Multisource Image Fusion Method Using Support Value Transform

• Published in: IEEE transactions on image processing Vol. 16; no. 7; pp. 1831 - 1839
• Main Authors: Zheng, Sheng, Shi, Wen-Zhong, Liu, Jian, Zhu, Guang-Xi, Tian, Jin-Wen
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.07.2007; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Applied sciences; Artificial Intelligence; Data points; Detection, estimation, filtering, equalization, prediction; Discrete wavelet transforms; Exact sciences and technology; Filling; Image Enhancement - methods; Image fusion; Image Interpretation, Computer-Assisted - methods; Image processing; Image sensors; Imaging, Three-Dimensional - methods; Information theory; Information, signal and communications theory; Laplace equations; Least squares method; Least squares methods; mapped least squares support vector machine (mapped LS-SVM); Matched filters; Mathematical models; Methods; Mutual information; Pattern Recognition, Automated - methods; Preserves; Sensor fusion; Sensors; Signal and communications theory; Signal processing; Signal representation. Spectral analysis; Signal, noise; Studies; Subtraction Technique; support value transform (SVT); support vector machine (SVM); Support vector machines; Telecommunications and information theory; Transforms; Wavelet transforms; Image processing; support vector machine (SVM); support value transform (SVT); Support vector machine; Discrete wavelet transforms; Signal classification; Laplacian; Image method; Image quality; mapped least squares support vector machine (mapped LS-SVM); Least squares method; Multiscale method; Imaging; Information processing; Data fusion; Image sensor; Value analysis; Mutual information; Image fusion
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2007.896687

With the development of numerous imaging sensors, many images can be simultaneously pictured by various sensors. However, there are many scenarios where no one sensor can give the complete picture. Image fusion is an important approach to solve this problem and produces a single image which preserves all relevant information from a set of different sensors. In this paper, we proposed a new image fusion method using the support value transform, which uses the support value to represent the salient features of image. This is based on the fact that, in support vector machines (SVMs), the data with larger support values have a physical meaning in the sense that they reveal relative more importance of the data points for contributing to the SVM model. The mapped least squares SVM (mapped LS-SVM) is used to efficiently compute the support values of image. The support value analysis is developed by using a series of multiscale support value filters, which are obtained by filling zeros in the basic support value filter deduced from the mapped LS-SVM to match the resolution of the desired level. Compared with the widely used image fusion methods, such as the Laplacian pyramid, discrete wavelet transform methods, the proposed method is an undecimated transform-based approach. The fusion experiments are undertaken on multisource images. The results demonstrate that the proposed approach is effective and is superior to the conventional image fusion methods in terms of the pertained quantitative fusion evaluation indexes, such as quality of visual information (Q AB/F ) , the mutual information, etc.