Concurrent Object Recognition and Segmentation by Graph Partitioning

Published 1 January 2002

Stella X. Yu, Ralph Gross, Jianbo Shi

Citations81

TL;DR

It is demonstrated that the resulting object segmentation eliminates false positives for the part detection, while overcoming occlusion and weak contours for the low-level edge detection.

Abstract

Segmentation and recognition have long been treated as two separate processes. We propose a mechanism based on spectral graph partitioning that readily combine the two processes into one. A part-based recognition system detects object patches, supplies their partial segmentations and knowledge about the spatial configurations of the object. The goal of patch grouping is to find a set of patches that conform best to the object configuration. This process is integrated with the pixel grouping based on low-level feature similarity, through pixel-patch interactions and patch competition that is encoded as constraints in the solution space. The globally optimal partition is obtained by solving a constrained eigenvalue problem. We demonstrate that the resulting object segmentation eliminates local false positives at the high level of part detection, while overcoming occlusion and weak contours at the low level of edge detection.

Keywords

Computer Science

Rapid object detection using a boosted cascade of simple features

18,097 Citations2005Paul Viola, Michael Jones

A machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates and the introduction of a new image representation called the "integral image" which allows the features used by the detector to be computed very quickly.

Elsevier eBooksIntroduction to Statistical Pattern Recognition

11,121 Citations1990Keinosuke Fukunaga

A system to determine the sex of fish from their length, as accurately as possible, using a set of labelled data, together with the class label (male or female), as a training set.

International Journal of Computer VisionContour and Texture Analysis for Image Segmentation

1,091 Citations2001Jitendra Malik, Serge Belongie +2 more

This paper provides an algorithm for partitioning grayscale images into disjoint regions of coherent brightness and texture, and introduces a gating operator based on the texturedness of the neighborhood at a pixel to facilitate cue combination.

Normalized cuts and image segmentation

863 Citations2002Jianbo Shi, Jitendra Malik

This work treats image segmentation as a graph partitioning problem and proposes a novel global criterion, the normalized cut, for segmenting the graph, which measures both the total dissimilarity between the different groups as well as the total similarity within the groups.

Lecture notes in computer scienceClass-Specific, Top-Down Segmentation

370 Citations2002Eran Borenstein, Shimon Ullman

A novel class-based segmentation method, which is guided by a stored representation of the shape of objects within a general class (such as horse images), which leads to markedly improved segmentation results and can deal with significant variation in shape and varying backgrounds.

Learning image statistics for Bayesian tracking

110 Citations2002Hedvig Sidenbladh, Michael J. Black

Improved robustness and accuracy is demonstrated when tracking complex objects such as people in monocular image sequences with cluttered scene and a moving camera by combining multiple image cues and using learned likelihood models.

Neural Information Processing SystemsGrouping with Bias

73 Citations2001Stella X. Yu, Jianbo Shi

This paper considers priors from unitary generative models, partially labeled data and spatial attention, modelled as constraints in the solution space, and demonstrates that simple priors can greatly improve image segmentation results.

Lecture notes in computer scienceCombining Simple Discriminators for Object Discrimination

11 Citations2002S. Mahamud, Martial Hebert +1 more

This work reports results on a multi-class discrimination task in which significant gains in performance are seen by combining discriminators under the maximum entropy framework from a variety of easy to construct feature spaces.

View PDF