作者: Zhan Wu , Min Peng , Tong Chen
DOI: 10.1109/OPTIP.2016.7528489
关键词:
摘要: With the rapidly development of face recognition (FR), thermal has received increasing attention. However, traditional methods for mainly concentrate on hand-crafted feature design, which requires more efforts from human to select and extract features usually relatively lower rate. In this paper, we present a convolutional neural network (CNN) architecture recognition. CNN is new type method can automatically learn effective raw data. Experiment results RGB-D-T database show that our proposed achieves higher rate compared with such as LBP, HOG moments invariant.