We propose a novel complex activity recognition and localization framework which effectively fuses information from both grayscale and depth image channels at multiple levels of the video processing pipeline. In the individual visual feature detection level, depth based filters are applied to the detected human/object rectangles to remove false detections. In the next level of interaction model...

We experimentally demonstrate a camera whose primary optic is cannula (diameter=0.22mm and length=12.5mm) that acts lightpipe transporting light intensity from an object plane (35cm away) to its opposite end. Deep neural networks (DNNs) are used reconstruct color grayscale images with field of view 180 angular resolution ~0.40. When trained on depth information, the DNN can create maps. Finally...

This paper presents a novel approach to grayscale image matting and colorization. The first part of this approach is an efficient grayscale image matting algorithm in Bayesian framework. The foreground and background color distributions, and the alpha’s distribution are modelled with spatially varying sets of Gaussians. The major novelties of this matting algorithm are the introduction of alpha...

Introduction While a picture may say a thousand words, scientists and engineers often need to extract precise, quantitative information regarding physical processes from photographic evidence. Image analysis can, for example, be used as part of a quality control process in an industrial application, to monitor earth systems from space using satellite data, or to reconstruct changes in past clim...

Given an grayscale digital image, and a positive integer $n$, how well can we store the image at compression ratio of $n:1$? In this paper address above question in extreme cases when $n>>50$ using "$\mathbf{V}$-variable compression".

We analyze the quality of condensed text on LCD displays, generated with unhinted and hinted bilevel characters, with traditional anti-aliased and with perceptually-tuned grayscale characters. Hinted bi-level characters and perceptually-tuned grayscale characters improve the quality of displayed small size characters (8pt, 6pt) up to a line condensation factor of 80%. At higher condensation fac...

This paper presents a method to differentiate the foreground objects from the background of a color image. Firstly a color image of any size is input for processing. The algorithm converts it to a grayscale image. Next we apply canny edge detector to find the boundary of the foreground object. We concentrate to find the maximum distance between each boundary pixel column wise and row wise and w...

A color image contains luminance and chrominance components representing the intensity and color information respectively. The objective of the work presented in this paper is to show the significance of incorporating the chrominance information for the task of scene classification. An improved color-to-grayscale image conversion algorithm by effectively incorporating the chrominance informatio...