Image processing method and device, electronic device and storage medium

Abstract

The present disclosure relates to an image processing method and device, electronic equipment, and a storage medium. The method includes: performing feature equalization processing on a sample image through an equalization sub-network of a detection network to obtain an equalized feature image of the sample image; Perform target detection processing on the balanced feature image to obtain the predicted area of ​​the target object in the balanced feature image; respectively determine the intersection ratio of each predicted area; according to the intersection ratio of each predicted area, sample multiple predicted areas to obtain the target area ; According to the target area and the marked area, train the detection network. According to the image processing method of the embodiment of the present disclosure, performing feature equalization processing on the target sample image can avoid information loss and improve training effect. Moreover, the target area can be extracted according to the intersection ratio of the prediction area, which can increase the probability of extracting the prediction area that is difficult to determine, improve the training efficiency, and improve the training effect.

Description

Technical field[0001]The present disclosure relates to the field of computer technology, and in particular to an image processing method and device, electronic equipment, and storage medium.Background technique[0002]In related technologies, in the process of neural network training, difficult samples and simple samples are of different importance for neural network training. Difficult samples can obtain more information during the training process, making the training process more efficient and the training effect better , But in a large number of samples, the number of simple samples is larger, resulting in lower training efficiency. In addition, during the training process, each level of the neural network focuses on the extracted features, but it may cause information loss, resulting in poor detection effects of the neural network during use.Summary of the invention[0003]The present disclosure proposes an image processing method and device, electronic equipment and storage medium...

AI Technical Summary

Problems solved by technology

[0002] In related technologies, in the process of neural network training, the importance of difficult samples and simple samples to neural network training is different, and difficult samples can obtain more information during the training process, making the training process more efficient and the training effect better , but in a large number of samples, the number of simple samples is more, resulting in lower training efficiency

Moreover, during the training process, each level of the neural network has its own focus on the extracted features, but it may cause information loss, resulting in poor detection results during the use of the neural network.

Images