This paper investigates two fundamental problems in computer vision: contour detection and
image segmentation. We present state-of-the-art algorithms for both of these tasks. Our …

Stereopsis provides an additional depth cue and plays an important role in the human vision
system. This paper explores stereopsis for saliency analysis and presents two approaches …

We propose a two-class classification model for grou**. Human segmented natural
images are used as positive examples. Negative examples of grou** are constructed by …

This paper provides an algorithm for partitioning grayscale images into disjoint regions of
coherent brightness and texture. Natural images contain both textured and untextured …

Visible light communications (VLC) is an emerging field of optical communications that
focuses on the part of the electromagnetic spectrum that humans can see. Much existing …

This paper presents an algorithm for Interactive Co-segmentation of a foreground object
from a group of related images. While previous approaches focus on unsupervised co …

In this paper we extend the" shape, illumination and reflectance from shading"(SIRFS)
model [3, 4], which recovers intrinsic scene properties from a single image. Though SIRFS …

Occlusion reasoning is a fundamental problem in computer vision. In this paper, we propose
an algorithm to recover the occlusion boundaries and depth ordering of free-standing …

Contours and junctions are important cues for perceptual organization and shape
recognition. Detecting junctions locally has proved problematic because the image intensity …

Background The role of a sensor element is to measure incident irradiance and record that
quantity as an image intensity value. However, physical constraints limit the maximum …