A novel approach of rectangular shape object detection in color images based on an MRF model

Yangxing Liu, Takeshi Ikenaga, Satoshi Goto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Rectangular shape object detection in color images is a critical step of many image recognition systems. However, there are few reports on this matter. In this paper, we proposed a hierarchical approach, which combines a global contour based line segment detection algorithm and an Markov Random Field (MRF) Model, to extract rectangular shape objects from real color images. First, we use an elaborate edge detection algorithm to obtain image edge map and accurate edge pixel gradient information (magnitude and direction). Then line segments are extracted from the edge map and some neighboring parallel segments are merged into a single line segment. Finally all segments lying on the boundary of unknown rectangular shape objects are labeled via an MRF Model built on line segments. Experimental results show that our method is robust in locating multiple rectangular shape objects simultaneously with respect to different size, orientation and color.

Original languageEnglish
Title of host publicationProceedings of the 5th IEEE International Conference on Cognitive Informatics, ICCI 2006
Pages386-393
Number of pages8
Volume1
DOIs
Publication statusPublished - 2006
Event5th IEEE International Conference on Cognitive Informatics, ICCI 2006 - Beijing
Duration: 2006 Jul 172006 Jul 19

Other

Other5th IEEE International Conference on Cognitive Informatics, ICCI 2006
CityBeijing
Period06/7/1706/7/19

Fingerprint

Color
Image recognition
Edge detection
Pixels
Object detection

ASJC Scopus subject areas

  • Artificial Intelligence
  • Information Systems

Cite this

Liu, Y., Ikenaga, T., & Goto, S. (2006). A novel approach of rectangular shape object detection in color images based on an MRF model. In Proceedings of the 5th IEEE International Conference on Cognitive Informatics, ICCI 2006 (Vol. 1, pp. 386-393). [4216438] https://doi.org/10.1109/COGINF.2006.365521

A novel approach of rectangular shape object detection in color images based on an MRF model. / Liu, Yangxing; Ikenaga, Takeshi; Goto, Satoshi.

Proceedings of the 5th IEEE International Conference on Cognitive Informatics, ICCI 2006. Vol. 1 2006. p. 386-393 4216438.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Liu, Y, Ikenaga, T & Goto, S 2006, A novel approach of rectangular shape object detection in color images based on an MRF model. in Proceedings of the 5th IEEE International Conference on Cognitive Informatics, ICCI 2006. vol. 1, 4216438, pp. 386-393, 5th IEEE International Conference on Cognitive Informatics, ICCI 2006, Beijing, 06/7/17. https://doi.org/10.1109/COGINF.2006.365521
Liu Y, Ikenaga T, Goto S. A novel approach of rectangular shape object detection in color images based on an MRF model. In Proceedings of the 5th IEEE International Conference on Cognitive Informatics, ICCI 2006. Vol. 1. 2006. p. 386-393. 4216438 https://doi.org/10.1109/COGINF.2006.365521
Liu, Yangxing ; Ikenaga, Takeshi ; Goto, Satoshi. / A novel approach of rectangular shape object detection in color images based on an MRF model. Proceedings of the 5th IEEE International Conference on Cognitive Informatics, ICCI 2006. Vol. 1 2006. pp. 386-393
@inproceedings{9fe103298e444322958ed99e880d2ad0,
title = "A novel approach of rectangular shape object detection in color images based on an MRF model",
abstract = "Rectangular shape object detection in color images is a critical step of many image recognition systems. However, there are few reports on this matter. In this paper, we proposed a hierarchical approach, which combines a global contour based line segment detection algorithm and an Markov Random Field (MRF) Model, to extract rectangular shape objects from real color images. First, we use an elaborate edge detection algorithm to obtain image edge map and accurate edge pixel gradient information (magnitude and direction). Then line segments are extracted from the edge map and some neighboring parallel segments are merged into a single line segment. Finally all segments lying on the boundary of unknown rectangular shape objects are labeled via an MRF Model built on line segments. Experimental results show that our method is robust in locating multiple rectangular shape objects simultaneously with respect to different size, orientation and color.",
author = "Yangxing Liu and Takeshi Ikenaga and Satoshi Goto",
year = "2006",
doi = "10.1109/COGINF.2006.365521",
language = "English",
volume = "1",
pages = "386--393",
booktitle = "Proceedings of the 5th IEEE International Conference on Cognitive Informatics, ICCI 2006",

}

TY - GEN

T1 - A novel approach of rectangular shape object detection in color images based on an MRF model

AU - Liu, Yangxing

AU - Ikenaga, Takeshi

AU - Goto, Satoshi

PY - 2006

Y1 - 2006

N2 - Rectangular shape object detection in color images is a critical step of many image recognition systems. However, there are few reports on this matter. In this paper, we proposed a hierarchical approach, which combines a global contour based line segment detection algorithm and an Markov Random Field (MRF) Model, to extract rectangular shape objects from real color images. First, we use an elaborate edge detection algorithm to obtain image edge map and accurate edge pixel gradient information (magnitude and direction). Then line segments are extracted from the edge map and some neighboring parallel segments are merged into a single line segment. Finally all segments lying on the boundary of unknown rectangular shape objects are labeled via an MRF Model built on line segments. Experimental results show that our method is robust in locating multiple rectangular shape objects simultaneously with respect to different size, orientation and color.

AB - Rectangular shape object detection in color images is a critical step of many image recognition systems. However, there are few reports on this matter. In this paper, we proposed a hierarchical approach, which combines a global contour based line segment detection algorithm and an Markov Random Field (MRF) Model, to extract rectangular shape objects from real color images. First, we use an elaborate edge detection algorithm to obtain image edge map and accurate edge pixel gradient information (magnitude and direction). Then line segments are extracted from the edge map and some neighboring parallel segments are merged into a single line segment. Finally all segments lying on the boundary of unknown rectangular shape objects are labeled via an MRF Model built on line segments. Experimental results show that our method is robust in locating multiple rectangular shape objects simultaneously with respect to different size, orientation and color.

UR - http://www.scopus.com/inward/record.url?scp=78650067830&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650067830&partnerID=8YFLogxK

U2 - 10.1109/COGINF.2006.365521

DO - 10.1109/COGINF.2006.365521

M3 - Conference contribution

AN - SCOPUS:78650067830

VL - 1

SP - 386

EP - 393

BT - Proceedings of the 5th IEEE International Conference on Cognitive Informatics, ICCI 2006

ER -