Product defect detection

Patent metadata

Field	Value
Publication number	US-11756185-B2
Application number	US-202017131936-A
Country	US
Kind code	B2
Filing date	Dec 23, 2020
Priority date	Jan 15, 2019
Publication date	Sep 12, 2023
Grant date	Sep 12, 2023

Abstract

Embodiments of the present invention facilitate product defect detection. A computer-implemented method comprises: receiving, by a device operatively coupled to one or more processors, a template image of a normal product; generating, by the device, one or more geometric training parameters for transforming the template image; and transforming, by the device, the template image using the one or more geometric training parameters to generate a transformed image for training a data model, wherein the trained data model being used for aligning the template image and an image under inspection of a product.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
iteratively employing, by a device operatively coupled to a processor, a random number generator to randomly generate respective random transformation parameters to be employed by a geometric transformation module to geometrically transform a template image of a defined product; and
iteratively generating, by the device, respective geometric training parameters for transforming the template image, wherein the respective geometric training parameters are based on the respective random transformation parameters.

2. The computer-implemented method of claim 1 , further comprising:
iteratively transforming, by the device, the template image using the respective geometric training parameters to generate respective transformed template images that are randomly generated to train a data model.

3. The computer-implemented method of claim 2 , wherein trained data model is employed to align the template image and an image of a product under inspection to determine whether the product has a defect.

4. The computer-implemented method of claim 1 , wherein types of the respective geometric training parameters are selected from a group consisting of a rotation angle parameter, a shearing parameter and a scale parameter.

5. The computer-implemented method of claim 1 , further comprising:
evaluating, by the device, an image of the product under inspection; and
aligning, by the device, the image of the product under inspection with the template image, wherein the aligning is performed based on the trained data model generated from the respective transformed template images.

6. The computer-implemented method of claim 5 , further comprising:
comparing, by the device, the aligned image and the template image to identify the defect of the product under inspection.

7. The computer-implemented method of claim 1 , wherein a data model is built based on a neural network selected from a group consisting of a Convolution Neural Network, a Recurrent Neural Network and a Deep Neural Network.

8. The computer-implemented method of claim 7 , wherein the neural network on which the data model is based contains multiple convolution layers and multiple max pooling layers.

9. The computer-implemented method of claim 1 , wherein a data model is trained by machine learning of a correspondence between a transformed image and the template image through the respective geometric training parameters.

10. A system, comprising:
a memory that stores computer executable components;
a processor that executes the computer executable components stored in the memory, wherein the computer executable components comprise:
at least one computer-executable component that:
iteratively employs a random number generator to randomly generate respective random transformation parameters to be employed by a geometric transformation module to geometrically transform a template image of a defined product; and
iteratively generates respective geometric training parameters for transforming the template image, wherein the respective geometric training parameters are based on the respective random transformation parameters.

11. The system of claim 10 , wherein the at least one computer-executable component comprises:
at least one computer-executable component that:
iteratively transforms the template image using the respective geometric training parameters to generate respective transformed template images that are randomly generated to train a data model.

12. The system of claim 11 , wherein a trained data model is employed to align the template image and an image of the product under inspection to determine whether the product has a defect.

13. The system of claim 10 , wherein types of the respective geometric training parameters are selected from a group consisting of a rotation angle parameter, a shearing parameter and a scale parameter.

14. The system of claim 10 , wherein the at least one computer-executable component comprises:
at least one computer-executable component that:
evaluates an image of the product under inspection; and
aligns the image of the product under inspection with the template image, wherein the aligning is performed based on the trained data model generated from the respective transformed template images.

15. The system of claim 14 , wherein the at least one computer-executable components comprise:
at least one computer-executable component that:
compares the aligned image and the template image to identify the defect of the product under inspection.

16. The system of claim 10 , wherein a data model is built based on a neural network selected from a group consisting of a Convolution Neural Network, a Recurrent Neural Network and a Deep Neural Network.

17. A computer program product facilitating detection of product defects by aligning product images under inspection with template product images, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by one or more processors to cause the one or more processors to:
iteratively employ, by the one or more processors, a random number generator to randomly generate respective random transformation parameters to be employed by a geometric transformation module to geometrically transform a template image of a defined product; and
iteratively generate, by the one or more processors, respective geometric training parameters for transforming the template image, wherein the respective geometric training parameters are based on the respective random transformation parameters.

18. The computer program product of claim 17 , wherein the program instructions executable by the one or more processors to cause the one or more processors to:
iteratively transforms the template image using the respective geometric training parameters to generate respective transformed template images that are randomly generated to train a data model.

19. The computer program product of claim 17 , wherein types of the respective geometric parameters are selected from a group consisting of a rotation angle parameter, a shearing parameter and a scale parameter.

20. The computer program product of claim 17 , wherein the program instructions are further executable by the one or more processors to cause the one or more processors to:
receive an image of a product under inspection;
align the image of the product under inspection with the template image; and
compare the aligned image and the template image to identify the defect of the product.

Assignees

• IBM

Inventors

• Hu Guo Qiang
• Yan jun chi
• Zhu Jun
• Huang Jing Chang
• Ji Peng

Classifications

• G06T7/001 Primary

  using an image reference approach · CPC title

• G06T7/0008

  checking presence/absence · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/30141

  Printed circuit board [PCB] · CPC title

• G06T2207/30121

  CRT, LCD or plasma display · CPC title