Quotient Based Multiresolution Image Fusion of Thermal and Visual Images Using Daubechies Wavelet Transform for Human Face Recognition

TL;DR

This paper presents a multiresolution image fusion technique using Daubechies wavelet transform for thermal and visual face images, enhancing recognition accuracy with quotient-based fusion and PCA classification.

Contribution

It introduces quotient-based fusion methods at multiple wavelet decomposition levels for thermal and visual images, improving face recognition performance.

Findings

Maximum recognition accuracy achieved is 100%.

Wavelet-based quotient fusion preserves image information effectively.

Fusion methods outperform traditional techniques in recognition tasks.

Abstract

This paper investigates the multiresolution level-1 and level-2 Quotient based Fusion of thermal and visual images. In the proposed system, the method-1 namely "Decompose then Quotient Fuse Level-1" and the method-2 namely "Decompose-Reconstruct then Quotient Fuse Level-2" both work on wavelet transformations of the visual and thermal face images. The wavelet transform is well-suited to manage different image resolution 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 is 100%.