Object detection based on multiclass discriminative field

Xiaofeng Zhang; Qiaoyu Sun; Yue Lu

doi:10.1007/978-3-642-25664-6_58

Object detection based on multiclass discriminative field

Xiaofeng Zhang^*
, Qiaoyu Sun
, Yue Lu

^*Corresponding author for this work

School of Communication and Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In this paper, we present a novel object detection scheme that uses information of the sample fragments. These sample fragments are extracted by decomposition of the sample contour. Then, the candidate fragments corresponding to the sample fragments are detected from the images by partial Hausdorff distance. The Multiclass Discriminative Field (MDF) is used to select the most probable fragments from candidate fragments. The parameter estimation and inference of the MDF are simplified by using the candidate fragments as nodes of a graph. With these selected fragments, the contours of the objects can be obtained. The experiments on our postmark database and the ETHZ database show the feasibility of our proposed scheme.

Original language	English
Title of host publication	Foundations of Intelligent Systems
Subtitle of host publication	Proceedings of the Sixth International Conference on Intelligent Systems and Knowledge Engineering, Shanghai, China, Dec 2011 (ISKE2011)
Editors	Yinglin Wang, Tianrui Li
Pages	495-500
Number of pages	6
DOIs	https://doi.org/10.1007/978-3-642-25664-6_58
State	Published - 2011

Publication series

Name	Advances in Intelligent and Soft Computing
Volume	122
ISSN (Print)	1867-5662

Keywords

Hausdorff distance
Multiclass Discriminative Field
Object detection

Access to Document

10.1007/978-3-642-25664-6_58

Cite this

Zhang, X., Sun, Q., & Lu, Y. (2011). Object detection based on multiclass discriminative field. In Y. Wang, & T. Li (Eds.), Foundations of Intelligent Systems: Proceedings of the Sixth International Conference on Intelligent Systems and Knowledge Engineering, Shanghai, China, Dec 2011 (ISKE2011) (pp. 495-500). (Advances in Intelligent and Soft Computing; Vol. 122). https://doi.org/10.1007/978-3-642-25664-6_58

Zhang, Xiaofeng ; Sun, Qiaoyu ; Lu, Yue. / Object detection based on multiclass discriminative field. Foundations of Intelligent Systems: Proceedings of the Sixth International Conference on Intelligent Systems and Knowledge Engineering, Shanghai, China, Dec 2011 (ISKE2011). editor / Yinglin Wang ; Tianrui Li. 2011. pp. 495-500 (Advances in Intelligent and Soft Computing).

@inproceedings{fdd456d23a654975b77094c775ff833f,

title = "Object detection based on multiclass discriminative field",

abstract = "In this paper, we present a novel object detection scheme that uses information of the sample fragments. These sample fragments are extracted by decomposition of the sample contour. Then, the candidate fragments corresponding to the sample fragments are detected from the images by partial Hausdorff distance. The Multiclass Discriminative Field (MDF) is used to select the most probable fragments from candidate fragments. The parameter estimation and inference of the MDF are simplified by using the candidate fragments as nodes of a graph. With these selected fragments, the contours of the objects can be obtained. The experiments on our postmark database and the ETHZ database show the feasibility of our proposed scheme.",

keywords = "Hausdorff distance, Multiclass Discriminative Field, Object detection",

author = "Xiaofeng Zhang and Qiaoyu Sun and Yue Lu",

year = "2011",

doi = "10.1007/978-3-642-25664-6\_58",

language = "英语",

isbn = "9783642256639",

series = "Advances in Intelligent and Soft Computing",

pages = "495--500",

editor = "Yinglin Wang and Tianrui Li",

booktitle = "Foundations of Intelligent Systems",

}

Zhang, X, Sun, Q & Lu, Y 2011, Object detection based on multiclass discriminative field. in Y Wang & T Li (eds), Foundations of Intelligent Systems: Proceedings of the Sixth International Conference on Intelligent Systems and Knowledge Engineering, Shanghai, China, Dec 2011 (ISKE2011). Advances in Intelligent and Soft Computing, vol. 122, pp. 495-500. https://doi.org/10.1007/978-3-642-25664-6_58

Object detection based on multiclass discriminative field. / Zhang, Xiaofeng; Sun, Qiaoyu; Lu, Yue.
Foundations of Intelligent Systems: Proceedings of the Sixth International Conference on Intelligent Systems and Knowledge Engineering, Shanghai, China, Dec 2011 (ISKE2011). ed. / Yinglin Wang; Tianrui Li. 2011. p. 495-500 (Advances in Intelligent and Soft Computing; Vol. 122).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Object detection based on multiclass discriminative field

AU - Zhang, Xiaofeng

AU - Sun, Qiaoyu

AU - Lu, Yue

PY - 2011

Y1 - 2011

N2 - In this paper, we present a novel object detection scheme that uses information of the sample fragments. These sample fragments are extracted by decomposition of the sample contour. Then, the candidate fragments corresponding to the sample fragments are detected from the images by partial Hausdorff distance. The Multiclass Discriminative Field (MDF) is used to select the most probable fragments from candidate fragments. The parameter estimation and inference of the MDF are simplified by using the candidate fragments as nodes of a graph. With these selected fragments, the contours of the objects can be obtained. The experiments on our postmark database and the ETHZ database show the feasibility of our proposed scheme.

AB - In this paper, we present a novel object detection scheme that uses information of the sample fragments. These sample fragments are extracted by decomposition of the sample contour. Then, the candidate fragments corresponding to the sample fragments are detected from the images by partial Hausdorff distance. The Multiclass Discriminative Field (MDF) is used to select the most probable fragments from candidate fragments. The parameter estimation and inference of the MDF are simplified by using the candidate fragments as nodes of a graph. With these selected fragments, the contours of the objects can be obtained. The experiments on our postmark database and the ETHZ database show the feasibility of our proposed scheme.

KW - Hausdorff distance

KW - Multiclass Discriminative Field

KW - Object detection

UR - https://www.scopus.com/pages/publications/84555170672

U2 - 10.1007/978-3-642-25664-6_58

DO - 10.1007/978-3-642-25664-6_58

M3 - 会议稿件

AN - SCOPUS:84555170672

SN - 9783642256639

T3 - Advances in Intelligent and Soft Computing

SP - 495

EP - 500

BT - Foundations of Intelligent Systems

A2 - Wang, Yinglin

A2 - Li, Tianrui

ER -

Zhang X, Sun Q, Lu Y. Object detection based on multiclass discriminative field. In Wang Y, Li T, editors, Foundations of Intelligent Systems: Proceedings of the Sixth International Conference on Intelligent Systems and Knowledge Engineering, Shanghai, China, Dec 2011 (ISKE2011). 2011. p. 495-500. (Advances in Intelligent and Soft Computing). doi: 10.1007/978-3-642-25664-6_58

Object detection based on multiclass discriminative field

Abstract

Publication series

Keywords

Access to Document

Other files and links

Fingerprint

Cite this