Assessment approach for image mosaicing algorithms
Li-hui Zou · Optical Engineering · 2011
In this paper, a novel quantitative assessment approach for image mosaicing algorithms is proposed by evaluating the quality of an output mosaic image and comparing with the input images. Five evaluation indices-entropy, clarity, registration error, peak signal-to-noise ratio, and structural similarity-are calculated and combined with the analytic hierarchy process for comprehensive assessment. This approach can overcome the lack of panoramic image and is easy to implement. Experimental results show the objectivity and the validity of the proposed approach.