Thermal Human Face Recognition Based on Haar Wavelet Transform and Series Matching Technique

Abstract

Thermal infrared (IR) images represent the heat patterns emitted from hot object and they don't consider the energies reflected from an object. Objects living or non-living emit different amounts of IR energy according to their body temperature and characteristics. Humans are homoeothermic and hence capable of maintaining constant temperature under different surrounding temperature. Face recognition from thermal (IR) images should focus on changes of temperature on facial blood vessels. These temperature changes can be regarded as texture features of images and wavelet transform is a very good tool to analyze multi-scale and multi-directional texture. Wavelet transform is also used for image dimensionality reduction, by removing redundancies and preserving original features of the image. The sizes of the facial images are normally large. So, the wavelet transform is used before image similarity is measured. Therefore this paper describes an efficient approach of human face recognition based on wavelet transform from thermal IR images. The system consists of three steps. At the very first step, human thermal IR face image is preprocessed and the face region is only cropped from the entire image. Secondly, "Haar" wavelet is used to extract low frequency band from the cropped face region. Lastly, the image classification between the training images and the test images is done, which is based on low-frequency components. The proposed approach is tested on a number of human thermal infrared face images created at our own laboratory and "Terravic Facial IR Database". Experimental results indicated that the thermal infra red face images can be recognized by the proposed system effectively. The maximum success of 95% recognition has been achieved.

Optimized superpixel and AdaBoost classifier for human thermal face recognition

“…Compared with some of the related work which used Terravic dataset, our proposed model achieved promising results (approximately 99%) while the model that were proposed in [4], [5] and [8] achieved 92.2%-94.1%, 93% and 94.1%, respectively. This achievement was obtained due to: (1) the proposed segmentation method, which extracts only the face and removes the background or any other noise, (2) using SFTA algorithm which extracts discriminative features, (3) using the rough set-based feature selection methods which remove the irrelevant features and improve the classification accuracy and (4) using the AdaBoost classifier which increases the weight of critical samples and hence improves the classification performance.…”

“…The experiments proved that using minimum distance and Artificial Neural Networks (ANNs) classifiers the obtained results were 94.11% and 92.15%, respectively, using the Terravic Facial IR Dataset. Also, Seal et al proposed an approach used Discrete Wavelet Transform (DWT) for feature extraction and dimensionality reduction [5]. The experiments using their private database showed that the recognition rate was 95%.…”

On-Road Driver Emotion Recognition Using Facial Expression

“…The handcrafted features include Gobar wavelets [18], line-based caricatures [19], scale-invariant feature transform [20], histograms of oriented gradients (HOG) [21], local binary patterns (LBP) [22], minutiae points [23], Haar wavelet [24], and histograms of bunched intensity values (HBIV) [25]. The features using machine learning methods include dynamic-Bayesian networks (DBN) [26] and SVM [27][28][29][30][31] for further classification.…”

Facial Expression Recognition Using Local Gravitational Force Descriptor-Based Deep Convolution Neural Networks

“…Mainly two steps, namely, feature extraction and classification, are associated with the FER task. Conventional features, such as Gobar wavelets [4], curves [12], scale-invariant feature transform [21], HOG [8], LBP [6], minutiae points [11], Haar wavelet [5], HBIV [9], DBN [10], and edges [38], were exploited with advanced domain comprehension in the first step. In the second step, support vector machine (SVM) [39], feedforward neural network [40], and extreme learning machine [41] were adopted for classification.…”

“…Appearance-based methods rely on various statistics of the pixels' values within the face image. Examples include Gobar wavelets [4], Haar wavelet [5], local binary pattern (LBP) [6], [7], histogram of oriented gradients (HOG) [7], [8], histogram of bunched intensity values (HBIV) [9], dynamic Bayesian network (DBN) [10], and so on. On the other hand, geometric features are obtained by transforming the image into geometric primitives, such as corner or minutiae points [11], edges, and curves [12].…”