Infrared Image Analysis for Human Face Recognition

Thermal infrared images have potential to captured the images without being affected by illumination. In this paper, we proposed a face recognition method using infrared images. The Convolution Neural Network are used to extract feature from the images with the combination of Haar Cascade, and Local Binary Pattern to indicate the face area. At the same time, images were acquired by using infrared camera and webcam. Compared between infrared and visible images, the experimental result from infrared images by using Convolutional Neural Network in combined with Haar Cascade show superiority in the measurement result of several parameters used with the highest score in accuracy up to 98% which outperforms the other experiment in this paper.