Image-recognition apparatus, image-recognition method, and non-transitory computer-readable storage medium thereof

An image-recognition method, comprising:

• receiving a plurality of check-point images, and classifying the check-point images into a plurality of groups;
• classifying the check-point images in each group into a plurality of types for each group to generate first structured data;
• balancing a number of the check-point images in each type of each group in the first structured data to generate second structured data, wherein the second structured data comprises training-set data and testing-set data;
• training an artificial-intelligence (AI) model using the training-set data;
• and
• inputting the testing-set data into the AI model to obtain a model evaluation of the AI model;
• wherein there is a first number of the check-point images in each group of the second structured data generated by the image-generating module, and a second number of check-point images in each type of the plurality of types for each group is obtained by dividing the first number by a number of the plurality of types for each group.

An image-recognition apparatus, comprising:

• a non-volatile memory, configured to store an artificial-intelligence (AI) image-recognition program;
• and
• a processor, configured to execute the AI image-recognition program to perform the following steps:
• receiving a plurality of check-point images, and classifying the check-point images into a plurality of groups;
• classifying the check-point images in each group into a plurality of types for each group to generate first structured data;
• balancing a number of the check-point images in each type of each group in the first structured data to generate second structured data, wherein the second structured data comprises training-set data and testing-set data;
• training an artificial-intelligence (AI) model using the training-set data;
• and
• inputting the testing-set data into the AI model to obtain a model evaluation of the AI model;
• wherein there is a first number of the check-point images in each group of the second structured data generated by the image-generating module, and a second number of check-point images in each type of the plurality of types for each group is obtained by dividing the first number by a number of the plurality of types for each group.