Quotient Based Multiresolution Image Fusion of Thermal and Visual Images Using Daubechies Wavelet Transform for Human Face Recognition
This paper investigates Quotient based Fusion of thermal and visual images, which were individually passed through level-1 and level-2 multiresolution analyses. In the proposed system, the method-1 namely "Decompose then Quotient Fuse Level-1" and the method-2 namely "Decompose-Reconstruct in level-2 and then Fuse Quotients", both work on wavelet transformations of the visual and thermal face images. The wavelet transform is well-suited to manage different image resolutions and allows the image decomposition in different kinds of coefficients, while preserving the image information without any loss. This approach is based on a definition of an illumination invariant signature image which enables an analytic generation of the image space with varying illumination. The quotient fused images are passed through Principal Component Analysis (PCA) for dimension reduction and then those images are classified using a multi-layer perceptron (MLP). The performances of both the methods have been evaluated using OTCBVS and IRIS databases. All the different classes have been tested separately, among them the maximum recognition result for a class is 100% and the minimum recognition rate for a class is 73%.
Keywords: Discrete Wavelet Transform, Inverse Discrete Wavelet Transform, Quotient Fused Image, Principal Component Analysis (PCA), Multi-layer Perceptron (MLP), Face Recognition, Classification
Download Full-Text
