A classification method for face images under complex illumination based on multi-agent cooperation

Abstract

The invention discloses a face image classification method under complex illumination based on multi-agent cooperation, and the method comprises the steps of (1), obtaining a face image set, and extracting the principal component features, texture features and gradient features of all face images; (2) respectively clustering the principal component characteristics, the texture characteristics andthe gradient characteristics to obtain a plurality of clustering sets; (3) establishing a human face feature extraction network for each clustering set, establishing a human face classification network according to the human face feature extraction network, and training the human face classification network to obtain a human face classification model; (4) extracting principal component characteristics, texture characteristics and gradient characteristics of the face image to be detected, and dividing the principal component characteristics, the texture characteristics and the gradient characteristics into three corresponding cluster sets; and (5) inputting the to-be-detected face image into the face classification models corresponding to the three clustering sets respectively, and obtaining a classification result of the to-be-detected face image through calculation.

Description

technical field [0001] The invention belongs to the field of image recognition, and in particular relates to a method for classifying human face images under complex illumination based on multi-agent cooperation. Background technique [0002] Convolutional neural networks have been sought after due to their powerful feature extraction capabilities. The convolutional neural network not only has the advantages of good fault tolerance, self-adaptability and strong self-learning ability of the traditional neural network, but also has the advantages of automatic feature extraction and weight sharing, so the convolutional neural network is easier than other networks. train. In recent years, the convolutional neural network has achieved a series of breakthrough research results in the fields of image classification, object detection, and image semantic segmentation, and its powerful feature learning and classification capabilities have been favored by the industry. Relevant exper...

AI Technical Summary

Problems solved by technology

In real life, due to the influence of complex lighting conditions such as insufficient lighting, uneven lighting, dramatic lighting changes, or excessive lighting, the acquired face images are prone to serious loss of local details, large noise, and less information. , has brought severe challenges to computer intelligent recognition technology

Images