Full and Reduced Reference Image Quality Assessment of Panoramic View using Novel Hybrid Image Stitching Method

Abstract

Image Stitching is becoming more popular in field of computer vision because of rapid development of efficient algorithms that replaces the high cost wider lens cameras and commercial image stitching tools. The existing methods used global geometric transformation in registration stage and hence suffered from object deformation, parallax error, ghosting effect and motion blur in output result. In this paper, newly developed Hybrid Warping of weighted linearized homography matrix and similarity transform matrix is implemented over standard image stitching database. The visual quality of stitched image using proposed method has been examined in terms of performance metrics of Full Reference Image Quality Assessment (FRIQA) such as Root Mean Square Error (RMSE), Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM) and Reduced Reference Image Quality Assessment (RRIQA). Also, the performance analysis of proposed method is compared against existing image stitching methods in terms of field of view and stitching time. This analysis has ascertained the outperformance of Novel Hybrid Image Stitching method.