Abstract

Image interpolation enhances the quality of images by introducing new pixels in the given image. The new pixels are created by using old pixels. Non-adaptive and adaptive interpolations are the two major categories of image interpolation which are widely used in multimedia applications. Non-adaptive image interpolation performs the same operation throughout the entire interpolation process. But the adaptive image interpolation performs differently based the characteristics of the surrounding pixels of the interpolation point. Adaptive image interpolation performs complex operations to improve the quality of image and it provides high-quality interpolation as compared with conventional non-adaptive interpolation. This work evaluates the characteristics of different adaptive image interpolation in terms of their quantitative measures. Both peak signal to noise ratio (PSNR) and structural similarity index measure (SSIM) are considered for this evaluation. Based on the detailed review, it is identified that the adaptive image interpolation using edge-orientation outperforms other adaptive interpolation schemes. Further, it affords that the quality of interpolation can also be improved by using optimized filters and by splitting the edge-regions by higher order.