Saumik Bhattacharya

Learn More
The main objective of this paper is to propose a method for localized image enhancement. This method can be highly beneficial in medical purposes, like Laminography, or in enhancing images captured under non-uniform illumination. Along with a depth map, a spatial queue-based data structure is used to properly locate the area to be enhanced in the captured(More)
Video decomposition into visually similar part and feature part has gained considerable importance due to its applications in different fields of video processing. Some of the diverse problems that can be handled using this decomposition technique are- background estimation, motion saliency detection, single object tracking, multiple object tracking,(More)
Kinect is an easy and convenient means to calculate the depth of a scene in real time. It is used widely in several applications for its ease of installation and handling. Many of these applications need a high accuracy depth map of the scene for rendering. Unfortunately, the depth map provided by Kinect suffers from various degradations due to occlusion,(More)
In vision based applications, depth plays a crucial role from different aspects. From 3D rendering to automation, precision in depth measurement is important for acceptable performances. Though several techniques have been proposed to capture depth map of a scene, the estimation is either erroneous or much expensive for regular usage. Thus, the demand for(More)
Estimation of salient regions in an input video is an active area of research due to its wide applications. In this paper, we propose a novel algorithm to estimate the eye gaze movement in a video using motion, color and structural cues with minimum outliers. The algorithm is generalized to capture salient information for the videos taken under different(More)
Scene flicker is a common artifact in old archival films. This arises mainly due to aging and causes significant degradation in the perceptual quality of a video. As most of the restoration techniques use temporal information, removal of other artifacts, like blotch, scratch, tearing etc., is highly depended on the consistency of illumination in a video(More)
Images captured in presence of fog, haze or snow usually suffer from poor contrast and visibility. In this paper we propose a novel dehazing method to increase visibility from a single view without using any prior knowledge about the outdoor scene. The proposed method estimates a visibility map of the scene from the input image and uses stochastic iterative(More)
With the increasing demand of visual media, video summarization is getting more and more importance in professional content browsing, sorting and selection. It is gaining importance in surveillance to preserve storage space and to reduce user interference in analysing huge video data. Unfortunately, most of the summarization algorithms pick the frames with(More)
Steganography is a popular field in communication engineering because of its wide range of applications. It deals with hiding data inside a digital image, video or audio file without creating any detectable changes, which makes the detection of the embedded information difficult. Based on the cover that is used to hide the data, steganography can be(More)