Image processing method and device, electronic equipment and storage medium

Abstract

The invention relates to an image processing method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the feature equalization processing of a sample image through an equalization sub-network of a detection network, and obtaining an equalization feature image of the sample image; Performing target detection processing on the equalization feature image through a detection sub-network to obtain a prediction area of a target object in the equalization feature image; Determining the cross-to-parallel ratio of each prediction area; Sampling a plurality of prediction areas according to the cross-to-parallel ratio of each prediction area to obtain a target area; And training the detection network according to the target area and the labeling area. According to the image processing method disclosed by the embodiment of the invention, feature equalization processing is carried out on the target sample image, information loss can be avoided,and the training effect is improved. Moreover, the target area can be extracted according to the cross-to-parallel ratio of the prediction area, the probability of extracting the prediction area difficult in the determination process can be improved, the training efficiency is improved, and the training effect is improved.

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 a storage medium. Background technique [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 emphasis on the extracted features, but it may cause information loss, resulting in poor detection results during the use of the neural network. Contents of the invention [0003] The disclosure proposes an image processing method and device, ele...

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