Study on algorithm evaluation of image fusion based on multi-hierarchical synthetic analysis

To resolve the algorithm evaluation issue of multi-sensor image fusion, we propose a novel synthetic evaluation method using multi-hierarchical gray relational analysis mechanism, which has the merit of using small-sized samples and of allowing unitary comparison. The proposed method combines a priori knowledge and quantization evaluation. In this paper we first outline a basic three-step procedure in order toperform the gray relational analysis for a single-hierarchy evaluation system, and then give a four-step procedure to perform multi-hierarchical evaluation system. Therefore, we obtain a synthetic evaluation result that is more quantitative and comprehensive than conventional subjective and objective measures such as correlation coefficient and average gradient. The novel evaluation method can give not only overall performance evaluation for image fusion algorithm but also specific performance evaluation. Extensive experimental analysis shows that the proposed method generates better evaluation result with respect to quantization, precision, objectivity, reliability, and real-time evaluation. These advantages make it applicable to fusion systems with feedback capability, and can enrich and perfect the image fusion system.