This paper introduces a novel challenge to “scene-referred” pleasant color reproduction. Principal component of objective color in reference image is transferred to that of source image by PCA matching, so that color atmosphere is transferred from one scene to another without any color targets or test chart. Image segmentation is a first step to vision system and used as a pre-processing for many image processing applications. In the previous papers, we reported an object-to-object color transformation between images with color similarity based on unsupervised image segmentation by color clustering. This paper proposes an advanced image segmentation method by [k-means+Bayesian] classifier and demonstrates “scene-to-scene color interchange” between different images with color dissimilarity.

View full abstract

View interpolation has been extensively studied in recent years. It is considered as synthesizing a series of continuous and realistic intermediate views between a pair of reference images without 3D knowledge. In general, the synthesizing procedure consists of five main steps including feature tracking, fundamental matrix constructing, image pre-warping, view morphing, and image post-warping. Because the last three steps are formulated as a common approach, the first two steps determine the accuracy and efficiency of view interpolation. In this paper, we discuss the reasons and phenomena by which the feature tracking parameters and their change constraints can influence the fundamental matrix constructing. Here, the discussed feature tracking parameters are mainly set by focal length, feature number, and feature patch size. Enlarging focal length, increasing feature number, and setting suitable feature patch size can generate the higher quality correspondences of feature, and then compute the correct fundamental matrix. These parameters' influences in the first step could be transferred to the other steps of view interpolation, then determine the final appearance of view interpolation. Experimental results show that in acceptable computational complexity, the feature tracking parameters can change the visual effects in view interpolation.

View full abstract

JPEG-LS is the first international standard which specifies the nearness for the difference between the pixel of the original image and the pixel of the reconstructed image. However, few references can be found which describe the evaluation of the near-lossless coding of JPEG-LS. This reference paper reports evaluation of the JPEG-LS near-lossless coding, by summarizing the experimental results, especially considering the run-mode. We first report the outline of the JPEG-LS near-lossless coding and the outline of the evaluation program implemented for experiments, then reports items considered concerning run-mode, compression ratio, and image quality, based on the experimental results by the evaluation program.

View full abstract