Learn More
We present a new example-based method to colorize a gray image. As input, the user needs only to supply a reference color image which is semantically similar to the target image. We extract features from these images at the resolution of superpixels, and exploit these features to guide the colorization process. Our use of a superpixel representation speeds(More)
In this paper, we present a new image matting algorithm that achieves state-of-the-art performance on a benchmark dataset of images. This is achieved by solving two major problems encountered by current sampling based algorithms. The first is that the range in which the foreground and background are sampled is often limited to such an extent that the true(More)
We formulate the problem of salient object detection in images as an automatic labeling problem on the vertices of a weighted graph. The seed (labeled) nodes are first detected using Markov random walks performed on two different graphs that represent the image. While the global properties of the image are computed from the random walk on a complete graph,(More)
Detection of salient regions in images is useful for object based image retrieval and browsing applications. This task can be done using methods based on the human visual attention model [1], where feature maps corresponding to color, intensity and orientation capture the corresponding salient regions. In this paper, we propose a strategy for combining the(More)
Color information is leveraged by color sampling-based matting methods to find the best known samples for foreground and background color of unknown pixels. Such methods do not perform well if there is an overlap in the color distribution of foreground and background regions because color cannot distinguish between these regions and hence, the selected(More)
In this paper, we present a new classification scheme based on Support Vector Machines (SVM) and a new texture feature, called texture correlogram, for high−level image classification. Originally, SVM classifier is designed for solving only binary classification problem. In order to deal with multiple classes, we present a new method to dynamically build up(More)
This paper presents a novel technique to simultaneously estimate the depth map and the focused image of a scene, both at a super-resolution, from its defocused observations. Super-resolution refers to the generation of high spatial resolution images from a sequence of low resolution images. Hitherto, the super-resolution technique has been restricted mostly(More)
This paper presents a new technique for generating a high resolution image from a blurred image sequence; this is also referred to as super-resolution restoration of images. The image sequence consists of decimated, blurred and noisy versions of the high resolution image. The high resolution image is modeled as a Markov random field (MRF) and a maximum a(More)
Matting is a useful tool for image and video editing where foreground objects need to be extracted and pasted onto a different background. A matte is represented by α which defines the opacity of a pixel and is a value in [0, 1], with 0 for background (B) pixels and 1 for foreground (F) pixels. There are three main approaches for image matting: In(More)