Abstract: A defect detection method includes: obtaining an image of a first defective block output by the SPI machine; wherein the first defective block is a solder paste block that is not qualified for printing after being detected by the SPI machine; processing the image of the first defective block; detecting whether solder paste printing in the first defective block is qualified; and determining that the first defective block is a second defective block and determining a defect type of the first defective block when the solder paste printing of the first defective block is not qualified. A terminal device and a non-volatile storage medium therein, for performing the above-described method, are also disclosed.

Abstract: An image processing method for identifying text on production line components obtains an image to be recognized and a standard image for reference and extracts a first text area of the image to be recognized. A second text area of the standard image is obtained, and a text window is extracted based on the second text area. The method further obtains a target text area of the image to be recognized based on the first text area and the text window, and obtains a first set of first text sub-areas, and obtains a second set of second text sub-areas, by dividing the second text area into sub-windows of the text window. The method further marks the image to be recognized as a qualifying image when each first text sub-area of the first set is the same as a corresponding second text sub-area of the second set.

Abstract: A method for setting testing thresholds applied by a testing device to products being made includes obtaining an initial lower threshold for testing the products and counting, followed by manual review, first, second, third, and fourth type product qualities as being quantities under the initial lower threshold. The method adds a minimum product parameter of defective products, the initial lower threshold, and a number of values between the minimum product parameter and the initial lower threshold into a set, repeating the application of one selected element from the set as an experiment threshold. First to fourth type quantities of the current products are counted again under the experiment threshold, an effectiveness of each element of the set is calculated, and an element of the set with the maximum effectiveness is defined as a suggested lower threshold for testing the products.

Abstract: An image processing method for identifying text on production line components obtains an image to be recognized and a standard image for reference and extracts a first text area of the image to be recognized. A second text area of the standard image is obtained, and a text window is extracted based on the second text area. The method further obtains a target text area of the image to be recognized based on the first text area and the text window, and obtains a first set of first text sub-areas, and obtains a second set of second text sub-areas, by dividing the second text area into sub-windows of the text window. The method further marks the image to be recognized as a qualifying image when each first text sub-area of the first set is the same as corresponding second text sub-area of the second set.

Abstract: A method for setting testing thresholds applied by a testing device to products being made includes obtaining an initial lower threshold for testing the products and counting, followed by manual review, first, second, third, and fourth type product qualities as being quantities under the initial lower threshold. The method adds a minimum product parameter of defective products, the initial lower threshold, and a number of values between the minimum product parameter and the initial lower threshold into a set, repeating the application of one selected element from the set as an experiment threshold. First to fourth type quantities of the current products are counted again under the experiment threshold, an effectiveness of each element of the set is calculated, and an element of the set with the maximum effectiveness is defined as a suggested lower threshold for testing the products.