Comparative Analysis on Different Fusion Methods Using Canny Edge Detection

In recent year, there has been a growing interest in merging images obtained using multiple sensors in academia, industry, and military due to the important role it plays in the applications related to these fields. Image fusion, a class of data fusion, aims at combining two or more source images from the same scene into an image that retains the most important salient features present in all the source images according to a specific fusion scheme. The composite image should provide increased interpretation capabilities and significantly reduce both human and machine errors in detection and object recognition. Edge detection is a common approach for detection of meaningful discontinuities in gray levels.
Automatic boundary detection with in an image is a challenging task. Humans are very good as their visual system makes this task possible within a moment whereas considerable efforts are required for machines to replicate the same or somewhat nearer. This paper presents an innovative way to apply canny edge detection on fused image for analyzing the fusion methods and finding which method is best among all which are discussed in this. In this paper Averaging method, Wavelet based methods like orthogonal, bi-orthogonal and non orthogonal, Wavelet Principal Component Analysis (WPCA) and Laplacian transform Wavelet transform fusion is more formally defined by considering the wavelet transforms for the two registered input images together with the fusion rule., In this paper the canny edge detection on different fused images are compared visually and statistically. The work is also supplemented by algorithms, which help us analyze the output qualitatively on attributes like Entropy, mean, Standard deviation, Covariance Correlation Coefficient.