Image classification method based on RGB three-component grouping attention weighted fusion

Abstract

The invention provides an image classification method based on RGB three-component grouping attention weighted fusion, and the method comprises the steps: collecting a target image in a complex environment, and carrying out the noise reduction processing, and obtaining a denoised target image; and respectively extracting RGB three-channel component images of the denoised target image. According to the image classification method based on RGB three-component grouping attention weighted fusion, RGB three components are introduced, an attention mechanism is introduced into the residual network model, global and local color three-component features are fully utilized for feature extraction, and the classification effect on targets with noise interference and bright colors, especially small targets, is good.

Description

technical field [0001] The invention relates to the technical field of image classification and intelligent optimization, in particular to an image classification method based on RGB three-component grouping attention weighted fusion. Background technique [0002] With the development of computer vision technology, applications such as traffic video surveillance, automatic identification of crop diseases and insect pests, and automatic equipment detection of industrial products have put forward higher requirements for the quality of visual recognition. How to accurately classify the extracted object images has become a problems to be solved. In practical applications, the captured video images are often affected by factors such as illumination changes, target occlusion, noise interference, etc., and the targets in the images are difficult to detect, especially due to factors such as low resolution and small size, some tiny targets are even more difficult to detect. , the ex...

AI Technical Summary

Problems solved by technology

In practical applications, the captured video images are often affected by factors such as illumination changes, target occlusion, and noise interference. The targets in the image are difficult to detect, especially due to factors such as low resolution and small size, some tiny targets are even more difficult to detect. , the extracted feature information is missing, resulting in misjudgment of the detection results, and the accuracy of target classification is not high in complex scene environments

Images