virtual non-defective product image according to the detected defect form or the detected background form; generating the virtual defect image according to the detected defect morphology or the detected background morphology.

12. 12. The defect detection method of claim 11, wherein the learning data generator extracts hand-crafted features, such as Haar-like features or a histogram of oriented gradient, from the defect image and then detects the defect shape or the background shape using clustering.

Images