Open AccessResearch on Face Recognition Technology Based on Improved YOLO Deep Convolution Neural Network
Author(s) -
Yu Fan,
Yiyue Luo,
Xianjun Chen
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1982/1/012010
Subject(s) - softmax function , artificial intelligence , computer science , deep learning , fuse (electrical) , facial recognition system , convolution (computer science) , pattern recognition (psychology) , face (sociological concept) , feature (linguistics) , artificial neural network , pyramid (geometry) , convolutional neural network , function (biology) , field (mathematics) , computer vision , mathematics , engineering , social science , linguistics , philosophy , geometry , evolutionary biology , sociology , pure mathematics , electrical engineering , biology
With the development of information technology, deep learning has become a research hots pot in the field of computer vision, among which face recognition technology, as one of its applications, has received extensive attention in recent years. A face recognition method based on improved YOLOv3 deep convolution neural network is proposed. The feature pyramid network is used to obtain the four scale features of the target to fuse the shallow features and the deep features, and the influence weight of the loss function is adjusted according to the size of the detected target, so as to enhance the detection effect of small targets and mutually occluded objects, and the Softmax function is used for classification and recognition. Experimental results on mixed data sets show that this method can improve the real-time performance of face detection.