Image enhancement processing method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of neural networks of the artificial intelligence technology, and provides an image enhancement processing method and device, computer equipment and a storage medium, and the method comprises the steps: carrying out the amplification of an image of a data set through employing a data enhancement algorithm, carrying out the classification of a target image through employing a digital recognition model, and obtaining a classification result; screening out a first target image which is correctly classified and a second target image which is wrongly classified; obtaining a first weight vector and a feature vector of the first target image of each category, and training a pre-constructed image recognition model by using the first target image to obtain a trained image recognition model; and predicting the second target image by using the trained image recognition model to obtain a prediction result, generating a second weight vector according to the prediction result, and multiplying the second weight vector by the second target image to obtain a quality-enhanced training image, so that inherent noise existing in the second target image can be suppressed, and the quality of the target image is improved. And the quality of the image after data enhancement is improved.

Description

technical field [0001] The present application relates to the technical field of neural networks of artificial intelligence technology, and in particular, the present application relates to an image enhancement processing method, apparatus, computer equipment and storage medium. Background technique [0002] At present, machine learning methods have been maturely applied to various high-performance model architectures, but their generalization ability still has problems. As far as handwritten digit recognition is concerned, the data obtained in practical applications are often accompanied by irregular handwriting, differences in handwriting between different individuals, and different degrees of noise. [0003] By using data enhancement methods, the generalization ability of the model can be improved and over-fitting can be reduced. However, most of the existing data enhancement methods change the spatial position and size of the target through simple rotation, translation, ...

AI Technical Summary

Problems solved by technology

As far as the problem of handwritten digit recognition is concerned, the data obtained in practical applications are often accompanied by problems such as irregular handwriting, differences in handwriting between different individuals, and different degrees of noise.

[0003] The generalization ability of the model can be improved and overfitting can be reduced by using data enhancement methods, but most of the existing data enhancement methods use simple rotation, translation, etc. to change the spatial position, size, etc. of the target, and the image after data enhancement There will also be Siamese, background noise, etc., and the quality is low

Images