Granted Patent B2

US 12,632,947 · App. 18/397,542 · Granted May 19, 2026

Inventors: Jin Kyu Gahm (Busan, KR); Il Hae Yu (Busan, KR); Won June Choi (Busan, KR)

Assignee: Pusan National University Industry—University Cooperation Foundation

G06T7/0004G06T2207/20081G06T2207/20084G06T2207/30136

Abstract

Claims (34)

1 . A method of detecting a surface defect, the method comprising:

acquiring a target image;

detecting at least one defect area from the target image;

generating a first defect matrix having a size corresponding to the target image, wherein the first defect matrix has a plurality of elements, and each of the plurality of elements is a first defect score calculated based on a number of the at least one defect area detected from the target image at a position corresponding to each element;

calculating a plurality of second defect scores while moving a predetermined reference window with respect to the first defect matrix, wherein each second defect score is a sum of the first defect scores of the first defect matrix corresponding to the predetermined reference window, and the predetermined reference window is a virtual area with a predetermined size; and

generating a defect image by extracting, from the target image, an image corresponding to a position of the predetermined reference window with a largest second defect scores.

2 . The method of claim 1 , further comprising inputting the defect image as input data into a network function and generating surface defect information,

wherein the network function is trained to output the surface defect information using an image with a size corresponding to the predetermined reference window as input data.

3 . The method of claim 1 , further comprising generating a second defect matrix by applying a standard deviation for each local area of the target image to the first defect matrix,

wherein the calculating of the plurality of second defect scores is performed on the second defect matrix with which the first defect matrix is replaced, and

wherein the applying the standard deviation includes generating a standard deviation matrix by calculating the standard deviation for each local area of the target image, and combining the first defect matrix with the standard deviation matrix.

4 . The method of claim 3 , wherein the generating of the second defect matrix includes generating a standard deviation matrix by calculating the standard deviation for each the local area from the target image and summing weights of the first defect matrix and the standard deviation matrix,

wherein the summing of the weights of the first defect matrix and the standard deviation matrix includes: multiplying the first defect matrix by a first weight to obtain a first product, multiplying the standard deviation matrix by a second weight to obtain a second product, and summing the first product and the second product.

5 . The method of claim 3 , further comprising generating a third defect matrix by removing an element corresponding to a non-defect area from the second defect matrix,

wherein the calculating of the plurality of second defect scores is performed on the third defect matrix with which the second defect matrix is replaced, and

wherein the removing the element corresponding to the non-defect area from the second defect matrix is performed by an AND operation on a non-defect matrix and the first defect matrix, the non-defect matrix having the size corresponding to the target image and representing at least one of background and padding from the target image.

6 . The method of claim 3 , wherein the detecting of the defect area includes generating boundary value information from the target image, generating boundary direction information from the target image, selecting a boundary value information which is greater than or equal to a predetermined critical value based on the boundary value information and the boundary direction information, and detecting the defect area based on the selected boundary value information and corresponding boundary direction information.

7 . The method of claim 1 , wherein the detecting of the at least one defect area, the generating of the first defect matrix, the calculating of the plurality of second defect scores, and the generating of the defect image are performed when at least one of a horizontal size and a vertical size of the target image is larger than that of the predetermined reference window.

8 . The method of claim 1 , further comprising adding padding to a periphery of the target image so that the target image corresponds to the predetermined reference window when at least one of a horizontal size and a vertical size of the target image is smaller than that of the predetermined reference window.

9 . A computer program stored in a non-transitory recording medium to execute the method of claim 1 .

10 . An apparatus for detecting a surface defect, the apparatus comprising:

a memory storing a program for detecting a surface defect; and

a processor configured to:

acquire a target image,

detect at least one defect area from the target image,

generate a first defect matrix having a size corresponding to the target image, wherein the first defect matrix has a plurality of elements, and each of the plurality of elements is a first defect score calculated based on a number of defect areas detected from the target image at a position corresponding to each element,

calculate a plurality of second defect scores while moving a predetermined reference window with respect to the first defect matrix, wherein each second defect score is a sum of the first defect scores of the first defect matrix corresponding to the predetermined reference window, and the predetermined reference window is a virtual area with a predetermined size, and

generate a defect image by extracting, from the target image, an image corresponding to a position of the predetermined reference window with a largest second defect score.

11 . The apparatus of claim 10 , wherein the processor is further configured to generate a second defect matrix by applying a standard deviation for each local area of the target image to the first defect matrix, and

calculate the plurality of second defect scores using the second defect matrix with which the first defect matrix is replaced,

wherein the applying the standard deviation includes generating a standard deviation matrix by calculating the standard deviation for each local area of the target image, and combining the first defect matrix with the standard deviation matrix.

12 . The apparatus of claim 11 , wherein the processor is further configured to generate a third defect matrix by removing an element corresponding to a non-defect area from the second defect matrix, and

calculate the plurality of second defect scores using the third defect matrix with which the second defect matrix is replaced,

wherein the third defect matrix is generated by generating a non-defect matrix having a size corresponding to the target image and representing at least one of background and padding from the target image, and performing an AND operation on the non-defect matrix and the first defect matrix to remove the element corresponding to the non-defect area from the second defect matrix.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (22)