Automated optical inspection method, automated optical inspection system and storage medium

An automated optical inspection system, comprising:

• an optical lens, configured to capture an original image of a target object, wherein the original image comprises a plurality of first images, wherein the target object is an integrated circuitry or a printed circuit board;
• and
• a processor, coupled to the optical lens and configured to:
• perform an edge detection on the original image to obtain an edge image having an edge pattern, wherein the edge image comprises a plurality of second images having an edge pattern;
• calculate at least one of a maximum value, a minimum value, and an average value of a pixel value in the plurality of second images;
• divide the edge image into a plurality of image blocks according to a unit area, such that each of the image blocks includes N second images, wherein N is an integer greater than 0, and a value of N is determined according to a number of the first images included when the original image is captured;
• calculate a plurality of characteristic values corresponding to each of the image blocks according to the at least one of the maximum value, the minimum value, and the average value corresponding to the N second images comprised in each of the plurality of image blocks;
• and
• obtain an optimal regression model by training a regression model corresponding to a defect of the target object according to the plurality of characteristic values and a data of the target object.

A non-transitory computer readable storage medium, recording a program, and being loaded into a processor to:

• capture an original image of a target object by an optical lens, wherein the original image comprises a plurality of first images, wherein the target object is an integrated circuitry or a printed circuit board;
• perform an edge detection on the original image to obtain an edge image having an edge pattern, wherein the edge image comprises a plurality of second images having an edge pattern;
• calculate at least one of a maximum value, a minimum value, and an average value of a pixel value in the plurality of second images;
• divide the edge image into a plurality of image blocks according to a unit area, such that each of the image blocks includes N second images, wherein N is an integer greater than 0, and a value of N is determined according to a number of the first images included when the original image is captured;
• calculate a plurality of characteristic values corresponding to each of the image blocks according to the at least one of the maximum value, the minimum value, and the average value corresponding to the N second images comprised in each of the plurality of image blocks;
• and
• obtain an optimal regression model by training a regression model corresponding to a defect of the target object according to the plurality of characteristic values and a data of the target object.