Search For:

Displaying 1-26 out of 26 total
Texture Features for Browsing and Retrieval of Image Data
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By B.s. Manjunath, W.y. Ma
Issue Date:August 1996
pp. 837-842
<p><b>Abstract</b>—Image content based retrieval is emerging as an important research area with application to digital libraries and multimedia databases. The focus of this paper is on the image processing aspects and in particular using ...
 
Unsupervised Segmentation of Color-Texture Regions in Images and Video
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yining Deng, b.s. Manjunath
Issue Date:August 2001
pp. 800-810
<p><b>Abstract</b>—A new method for unsupervised segmentation of color-texture regions in images and video is presented. This method, which we refer to as JSEG, consists of two independent steps: color quantization and spatial segmentatio...
 
Graph Partitioning Active Contours (GPAC) for Image Segmentation
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Baris Sumengen, B.S. Manjunath
Issue Date:April 2006
pp. 509-521
In this paper, we introduce new types of variational segmentation cost functions and associated active contour methods that are based on pairwise similarities or dissimilarities of the pixels. As a solution to a minimization problem, we introduce a new cur...
 
An efficient low-dimensional color indexing scheme for region-based image retrieval
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By Yining Deng, B.S. Manjunath
Issue Date:March 1999
pp. 3017-3020
In this work, an efficient low-dimensional color indexing scheme for region-based image retrieval is presented. The colors in each image region are first quantized so that only a small number of cluster centroids are needed to represent the region color in...
 
Image Processing in the Alexandria Digital Library Project
Found in: Advances in Digital Libraries Conference, IEEE
By B.S. Manjunath
Issue Date:April 1998
pp. 180
No summary available.
 
Graphical Model-Based Tracking of Curvilinear Structures in Bio-image Sequences
Found in: Pattern Recognition, International Conference on
By Pradeep Koulgi, Mehmet Emre Sargin, Kenneth Rose, B.S. Manjunath
Issue Date:August 2010
pp. 2596-2599
Tracking of curvilinear structures is a task of fundamental importance in the quantitative analysis of biological structures such as neurons, blood vessels, retinal interconnects, microtubules, etc. The state of the art HMM-based contour tracking scheme fo...
 
A Variational Framework for Multiregion Pairwise-Similarity-Based Image Segmentation
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Luca Bertelli, Baris Sumengen, B.S. Manjunath, Frédéric Gibou
Issue Date:August 2008
pp. 1400-1414
Variational cost functions that are based on pairwise similarity between pixels can be minimized within level set framework resulting in a binary image segmentation. In this paper we extend such cost functions and address multi-region image segmentation pr...
 
Color Image Segmentation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yining Deng, B.S. Manjunath, Hyundoo Shin
Issue Date:June 1999
pp. 2446
In this work, a new approach to fully automatic color image segmentation, called JSEG, is presented. First, colors in the image are quantized to several representing classes that can be used to differentiate regions in the image. Then, image pixel colors a...
 
From Where and How to What We See
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By S. Karthikeyan,Vignesh Jagadeesh,Renuka Shenoy,Miguel Ecksteinz,B.S. Manjunath
Issue Date:December 2013
pp. 625-632
Eye movement studies have confirmed that overt attention is highly biased towards faces and text regions in images. In this paper we explore a novel problem of predicting face and text regions in images using eye tracking data from multiple subjects. The p...
 
Camera Alignment Using Trajectory Intersections in Unsynchronized Videos
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Thomas Kuo,Santhoshkumar Sunderrajan,B.S. Manjunath
Issue Date:December 2013
pp. 1121-1128
This paper addresses the novel and challenging problem of aligning camera views that are unsynchronized by low and/or variable frame rates using object trajectories. Unlike existing trajectory-based alignment methods, our method does not require frame-to-f...
 
Discriminative Basis Selection Using Non-negative Matrix Factorization
Found in: Pattern Recognition, International Conference on
By Aruna Jammalamadaka, Swapna Joshi, S. Karthikeyan, B.S. Manjunath
Issue Date:August 2010
pp. 1533-1536
Non-negative matrix factorization (NMF) has proven to be useful in image classification applications such as face recognition. We propose a novel discriminative basis selection method for classification of image categories based on the popular term frequen...
 
Object Tracking with Ratio Cycles Using Shape and Appearance Cues
Found in: Pattern Recognition, International Conference on
By M.E. Sargin, P. Ghosh, B.S. Manjunath, K. Rose
Issue Date:August 2010
pp. 3649-3652
We present a method for object tracking over time sequence imagery. The image plane is represented with a 4-connected planar graph where vertices are associated with pixels. On each image, the outer contour of the object is localized by finding the optimal...
 
Particle Filter Tracking with Online Multiple Instance Learning
Found in: Pattern Recognition, International Conference on
By Zefeng Ni, Santhoshkumar Sunderrajan, Amir Rahimi, B.S. Manjunath
Issue Date:August 2010
pp. 2616-2619
This paper addresses the problem of object tracking by learning a discriminative classifier to separate the object from its background. The online-learned classifier is used to adaptively model object's appearance and its background. To solve the typical p...
 
Shape prior segmentation of multiple objects with graph cuts
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Nhat Vu, B.S. Manjunath
Issue Date:June 2008
pp. 1-8
We present a new shape prior segmentation method using graph cuts capable of segmenting multiple objects. The shape prior energy is based on a shape distance popular with level set approaches. We also present a multiphase graph cut framework to simultaneou...
 
Pairwise Similarities across Images for Multiple View Rigid/Non-Rigid Segmentation and Registration
Found in: Computer Vision, IEEE International Conference on
By Luca Bertelli, Marco Zuliani, B.S. Manjunath
Issue Date:October 2007
pp. 1-8
A variational approach for the background/foreground segmentation of multiple views of the same scene is presented. The main novelty is the introduction of cost functions based on pairwise similarity between pixels across different images. These cost funct...
 
A Condition Number for Point Matching with Application to Registration and Postregistration Error Estimation
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Charles S. Kenney, B.S. Manjunath, Marco Zuliani, Gary A. Hewer, Alan Van Nevel
Issue Date:November 2003
pp. 1437-1454
<p><b>Abstract</b>—Selecting salient points from two or more images for computing correspondence is a well-studied problem in image analysis. This paper describes a new and effective technique for selecting these tiepoints using condition...
 
Nearest Neighbor Search for Relevance Feedback
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jelena Te¡sic, B.S. Manjunath
Issue Date:June 2003
pp. 643
We introduce the problem of repetitive nearest neighbor search in relevance feedback and propose an efficient search scheme for high dimensional feature spaces. Relevance feedback learning is a popular scheme used in content based image and video retrieval...
 
Subset Selection for Active Object Recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jay Winkeler, B.S. Manjunath, S. Chandrasekaran
Issue Date:June 1999
pp. 2511
This paper presents an algorithm for constructing object representations suitable for recognition. The system automatically selects a representative subset of the views of the object while constructing the eigenspace basis. These views are actively located...
 
An eigenspace update algorithm for image analysis
Found in: Computer Vision, International Symposium on
By B.S. Manjunath, S. Chandrasekaran, Y.F. Wang
Issue Date:November 1995
pp. 551
During the past few years several interesting applications of eigenspace representation of images have been proposed. These include face recognition, video coding, pose estimation, etc. However, the vision research community has largely overlooked parallel...
 
Rotation-invariant texture classification using modified Gabor filters
Found in: Image Processing, International Conference on
By G.M. Haley, B.S. Manjunath
Issue Date:October 1995
pp. 262
A method of rotation invariant texture classification based on a joint space-frequency model is introduced. Multiresolution filters, based on a truly analytic form of a polar 2-D Gabor (1946) wavelet, are used to compute spatial frequency-specific but spat...
 
Unsupervised Texture Segmentation Using Markov Random Field Models
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By B.S. Manjunath, R. Chellappa
Issue Date:May 1991
pp. 478-482
<p>The problem of unsupervised segmentation of textured images is considered. The only explicit assumption made is that the intensity data can be modeled by a Gauss Markov random field (GMRF). The image is divided into a number of nonoverlapping regi...
 
Color image embedding using multidimensional lattice structures
Found in: Image Processing, International Conference on
By J.J. Chae, D. Mukherjee, B.S Manjunath
Issue Date:October 1998
pp. 460
This paper describes a robust data embedding scheme which uses noise resilient channel codes based on a multidimensional lattice structure. Compared to prior work in digital watermarking, the proposed scheme can handle a significantly larger quantity of si...
 
A Robust Data Hiding Technique Using Multidimensional Lattices
Found in: Advances in Digital Libraries Conference, IEEE
By J.J. Chae, D. Mukherjee, B.S. Manjunath
Issue Date:April 1998
pp. 319
No summary available.
 
Model-based detection and correction of corrupted wavelet coefficients
Found in: Image Processing, International Conference on
By N. Strobel, S.K. Mitra, B.S. Manjunath
Issue Date:October 1997
pp. 925
Image decomposition based on the discrete wavelet transform (DWT) has been proposed for efficient storage and progressive transmission of images for visual browsing in digital image libraries. Although the compression aspects of the DWT have been carefully...
 
NeTra: a toolbox for navigating large image databases
Found in: Image Processing, International Conference on
By W.Y. Ma, B.S. Manjunath
Issue Date:October 1997
pp. 568
We present an implementation of NeTra, a prototype image retrieval system that uses color texture, shape and spatial location information in segmented image database. A distinguishing aspect of this system is its incorporation of a robust automated image s...
 
A comparison of wavelet transform features for texture image annotation
Found in: Image Processing, International Conference on
By W.Y. Ma, B.S. Manjunath
Issue Date:October 1995
pp. 2256
A comparison of different wavelet transform based texture features for content based search and retrieval is made. These include the conventional orthogonal and bi-orthogonal wavelet transforms, tree-structured decompositions, and the Gabor wavelet transfo...
 
 1