Illumination Invariant Thermal Face Recognition using Convolutional Neural Network
Shinfeng D. Lin, Kuanyuan Chen · 2019
An illumination invariant thermal face recognition using convolutional neural network is proposed. The proposed CNN model includes training phase and testing phase. The convolutional layer of CNN model is utilized to extract features. This produces a feature map in the output image and the feature maps are fed to the next layer. The output from the last pooling layer is flattened and fed into a fully connected layer (FC layer). The goal of FC layer is to employ these features for classifying the input image into various classes based on the training datasets. Compared with the traditional thermal face recognition, experimental results demonstrate the superiority of the proposed method.