2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.

2003

Go

Filter Results

Displaying Results 1 - 25 of 97
  • Object segmentation using graph cuts based active contours

    Publication Year: 2003, Page(s):II - 46-53 vol.2
    Cited by:  Papers (7)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (14119 KB) | HTML iconHTML

    In this paper we present a graph cuts based active contours (GCBAC) approach to object segmentation problems. Our method is a combination of active contours and the optimization tool of graph cuts and differs fundamentally from traditional active contours in that it uses graph cuts to iteratively deform the contour. Consequently, it has the following advantages. (1) It has the ability to jump over... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Object-specific figure-ground segregation

    Publication Year: 2003, Page(s):II - 39-45 vol.2
    Cited by:  Papers (31)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (924 KB) | HTML iconHTML

    We consider the problem of segmenting an image into foreground and background, with foreground containing solely objects of interest known a priori. We propose an integration model that incorporates both edge detection and object part detection results. It consists of two parallel processes: low-level pixel grouping and high-level patch grouping. We seek a solution that optimizes a joint grouping ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Proceedings 2003 IEEE Computer Society Conference On Computer Vision And Pattern Recognition

    Publication Year: 2003, Page(s):iii - xii
    Request permission for commercial reuse | PDF file iconPDF (327 KB)
    Freely Available from IEEE
  • Multi-modal image registration by minimizing Kullback-Leibler distance between expected and observed joint class histograms

    Publication Year: 2003, Page(s):II - 570
    Cited by:  Papers (2)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (732 KB) | HTML iconHTML

    We present a new multimodal image registration method based on the a priori knowledge of the class label mappings between two segmented input images. A joint class histogram between the image pairs is estimated by assigning each bin value equal to the total number of occurrences of the corresponding class label pairs. The discrepancy between the observed and expected joint class histograms should ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Author index

    Publication Year: 2003, Page(s):737 - 742
    Request permission for commercial reuse | PDF file iconPDF (170 KB)
    Freely Available from IEEE
  • Texture classification: are filter banks necessary?

    Publication Year: 2003, Page(s):II - 691-8 vol.2
    Cited by:  Papers (146)  |  Patents (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (374 KB) | HTML iconHTML

    We question the role that large scale filter banks have traditionally played in texture classification. It is demonstrated that textures can be classified using the joint distribution of intensity values over extremely compact neighborhoods (starting from as small as 3 × 3 pixels square), and that this outperforms classification using filter banks with large support. We develop a novel texto... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Advanced Gaussian MRF rotation-invariant texture features for classification of remote sensing imagery

    Publication Year: 2003, Page(s):II - 685-90 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (428 KB) | HTML iconHTML

    The features based on Markov random field (MRF) models are usually sensitive to the rotation of image textures. The paper develops an anisotropic circular Gaussian MRF (ACGMRF) model for modeling rotated image textures and retrieving rotation-invariant texture features. To overcome the singularity problem of the least squares estimate (LSE) method, an approximate least squares estimate (ALSE) meth... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Enhancing DPF for near-replica image recognition

    Publication Year: 2003, Page(s):II - 416-23 vol.2
    Cited by:  Papers (7)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4037 KB) | HTML iconHTML

    Dynamic Partial Function (DPF), which dynamically selects a subset of features to measure pairwise image similarity, has been shown to be very effective in near-replica image recognition. DPF, however, suffers from the one-size-fits-all problem: it requires that all pairwise similarity measurements must use the same number of features. We propose methods for enhancing DPF's performance by allowing... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computing layered surface representations: an algorithm for detecting and separating transparent overlays

    Publication Year: 2003, Page(s):II - 11-18 vol.2
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1095 KB) | HTML iconHTML

    The biological visual system possesses the ability to compute layered surface representations, in which one surface is represented as being viewed through another. This ability is remarkable because, in scenes involving transparency, the link between surface topology and image topology is greatly complicated by the collapse of the photometric contributions of two distinct surfaces onto image inten... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Range image segmentation by surface extraction using an improved robust estimator

    Publication Year: 2003, Page(s):II - 33-8 vol.2
    Cited by:  Papers (13)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (422 KB) | HTML iconHTML

    The paper presents a novel range image segmentation algorithm based on planar surface extraction. The algorithm was applied to common range image databases and was favorably compared against seven other segmentation algorithms using a popular evaluation framework. The experimental results show that, as compared to the other methods, our algorithm presents a good performance in preserving small reg... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An efficient solution to the five-point relative pose problem

    Publication Year: 2003, Page(s):II - 195-202 vol.2
    Cited by:  Papers (84)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (660 KB) | HTML iconHTML

    An efficient algorithmic solution to the classical five-point relative pose problem is presented. The problem is to find the possible solutions for relative camera motion between two calibrated views given five corresponding points. The algorithm consists of computing the coefficients of a tenth degree polynomial and subsequently finding its roots. It is the first algorithm well suited for numeric... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Establishment shot detection using qualitative motion

    Publication Year: 2003, Page(s):II-85 - II-90 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (865 KB) | HTML iconHTML

    In this paper, we developed a technique to detect a special kind of shot, namely establishment shot, which is used to introduce a new scene to the audience or remind the audience of a known environment. The detection of establishment shot aids in various middle-level issues such as analyzing the story units of a movie. An establishment shot is usually realized by using camera motions such as panni... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • General c-means clustering model and its application

    Publication Year: 2003, Page(s):II-122 - II-127 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (391 KB) | HTML iconHTML

    Many partitional clustering algorithms originated from the definition of mean.We propose a new clustering model - general c-means clustering algorithm (GCM). Generally, when the data set is clustered into c (c > 1) subsets, each subset is often expected to have a different prototype (or cluster center) than others. Therefore, we propose the definition of undesirable solution of clustering algorith... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Visual hull alignment and refinement across time: a 3D reconstruction algorithm combining shape-from-silhouette with stereo

    Publication Year: 2003, Page(s):II - 375-82 vol.2
    Cited by:  Papers (38)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (862 KB) | HTML iconHTML

    Visual hull (VH) construction from silhouette images is a popular method of shape estimation. The method, also known as shape-from-silhouette (SFS), is used in many applications such as non-invasive 3D model acquisition, obstacle avoidance, and more recently human motion tracking and analysis. One of the limitations of SFS, however, is that the approximated shape can be very coarse when there are ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The effects of segmentation and feature choice in a translation model of object recognition

    Publication Year: 2003, Page(s):II - 675-82 vol.2
    Cited by:  Papers (20)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (399 KB) | HTML iconHTML

    We work with a model of object recognition where words must be placed on image regions. This approach means that large scale experiments are relatively easy, so we can evaluate the effects of various early and midlevel vision algorithms on recognition performance. We evaluate various image segmentation algorithms by determining word prediction accuracy for images segmented in various ways and repr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Object removal by exemplar-based inpainting

    Publication Year: 2003, Page(s):II-721 - II-728 vol.2
    Cited by:  Papers (225)  |  Patents (40)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (888 KB) | HTML iconHTML

    A new algorithm is proposed for removing large objects from digital images. The challenge is to fill in the hole that is left behind in a visually plausible way. In the past, this problem has been addressed by two classes of algorithms: (i) "texture synthesis" algorithms for generating large image regions from sample textures, and (ii) "inpainting" techniques for filling in small image gaps. The f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning object intrinsic structure for robust visual tracking

    Publication Year: 2003, Page(s):II-227 - II-233 vol.2
    Cited by:  Papers (28)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (409 KB) | HTML iconHTML

    In this paper, a novel method to learn the intrinsic object structure for robust visual tracking is proposed. The basic assumption is that the parameterized object state lies on a low dimensional manifold and can be learned from training data. Based on this assumption, firstly we derived the dimensionality reduction and density estimation algorithm for unsupervised learning of object intrinsic rep... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analyzing appearance and contour based methods for object categorization

    Publication Year: 2003, Page(s):II - 409-15 vol.2
    Cited by:  Papers (254)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1303 KB) | HTML iconHTML

    Object recognition has reached a level where we can identify a large number of previously seen and known objects. However, the more challenging and important task of categorizing previously unseen objects remains largely unsolved. Traditionally, contour and shape based methods are regarded most adequate for handling the generalization requirements needed for this task. Appearance based methods, on... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic relighting of overlapping textures of a 3D model

    Publication Year: 2003, Page(s):II - 166-73 vol.2
    Cited by:  Papers (13)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (483 KB) | HTML iconHTML

    The paper presents a new method to correct overlapping textures of a single 3D model where each texture was obtained under possibly different lighting conditions and color response of the camera. This situation arises frequently when a single object is digitized using multiple 3D scanners. Our goal is to remove any visible seam and improve color consistency between the textures in order to merge t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust crease detection in fingerprint images

    Publication Year: 2003, Page(s):II - 505-10 vol.2
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1991 KB) | HTML iconHTML

    We study a pattern in the fingerprint called a crease, a kind of stripe which irregularly crosses the normal fingerprint patterns (ridges and valleys). Creases will cause spurious minutiae when using a conventional feature detection algorithm, and therefore decreases the recognition rate of fingerprint identification. By representing the crease using a parameterized rectangle, we design an optimal... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Video segmentation based on graphical models

    Publication Year: 2003, Page(s):II - 335-42 vol.2
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (911 KB) | HTML iconHTML

    This paper proposes a unified framework for spatiotemporal segmentation of video sequences. A Bayesian network is presented to model the interactions among the motion vector field, the intensity segmentation field, and the video segmentation field. The notions of distance transformation and Markov random field are used to express spatiotemporal constraints. Given consecutive frames, an optimizatio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Nearest neighbor search for relevance feedback

    Publication Year: 2003, Page(s):II - 643-8 vol.2
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (356 KB) | HTML iconHTML

    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 to support high-level concept queries. The paper addresses those scenarios in which a similarity or distance matrix is updated during each iter... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Background subtraction based on cooccurrence of image variations

    Publication Year: 2003, Page(s):II-65 - II-72 vol.2
    Cited by:  Papers (73)  |  Patents (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (654 KB) | HTML iconHTML

    This paper presents a novel background subtraction method for detecting foreground objects in dynamic scenes involving swaying trees and fluttering flags. Most methods proposed so far adjust the permissible range of the background image variations according to the training samples of background images. Thus, the detection sensitivity decreases at those pixels having wide permissible ranges. If we ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Qualitative image based localization in indoors environments

    Publication Year: 2003, Page(s):II-3 - II-8 vol.2
    Cited by:  Papers (42)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (325 KB) | HTML iconHTML

    Man made indoor environments possess regularities, which can be efficiently exploited in automated model acquisition by means of visual sensing. In this context we propose an approach for inferring a topological model of an environment from images or the video stream captured by a mobile robot during exploration. The proposed model consists of a set of locations and neighborhood relationships betw... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Perception-based 3D triangle mesh segmentation using fast marching watersheds

    Publication Year: 2003, Page(s):II-27 - II-32 vol.2
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (475 KB) | HTML iconHTML

    In this paper, we describe an algorithm called fast marching watersheds that segments a triangle mesh into visual parts. This computer vision algorithm leverages a human vision theory known as the minima rule. Our implementation computes the principal curvatures and principal directions at each vertex of a mesh, and then our hill-climbing watershed algorithm identifies regions bounded by contours ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.