Recently, spatial principal component analysis of census transform histograms (PACT) was proposed to recognize instance and categories of places or scenes in an image. An improved representation called Local Difference Binary Pattern (LDBP) also was proposed and performed better than that of PACT. LDBP is based on the comparisons between center pixel and its neighboring pixels, but the relation...

Transform coding constitutes an integral component of contemporary image/video processing applications. Transform coding relies on the premise that pixels in an image exhibit a certain level of correlation with their neighboring pixels. Similarly in a video transmission system, adjacent pixels in consecutive frames 2 show very high correlation. Consequently, these correlations can be exploited ...

Video matting attempts to extract foreground images from an image sequence, as well as the alpha-mattes that describe their transparency. This papers presents an automated video matting framework using motion-based segmentation and bayesian matting. We build upon existing techniques for layer segmentation based on optical flow to generate a coarse trimap, by identifying image pixels as belongin...

We present a context-based scanning algorithm which reorders the input image using a hierarchical representation of the image. Our algorithm optimally orders (permutes) the leaves corresponding to the pixels, by minimizing the sum of distances between neighboring pixels. The reordering results in an improved autocorrelation between nearby pixels which leads to a smoother image. This allows us, ...

This paper introduces a power-efficient readout scheme for CMOS image sensors utilizing SAR ADCs. Inspired by the strong correlation between neighboring pixels, each SAR ADC assigned to readout multiple columns of pixels reads each pixel by first copying several MSBs from the previous pixel and, desirably, converts only LSBs to save conversion cycles and power consumption. The readout concept w...