Objective Assessment of Multiresolution Image Fusion Algorithms for Context Enhancement in Night Vision: A Comparative Study

Abstract

Comparison of image processing techniques is critically important in deciding which algorithm, method, or metric to use for enhanced image assessment. Image fusion is a popular choice for various image enhancement applications such as overlay of two image products, refinement of image resolutions for alignment, and image combination for feature extraction and target recognition. Since image fusion is used in many geospatial and night vision applications, it is important to understand these techniques and provide a comparative study of the methods. In this paper, we conduct a comparative study on 12 selected image fusion metrics over six multiresolution image fusion algorithms for two different fusion schemes and input images with distortion. The analysis can be applied to different image combination algorithms, image processing methods, and over a different choice of metrics that are of use to an image processing expert. The paper relates the results to an image quality measurement based on power spectrum and correlation analysis and serves as a summary of many contemporary techniques for objective assessment of image fusion algorithms.

Image Fusion Algorithm Based on Contourlet Transform and PCNN for Detecting Obstacles in Forests

“…Thus, the greater the entropy of the fused image is, the more abundant information the fused image provides, and the greater the quality of the fusion is [17,18]. The entropy of a fused image was calculated according to (9) where E is the entropy of an image, and i P is the probability of i in the image, i means value (which is a number between 0 up to 255).…”

Context-based Information Fusion: A survey and discussion

“…Improvements are discussed in [61], while a multiresolution approach is proposed in [62]. A recent comparative study on algorithms for objective assessment of multi-resolution image fusion for CE can be found in [63]. It should be noted however, that CE, as it is understood in these works, is essentially an image fusion technique and the focus is given to the quality of the resulting image [63] rather than the actual help that CE could bring to the primary fusion task (e.g.…”

Multimodality and Multiresolution Image Fusion

“…Many different metrics have already been proposed, but they rate algorithms differently (Liu et al, 2012). A rather general metric as the mutual information fusion metric persistently favors fusion by simply averaging input images (Cvejic et al, 2006), and looks not very suited for our new method.…”

“…A rather general metric as the mutual information fusion metric persistently favors fusion by simply averaging input images (Cvejic et al, 2006), and looks not very suited for our new method. The choice for a metric is driven by the requirements of the application (Liu et al, 2012). In future research we plan to apply the 12 metrics used by the latter, and possibly devise an additional one of our own making, to make an objective assessment of our new method.…”