A Comparative Study of Human Thermal Face Recognition Based on Haar Wavelet Transform and Local Binary Pattern

Abstract

Thermal infrared (IR) images focus on changes of temperature distribution on facial muscles and blood vessels. These temperature changes can be regarded as texture features of images. A comparative study of face two recognition methods working in thermal spectrum is carried out in this paper. In the first approach, the training images and the test images are processed with Haar wavelet transform and the LL band and the average of LH/HL/HH bands subimages are created for each face image. Then a total confidence matrix is formed for each face image by taking a weighted sum of the corresponding pixel values of the LL band and average band. For LBP feature extraction, each of the face images in training and test datasets is divided into 161 numbers of subimages, each of size 8 × 8 pixels. For each such subimages, LBP features are extracted which are concatenated in manner. PCA is performed separately on the individual feature set for dimensionality reduction. Finally, two different classifiers namely multilayer feed forward neural network and minimum distance classifier are used to classify face images. The experiments have been performed on the database created at our own laboratory and Terravic Facial IR Database.

Multi Biometric Thermal Face Recognition Using FWT and LDA Feature Extraction Methods with RBM DBN and FFNN Classifier Algorithms

“…Experiments were done by, Bhattacharjee, Seal, Ganguly, Nasipuri, and Basu, with the Terravic Facial IR Database. Using Haar wavelet transform and Local Binary Pattern (LBP) [24]. Martinez, Binefa, and Pantic propose recognition, in thermal images, using the detection of the eyes, nostrils and mouth.…”

“…Taking a lead from a paper on thermal facial recognition [24] and other works which use soft biometrics to augment hard biometric methods [25], [14]. A contemporary approach, to person recognition, using thermal imaging is being proposed.…”

À‐trous wavelet transform‐based hybrid image fusion for face recognition using region classifiers

“…The fused images are formed by some weighted factor, which is determined by 2v-GSVM. Then, local and global features from the fused images are extracted using 2D log-polar Gabor transform (Singh, Vatsa, & Noore, 2007a) and local binary pattern (Ahonen, Hadid, & Pietikainen, 2006;Bhattacharjee et al, 2012) algorithms, respectively. The corresponding match scores are fused using Dezert-Smarandache theory of fusion (Singh et al, 2007b), which is based on plausible and paradoxical reasoning.…”

“…Recently, researchers are using infrared images to reduce the illumination effects to a certain extent because the infrared image is illumination independent (Pop, Gordan, Florea, & Vlaicu, 2010;Reyhanian & Arbabi, 2015;Wang, He, Wu, He, & Ji, 2014;Nguyen, 2016). Recently, authors have also started to work in this field in Bhattacharjee, Seal, Ganguly, Nasipuri, and Basu (2012); Seal, Bhattacharjee, Nasipuri, and Basu (2013); and Seal, Bhattacharjee, Nasipuri, and Gonzalo-Martin (2014). The thermal image is captured by thermal sensor, which concentrates on electromagnetic spectrum having a wavelength in the range of 8 to 14 m. The face recognition systems using infrared images performs poorly for pose changes and different facial expressions.…”

Robust Thermal Face Recognition Using Region Classifiers

“…9 This algorithm is based either on \4-connected" neighbors or \8-connected" neighbor's method. 7,17 In this study \8-connected" neighbor's method is used. It is a binary image.…”