Image training set generation method and model training method based on image data enhancement

Abstract

The invention provides an image training set generation method and a model training method based on image data enhancement, and the method comprises the steps of constructing an initial image training set, and then training an initial target detection model; re-detecting the original training sample image and then outputting a detection output image; comparing a detection frame formed on each detection output image with a labeling frame on the original training sample image, and cutting error target image blocks selected by the detection frames; cutting a rejected image block from the selected original training sample image, selecting a wrong target image block, and compensating the wrong target image block at the original position of the rejected image block to form a negative sample image; and mixing into an initial image training set to form an image training set. According to the invention, the problem that a pattern training set expanded by using a data enhancement method in the prior art can improve the generalization ability of a trained target detection model but cannot improve the recognition accuracy of the target detection model to a specific target object is solved.

Description

technical field [0001] The present invention relates to the technical field of image processing and model training, in particular, to a method for generating an image training set and a method for model training based on image data enhancement. Background technique [0002] In the existing field of computer vision, the target detection model based on deep learning is usually used to make decisions. In order to achieve the ideal training effect of the target detection model, an image training set containing a large number of image samples needs to be used in the model training process. When the number of image samples is insufficient, it is necessary to use data enhancement methods to expand the image training set. [0003] In related technologies, geometric transformation, color change, or mixed sample data enhancement are usually used to obtain more image sample data. Although the above-mentioned several data enhancement methods can effectively expand the pattern training s...

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to provide an image training set generation method and a model training method based on image data enhancement, so as to solve the problem of using the image training set expanded by the data enhancement method in the prior art, and to improve the performance of the trained target detection model. Generalization ability, but cannot improve the recognition accuracy of the target detection model for specific target objects

Images