Panoramic mosaic conception using optimal seam with graded colour correction
Sunil Karamchandani, P. Siganporia, M. Shah, Zeel Thakkar · 2015
We propose a duplex methodology for merging a set of aligned source images with exceedingly dissimilar colours and luminance into a composite panorama with amenable blending attributes. The algorithm performs an optimal seam to determine the suture point which consequently is expertly camouflaged using the graded colour blending to create the vista. Exposure leveler is the pedestal on which the dual algorithms are juxtaposed. The individual Y components of each slice are normalized as the direct ratio of the maximum luminance averaged over the brightest source image. The graded colour blending performs a smooth transition over the seam by weighing the pixels colours as an inverse function of the square of the distance from the seam. The technique has been exhaustively verified on divergent image sequences which generate progressively transcendent sutures in both indoor and outdoor scenarios providing comparatively low values of mse (~11.18).