Face attribute recognition method in community monitoring scene

Abstract

The invention relates to the technical field of image processing and deep learning, and particularly discloses a face attribute recognition method in a community monitoring scene, which combines an image enhancement technology, a face detection technology and a high-precision face attribute recognition technology. The method comprises the following steps: firstly, carrying out image enhancement processing on a part of pedestrian images acquired in a community environment by using a histogram equalization traditional method, and training an image enhancement network ReForce-Net by using processed data; performing deblurring preprocessing on the acquired original image data set by using the trained ReForceNet network, and performing pixel value normalization operation on the processed image;using a full convolutional neural network FCN to realize face key point detection; and utilizing the trained convolutional neural network FARNet to extract the aligned face attribute features, and performing classification and the like. According to the invention, the accuracy of subsequent face attribute recognition is improved through original image enhancement processing, and the precision offace attribute recognition is improved; and compared with other network models, the FAR-Net network model is more applicable.

Description

technical field [0001] The invention relates to the technical fields of image processing and deep learning, in particular to a face attribute recognition method in a community monitoring scene. Background technique [0002] With the continuous development of science and technology and network technology, the lifestyle of social residents is constantly changing, and people's daily life, basic necessities of life, clothing, food, housing and transportation are gradually changing to the direction of digitalization and networking. In recent years, with the rise of artificial intelligence technology and machine learning, the society has been continuously developed towards intelligence. Smart communities and smart cities are the products of the development of artificial intelligence. More and more researchers have begun to pay attention to the field of deep learning. Deep learning is the highest level in the current development stage of machine learning. Convolutional neural netw...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem of low accuracy and efficiency of face attribute recognition in the community monitoring scene, the purpose of the present invention is to provide a face attribute recognition method in the community monitoring scene

Images