WO2021049721A1 - Procédé et dispositif pour effectuer un apprentissage machine et un test sur une pluralité d'images - Google Patents

Procédé et dispositif pour effectuer un apprentissage machine et un test sur une pluralité d'images Download PDF

Info

Publication number
WO2021049721A1
WO2021049721A1 PCT/KR2020/000251 KR2020000251W WO2021049721A1 WO 2021049721 A1 WO2021049721 A1 WO 2021049721A1 KR 2020000251 W KR2020000251 W KR 2020000251W WO 2021049721 A1 WO2021049721 A1 WO 2021049721A1
Authority
WO
WIPO (PCT)
Prior art keywords
learning
criterion
image
images
satisfied
Prior art date
Application number
PCT/KR2020/000251
Other languages
English (en)
Korean (ko)
Inventor
추연학
정재호
박주영
Original Assignee
라온피플 주식회사
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 라온피플 주식회사 filed Critical 라온피플 주식회사
Priority to CN202080041294.6A priority Critical patent/CN113906471A/zh
Publication of WO2021049721A1 publication Critical patent/WO2021049721A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G06T7/001—Industrial image inspection using an image reference approach
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning

Definitions

  • the embodiments disclosed herein relate to a method and apparatus for performing machine learning and testing on a plurality of images, and in particular, performing both machine learning and testing on the same image, and reflecting the results of machine learning. It relates to a method and apparatus for performing a test.
  • Machine learning needs to be performed on. For example, machine learning may be performed on a plurality of images photographing good or defective products, or machine learning may be performed on a plurality of images photographing various types of goods.
  • learning is first performed using images separately prepared for training in order to perform a test to distinguish between good and defective products through photographed images. For example, by performing learning on a plurality of images of good or defective products, after grasping the characteristics of images of good or defective products, testing the image of the goods to determine whether the goods are good or not It is a method of determining whether the product is defective.
  • the accuracy of the test result is degraded if there is a change in the environment, such as a change in the brightness or position of the light illuminating the article after learning.
  • Korean Patent Registration No. 10-1867475 discloses a description of clustering similar models by performing unsupervised learning on static data using an autoencoder.
  • the above-described background technology is technical information that the inventor possessed for derivation of the present invention or acquired during the derivation process of the present invention, and is not necessarily a known technology disclosed to the general public before filing the present invention. .
  • Embodiments disclosed herein are to provide a machine learning and test execution method and apparatus for increasing test accuracy by reflecting a learning result in real time by performing both machine learning and testing on a plurality of images.
  • both learning and testing are performed on a plurality of images, but the test is performed by reflecting the results of learning.
  • any one of the above-described task solving means it is possible to perform a test by reflecting the learning result in real time by performing both learning and testing on a plurality of images but reflecting the learning result, and thus, the environment It can be expected to increase test accuracy by adaptively responding to changes.
  • FIG. 1 is a diagram illustrating a system for performing machine learning and testing on a plurality of images according to an exemplary embodiment.
  • FIG. 2 is a block diagram illustrating a configuration of the computing device illustrated in FIG. 1.
  • 3 to 8 are flowcharts illustrating a method for performing machine learning and testing on a plurality of images according to embodiments.
  • a method of performing machine learning and testing on a plurality of images includes the steps of receiving a plurality of images, and learning and learning about the plurality of images. Performing all tests, but may include performing the test by reflecting the result of performing the learning.
  • the method of performing machine learning and testing on a plurality of images includes: And performing both learning and testing on the plurality of images, and performing the test by reflecting a result of performing the learning.
  • a computer-readable recording medium in which a program for performing a method of performing machine learning and testing on a plurality of images in a computing device is recorded, machine learning and testing are performed on a plurality of images.
  • the performing method may include receiving a plurality of images and performing both learning and testing on the plurality of images, and performing the test by reflecting the result of performing the learning.
  • an apparatus for performing machine learning and testing includes an input/output unit for receiving operation and data input related to machine learning and testing, displaying data processing results, and communication for transmitting and receiving data with an external device. And a communication unit for performing machine learning and a storage unit for storing a program for performing the test, and a control unit for performing machine learning and testing on a plurality of images by executing the program, wherein the control unit includes: Both learning and testing may be performed on a plurality of images to be received, but the test may be performed by reflecting the result of performing the learning.
  • a system for performing machine learning and testing on a plurality of images according to an exemplary embodiment may include a photographing unit 10 and a computing device 100.
  • the system shown in FIG. 1 is a machine vision system for determining whether articles 1 are good or defective, and the photographing unit 10 captures an image of the article 1 and transmits it to the computing device 100 Then, the computing device 100 determines whether the photographed article 1 is good or defective by analyzing the received image. To this end, the computing device 100 learns the received images (hereinafter, it is used in the same meaning as'machine learning') to determine the characteristics of a normal image (an image in which a good product was photographed) and an abnormal image (an image in which a defective product was photographed). I can grasp it.
  • the photographing unit 10 is a component for photographing the appearance of the article 1 and may be implemented as a camera including an image sensor.
  • the photographing unit 10 is illustrated as being a separate component from the computing device 100, but differently, the photographing unit 10 may be a component included in the computing device 100.
  • the photographing unit 10 may include an illumination for illuminating the article 1 when photographing in order to secure a clearer image.
  • the photographing unit 10 may photograph items 1 moving through a conveyor belt or the like one by one and transmit the photographed images to the computing device 100.
  • the computing device 100 performs machine learning and tests on a plurality of images received from the photographing unit 10.
  • the computing device 100 determines whether the product 1 included in the image is a good product or a defective product by analyzing the image in which the product 1 is photographed.
  • the computing device 100 performs both learning and testing on a plurality of images, but by reflecting the learning result and performing the test, the learning result may be reflected in the test in real time. That is, the computing device 100 may perform both learning and testing on the same image without separating the training image and the test image from each other. Therefore, it is not necessary to separately prepare an image for learning, so an effect of improving user convenience can be expected.
  • the test is performed while learning the image that has been tested at the same time, and the result of the learning is reflected when the test is performed on the next image, so even if the surrounding environment such as the brightness or location of the light changes, it is adaptively. In response, it can be expected to increase test accuracy.
  • FIG. 2 is a block diagram illustrating the configuration of the computing device 100 illustrated in FIG. 1.
  • the computing device 100 may include an input/output unit 110, a communication unit 120, a control unit 130, and a storage unit 140.
  • the input/output unit 110 is a component for receiving inputs such as settings related to machine learning and test performance from a user, and outputting a test result. According to an embodiment, the input/output unit 110 may receive a setting input from a user through input devices such as a keyboard and a mouse, and display results of learning and testing on a screen.
  • the communication unit 120 is a component for performing communication for transmitting and receiving data with an external device, and may support various types of wired/wireless communication. For example, the communication unit 120 may sequentially receive images photographed of the article 1 from the photographing unit 10.
  • the communication unit 120 may be implemented as a communication chipset supporting various communication protocols.
  • the controller 130 is a component including at least one processor such as a CPU, and controls the overall operation of the computing device 100.
  • the control unit 130 may perform machine learning and testing on a plurality of images by executing a program stored in the storage unit 140. A detailed operation of the controller 130 performing machine learning and testing on a plurality of images will be described in detail below.
  • Various types of programs and data may be stored in the storage unit 140.
  • a program for performing machine learning and testing on a plurality of images may be stored in the storage unit 140, and a plurality of images to be learned and tested may also be stored.
  • the controller 130 may learn and test a plurality of images received through the communication unit 120, but may perform a test by reflecting a result of performing the learning.
  • the communication unit 120 may receive images photographed by the article 1 one by one from the photographing unit 10 in order, and the controller 130 may perform learning and testing one by one in the order in which the images were received.
  • the controller 130 may learn and test each of the plurality of images one by one, but may perform a test on the next image by reflecting the results learned before. For example, when learning and testing on any one image (first image), the controller 130 reflects the learning result for the corresponding image (first image), Perform the test. In addition, the controller 130 may perform learning on the next image (second image) and reflect the result when performing a test on the next image (third image).
  • test criteria for example, characteristics of a normal image (an image in which a good product was photographed).
  • test criteria may be pre-stored in the storage unit 140, or the control unit 130 may directly grasp and store them in the storage unit 140 in the process of learning the images.
  • control unit 130 directly grasps the test criterion in the process of learning the images.
  • the controller 130 starts learning one by one for a plurality of images in order. Initially, since the test criterion was not prepared, the controller 130 only learns the image. When learning is performed on images one by one in order, and when a preset certain criterion (hereinafter, referred to as'preparation criterion') is satisfied, the controller 130 determines that preparation for setting the test criterion is completed, and the subsequent images Regarding, both learning and testing are performed, but the test is performed by reflecting the learning results performed until the preparation criteria are satisfied and the learning results of the images in subsequent steps.
  • a preset certain criterion hereinafter, referred to as'preparation criterion'
  • the controller 130 sets a test criterion based on the learning result performed until the preparation criterion is satisfied, and then performs a test on the subsequent images.
  • the control unit 130 continuously updates the test criteria based on the result while simultaneously performing the test and learning on the subsequent images. That is, in performing a test on images in a subsequent sequence, the controller 130 performs the test by reflecting the learning results of other images performed just before the test execution.
  • a method for the controller 130 to determine whether the preparation criterion is satisfied is as follows.
  • the controller 130 may determine whether or not the preparation criterion is satisfied based on the time at which learning has been performed to the present or the number of images that have been trained to date. This is because test criteria such as characteristics of normal images can be grasped only when learning is performed for at least a predetermined time or on at least a predetermined number of images.
  • control unit 130 may check the time at which learning has been performed so far, and determine that the preparation criterion is satisfied if the checked time exceeds a preset value.
  • controller 130 may check the number of images that have been trained so far, and determine that the preparation criterion is satisfied if the confirmed number exceeds a preset value.
  • controller 130 may determine whether preparations for setting the test criteria are completed in various ways (whether the preparation criteria are satisfied).
  • the controller 130 determines the characteristics of the normal image based on the learning result performed until the preparation criterion is satisfied, and sets this as a test criterion.
  • the test criterion is described as an example as a characteristic of a normal image, but differently, the characteristic of an abnormal image may be a test criterion.
  • the controller 130 performs a test on any one image (first image) on the basis of the identified characteristics of the normal image. That is, the controller 130 determines whether the first image is a normal image or an abnormal image. When it is determined that the first image is an abnormal image, the controller 130 may display a guide indicating that a defective product has been detected through the input/output unit 110.
  • the controller 130 performs learning as well as testing on the first image.
  • the controller 130 updates the characteristics of the normal image based on the result of learning the first image. Therefore, when performing a test on an image (second image) in a sequence following the first image, the controller 130 determines whether the second image is a normal image based on the characteristics of the normal image in which the learning result for the first image is reflected. Can be judged. In this way, the controller 130 may continuously update the test criteria by performing a test on each image and learning at the same time.
  • the control unit 130 updates the test criterion (characteristic of a normal image) every time it learns about one image. May not be efficient at Therefore, instead of updating the test criterion for each image, the test criterion may be updated only when a preset certain criterion (hereinafter, referred to as “update criterion”) is satisfied.
  • update criterion a preset certain criterion
  • the controller 130 determines the characteristics of the normal image based on the previously performed learning result.
  • the test criterion is described as an example as a characteristic of a normal image, but differently, the characteristic of an abnormal image may be a test criterion.
  • the controller 130 performs a test on any one image (first image) on the basis of the identified characteristics of the normal image. That is, the controller 130 determines whether the first image is a normal image or an abnormal image. When it is determined that the first image is an abnormal image, the controller 130 may display a guide indicating that a defective product has been detected through the input/output unit 110.
  • the controller 130 performs learning as well as testing on the first image.
  • the controller 130 determines whether or not a preset update criterion is satisfied.
  • the controller 130 checks the time when the feature of the normal image has been identified or the time when the feature of the normal image has been updated has been completed, and if the time has exceeded a preset value, the update criterion It can be judged as satisfying.
  • the controller 130 checks the number of images that have been trained after the time when the feature of the normal image has been identified or the time when the feature of the normal image has been updated is completed, and if the confirmed number exceeds a preset value, it is updated. It can be determined that the criteria are satisfied.
  • the controller 130 reflects the learning result and updates the test criterion only when a certain criterion (update criterion) is satisfied, thereby reflecting the learning result in real time and increasing efficiency.
  • the method of performing machine learning and testing according to the embodiments illustrated in FIGS. 3 to 8 includes steps processed in a time series by the computing device 100 illustrated in FIGS. 1 and 2. Therefore, even though the contents are omitted below, the contents described above with respect to the computing device 100 shown in FIGS. 1 and 2 are also included in the method of performing machine learning and testing according to the embodiments shown in FIGS. 3 to 8. Can be applied.
  • FIG. 3 is a flowchart illustrating a method for performing machine learning and testing on a plurality of images according to an exemplary embodiment.
  • the computing device 100 receives a plurality of images.
  • the computing device 100 may receive a plurality of images at once, or may receive target images one by one while performing learning and testing.
  • step 302 the computing device 100 performs both learning and testing on a plurality of images, but performs a test by reflecting the learning result.
  • the computing device 100 performs learning and testing on each of the plurality of images in order, reflecting the result of learning on the previous image, and performs a test on the next image.
  • step 401 the computing device 100 learns a plurality of received images one by one.
  • step 402 the computing device 100 determines whether the next image to be learned exists, ends the process if the next image does not exist, and proceeds to step 403 if the next image exists.
  • step 403 the computing device 100 determines whether a predetermined criterion (preparation criterion) is satisfied, and if the preparatory criterion is not satisfied, returns to step 401, and if the preparatory criterion is satisfied, the computing device 100 proceeds to step 404.
  • the'preparation criterion' is a criterion for determining whether preparation for setting a criterion (test criterion) for testing is completed, as described above. That is, when the preparation criterion is satisfied, the computing device 100 determines that preparation for setting the test criterion is completed.
  • the computing device 100 determines whether or not the preparation criterion is satisfied based on the time at which the training has been performed to the present or the number of images that have been trained to date, a detailed process will be described with reference to FIGS. 7 and 8 below. .
  • step 404 the computing device 100 performs both learning and testing on the remaining images, but performs a test by reflecting the learning results of other images.
  • the computing device 100 When it is determined that the preparation criterion is satisfied, the computing device 100 performs both learning and testing for the subsequent images, but reflects the learning result performed until the preparation criterion is satisfied and the learning results for the subsequent images. To perform the test. In detail, when it is determined that the preparation criterion is satisfied, the computing device 100 sets a test criterion based on a learning result performed until the preparation criterion is satisfied, and then performs tests on images in a subsequent sequence. In this case, the computing device 100 continuously updates the test criteria based on the result while simultaneously performing the test and learning on the subsequent images. That is, when the computing device 100 performs a test on images in a subsequent sequence, the computing device 100 performs the test by reflecting the learning results of other images performed just before the test.
  • step 501 the computing device 100 identifies features of a normal image based on a result of performing previous learning.
  • the computing device 100 detects an abnormal image by performing a test on the image based on the characteristics of the normal image.
  • the computing device 100 may determine whether each image is a normal image or an abnormal image by comparing features of the normal image identified in step 501 with each image.
  • step 503 the computing device 100 performs learning on the image tested in step 502.
  • step 504 the computing device 100 updates the features of the normal image based on the result of performing the learning in step 503.
  • step 505 the computing device 100 determines whether the next image exists, returns to step 502 if the next image exists, and terminates the process if the next image does not exist.
  • the computing device 100 does not update each time learning of one image is completed, and only updates when a predetermined condition (update condition) is satisfied. By doing so, it is possible to increase the efficiency while reflecting the learning result in real time. This embodiment will be described with reference to FIG. 6 below.
  • step 601 the computing device 100 identifies features of a normal image based on a result of performing previous learning.
  • the computing device 100 detects an abnormal image by performing a test on the image based on features of the normal image.
  • the computing device 100 may determine whether each image is a normal image or an abnormal image by comparing the features of the normal image identified in step 601 with each image.
  • step 603 the computing device 100 learns the image that has been tested in step 602.
  • step 604 the computing device 100 determines whether there is a next image, and if there is no next image as a result of the determination, the process ends. Conversely, if there is a next image, the process proceeds to step 605.
  • step 605 the computing device 100 determines whether or not a preset criterion (update criterion) is satisfied.
  • the computing device 100 checks the time at which the learning was performed after the time when the feature of the normal image was completed or the time when the update of the feature of the normal image was completed, and if the checked time exceeds a preset value, it is updated. It can be determined that the criteria are satisfied.
  • the computing device 100 checks the number of images that have been trained after the time when the feature identification of the normal image has been completed or the time when the update of the features of the normal image is completed, and if the confirmed number exceeds a preset value, It can be determined that the update criteria are satisfied.
  • step 605 if it is determined that the preset criterion is not satisfied, the computing device 100 returns to and performs step 602 again. Conversely, if it is determined that the preset criterion is satisfied, the computing device 100 proceeds to step 606.
  • step 606 the computing device 100 updates the features of the normal image based on the results of learning the images after the features of the normal image are last updated. After performing step 606, the computing device 100 returns and performs step 602 again.
  • step 701 the computing device 100 checks the time at which learning has been performed.
  • step 702 the computing device 100 determines whether the checked time exceeds a preset value, and if it exceeds the preset value, proceeds to step 404 of FIG. 4, and if it is less than the preset value, step 401 of FIG. Do it again.
  • step 801 the computing device 100 checks the number of images that have been trained so far.
  • step 802 the computing device 100 determines whether the confirmed number exceeds a preset value, and if it exceeds the preset value, proceeds to step 404 of FIG. 4, and if it is less than the preset value, step 401 of FIG. 4 Do it again.
  • the computing device 100 learns the images until the preparation criterion is satisfied, thereby grasping the criteria for testing, and learning the subsequent images and at the same time grasping the learning results up to the previous image.
  • the test can be performed based on the established test criteria.
  • the term' ⁇ unit' used in the above embodiments refers to software or hardware components such as field programmable gate array (FPGA) or ASIC, and' ⁇ unit' performs certain roles. However,' ⁇ part' is not limited to software or hardware.
  • The' ⁇ unit' may be configured to be in an addressable storage medium, or may be configured to reproduce one or more processors.
  • ' ⁇ unit' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , Subroutines, segments of program patent code, drivers, firmware, microcode, circuitry, data, database, data structures, tables, arrays, and variables.
  • the components and functions provided within the' ⁇ units' may be combined into a smaller number of elements and' ⁇ units', or may be separated from the additional elements and' ⁇ units'.
  • components and' ⁇ units' may be implemented to play one or more CPUs in a device or a security multimedia card.
  • the method of performing machine learning and testing according to the embodiments described with reference to FIGS. 3 to 8 may also be implemented in the form of a computer-readable medium that stores instructions and data executable by a computer.
  • the instructions and data may be stored in the form of a program code, and when executed by a processor, a predetermined program module may be generated to perform a predetermined operation.
  • the computer-readable medium may be any available medium that can be accessed by a computer, and includes both volatile and nonvolatile media, removable and non-removable media.
  • the computer-readable medium may be a computer recording medium, which is volatile and non-volatile implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules, or other data.
  • the computer recording medium may be a magnetic storage medium such as HDD and SSD, an optical recording medium such as CD, DVD, and Blu-ray disk, or a memory included in a server accessible through a network.
  • the method of performing machine learning and testing according to the embodiments described with reference to FIGS. 3 to 8 may be implemented as a computer program (or computer program product) including instructions executable by a computer.
  • the computer program includes programmable machine instructions processed by a processor, and may be implemented in a high-level programming language, an object-oriented programming language, an assembly language, or a machine language.
  • the computer program may be recorded on a tangible computer-readable recording medium (eg, a memory, a hard disk, a magnetic/optical medium or a solid-state drive (SSD), etc.).
  • the method of performing machine learning and testing according to the embodiments described with reference to FIGS. 3 to 8 may be implemented by executing the computer program as described above by the computing device.
  • the computing device may include at least some of a processor, a memory, a storage device, a high-speed interface connected to the memory and a high-speed expansion port, and a low-speed interface connected to the low-speed bus and the storage device.
  • a processor may include at least some of a processor, a memory, a storage device, a high-speed interface connected to the memory and a high-speed expansion port, and a low-speed interface connected to the low-speed bus and the storage device.
  • Each of these components is connected to each other using a variety of buses, and can be mounted on a common motherboard or in other suitable manner.
  • the processor can process commands within the computing device.
  • commands include, for example, to display graphic information for providing a GUI (Graphic User Interface) on an external input or output device, such as a display connected to a high-speed interface.
  • GUI Graphic User Interface
  • multiple processors and/or multiple buses may be used with multiple memories and memory types as appropriate.
  • the processor may be implemented as a chipset formed by chips including a plurality of independent analog and/or digital processors.
  • the memory also stores information within the computing device.
  • the memory may be composed of volatile memory units or a set of them.
  • the memory may be composed of a nonvolatile memory unit or a set of them.
  • the memory may be another type of computer-readable medium such as a magnetic or optical disk.
  • the storage device may provide a large-capacity storage space to the computing device.
  • the storage device may be a computer-readable medium or a configuration including such a medium, for example, devices in a storage area network (SAN) or other configurations, a floppy disk device, a hard disk device, an optical disk device, Alternatively, it may be a tape device, a flash memory, or another semiconductor memory device or device array similar thereto.
  • SAN storage area network
  • floppy disk device a hard disk device
  • optical disk device Alternatively, it may be a tape device, a flash memory, or another semiconductor memory device or device array similar thereto.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Medical Informatics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)

Abstract

Un procédé pour effectuer un apprentissage machine et un test sur une pluralité d'images comprend : une étape consistant à recevoir une pluralité d'images; et une étape pour effectuer à la fois l'apprentissage et le test sur la pluralité d'images, le test étant effectué en reflétant le résultat de la réalisation de l'apprentissage.
PCT/KR2020/000251 2019-09-10 2020-01-07 Procédé et dispositif pour effectuer un apprentissage machine et un test sur une pluralité d'images WO2021049721A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202080041294.6A CN113906471A (zh) 2019-09-10 2020-01-07 用于对多个图像执行机器学习和测试的方法及装置

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020190111843A KR102357729B1 (ko) 2019-09-10 2019-09-10 복수의 이미지들에 대해 기계학습 및 테스트를 수행하기 위한 방법 및 장치
KR10-2019-0111843 2019-09-10

Publications (1)

Publication Number Publication Date
WO2021049721A1 true WO2021049721A1 (fr) 2021-03-18

Family

ID=74866737

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2020/000251 WO2021049721A1 (fr) 2019-09-10 2020-01-07 Procédé et dispositif pour effectuer un apprentissage machine et un test sur une pluralité d'images

Country Status (3)

Country Link
KR (1) KR102357729B1 (fr)
CN (1) CN113906471A (fr)
WO (1) WO2021049721A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR19990078833A (ko) * 1999-08-11 1999-11-05 김주환 반도체 패키지 마킹 검사공정에서의 오토티칭 장치 및 그 제어방법
WO2017145960A1 (fr) * 2016-02-24 2017-08-31 日本電気株式会社 Dispositif d'apprentissage, procédé d'apprentissage et support d'enregistrement
KR101838664B1 (ko) * 2017-11-28 2018-03-14 서울전선 주식회사 케이블 표면 검사 장치
JP2018054375A (ja) * 2016-09-27 2018-04-05 日本電気株式会社 画像検査装置、画像検査方法および画像検査プログラム
JP2019087181A (ja) * 2017-11-10 2019-06-06 アズビル株式会社 画像検査装置および方法

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4912028B2 (ja) 2006-05-01 2012-04-04 日本電信電話株式会社 逐次学習式非定常映像検出装置，逐次学習式非定常映像検出方法及びその方法を実装したプログラム
KR101842347B1 (ko) * 2016-05-04 2018-03-26 두산중공업 주식회사 플랜트 이상 감지를 위한 자동 학습 시스템 및 방법
JP6942472B2 (ja) 2017-01-13 2021-09-29 キヤノン株式会社 映像認識装置、映像認識方法及びプログラム

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR19990078833A (ko) * 1999-08-11 1999-11-05 김주환 반도체 패키지 마킹 검사공정에서의 오토티칭 장치 및 그 제어방법
WO2017145960A1 (fr) * 2016-02-24 2017-08-31 日本電気株式会社 Dispositif d'apprentissage, procédé d'apprentissage et support d'enregistrement
JP2018054375A (ja) * 2016-09-27 2018-04-05 日本電気株式会社 画像検査装置、画像検査方法および画像検査プログラム
JP2019087181A (ja) * 2017-11-10 2019-06-06 アズビル株式会社 画像検査装置および方法
KR101838664B1 (ko) * 2017-11-28 2018-03-14 서울전선 주식회사 케이블 표면 검사 장치

Also Published As

Publication number Publication date
KR102357729B1 (ko) 2022-02-03
KR20210030576A (ko) 2021-03-18
CN113906471A (zh) 2022-01-07

Similar Documents

Publication Publication Date Title
WO2021095991A1 (fr) Dispositif et procédé de génération d'une image de défaut
WO2021194056A1 (fr) Procédé de formation d'un réseau d'apprentissage profond basé sur une intelligence artificielle et dispositif d'apprentissage l'utilisant
WO2015141891A1 (fr) Dispositif d'affichage et son procédé de commande
WO2022055099A1 (fr) Procédé de détection d'anomalies et dispositif associé
WO2022059969A1 (fr) Procédé de pré-apprentissage de réseau neuronal profond permettant une classification de données d'électrocardiogramme
WO2020004749A1 (fr) Appareil et procédé permettant à un équipement d'apprendre, à l'aide d'un fichier vidéo
WO2015194709A1 (fr) Dispositif d'affichage portable et procédé de commande associé
WO2020262800A1 (fr) Système et procédé d'automatisation de compréhension de langage naturel (nlu) pour un développement de compétence
WO2014181946A1 (fr) Système et procédé d'extraction de données volumineuses
WO2021049721A1 (fr) Procédé et dispositif pour effectuer un apprentissage machine et un test sur une pluralité d'images
WO2016072610A1 (fr) Procédé de reconnaissance et dispositif de reconnaissance
WO2017222228A1 (fr) Procédé de reconnaissance de transition d'écran dans un contenu d'image, et serveur de commande correspondant
WO2022080582A1 (fr) Procédé d'apprentissage par renforcement orienté cible et dispositif pour sa réalisation
EP3186956A1 (fr) Dispositif d'affichage et procédé de commande pour celui-ci
WO2018066852A1 (fr) Dispositif d'inspection de substrat et procédé de compensation de distorsion de substrat l'utilisant
EP3895116A1 (fr) Système d'affichage permettant de détecter un défaut sur un écran large
WO2021080043A1 (fr) Dispositif et procédé de détection de mutation somatique, présentant des erreurs spécifiques à la plateforme de séquençage réduites
WO2022139177A1 (fr) Dispositif électronique et procédé de commande associé
WO2022075543A1 (fr) Procédé de détection d'anomalie utilisant un capteur multimodal, et dispositif informatique pour sa mise en œuvre
WO2022145524A1 (fr) Procédé et appareil de structuration de différents types de données
WO2021125550A1 (fr) Dispositif électronique et procédé de commande du dispositif électronique
WO2019208869A1 (fr) Appareil et procédé de détection des caractéristiques faciales à l'aide d'un apprentissage
WO2019231119A1 (fr) Appareil et procédé de visualisation d'encombrement
WO2022114489A1 (fr) Dispositif de support d'apprentissage profond et procédé de support d'apprentissage profond
WO2024096230A1 (fr) Procédé et dispositif pour déterminer des espaces de stationnement sur la base de zones occupées ou inoccupées

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20862448

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20862448

Country of ref document: EP

Kind code of ref document: A1