An accurate and low complexity approach of detecting circular shape objects in still color images

Yangxing Liu, Satoshi Goto, Takeshi Ikenaga

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

2 Citations (Scopus)

Abstract

Object detection is a critical step of many image recognition systems. In this paper, we discussed the circular shape object detection problem in still color images. The proposed method has an important feature of integrating color image edge extraction result with a novel circle parameter determination algorithm efficiently. First, an accurate isotropic edge detector is introduced to extract color image edge and calculate precise gradient direction of each potential edge pixel, which assures the high accuracy of subsequent circle detection. Then the detected potential edge results are verified by integrating them with spatial information and the result of region based analysis. Second we utilize just only one 2-dimensional accumulator array and one 1-dimensional accumulator array, which greatly reduce storage requirement and time complexity, to detect circles of any radius. Furthermore, the validity of detected potential circle centers is checked to avoid detecting false circles. Experimental results show that our method is robust and effective in locating objects with complete or incomplete or concentric circle boundary in real color images without any prior knowledge.

Original languageEnglish
Title of host publicationProceedings - International Conference on Image Processing, ICIP
Pages333-336
Number of pages4
Volume1
DOIs
Publication statusPublished - 2005
EventIEEE International Conference on Image Processing 2005, ICIP 2005 - Genova
Duration: 2005 Sep 112005 Sep 14

Other

OtherIEEE International Conference on Image Processing 2005, ICIP 2005
CityGenova
Period05/9/1105/9/14

Fingerprint

Color
Image recognition
Pixels
Detectors
Object detection

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Liu, Y., Goto, S., & Ikenaga, T. (2005). An accurate and low complexity approach of detecting circular shape objects in still color images. In Proceedings - International Conference on Image Processing, ICIP (Vol. 1, pp. 333-336). [1529755] https://doi.org/10.1109/ICIP.2005.1529755

An accurate and low complexity approach of detecting circular shape objects in still color images. / Liu, Yangxing; Goto, Satoshi; Ikenaga, Takeshi.

Proceedings - International Conference on Image Processing, ICIP. Vol. 1 2005. p. 333-336 1529755.

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

Liu, Y, Goto, S & Ikenaga, T 2005, An accurate and low complexity approach of detecting circular shape objects in still color images. in Proceedings - International Conference on Image Processing, ICIP. vol. 1, 1529755, pp. 333-336, IEEE International Conference on Image Processing 2005, ICIP 2005, Genova, 05/9/11. https://doi.org/10.1109/ICIP.2005.1529755
Liu Y, Goto S, Ikenaga T. An accurate and low complexity approach of detecting circular shape objects in still color images. In Proceedings - International Conference on Image Processing, ICIP. Vol. 1. 2005. p. 333-336. 1529755 https://doi.org/10.1109/ICIP.2005.1529755
Liu, Yangxing ; Goto, Satoshi ; Ikenaga, Takeshi. / An accurate and low complexity approach of detecting circular shape objects in still color images. Proceedings - International Conference on Image Processing, ICIP. Vol. 1 2005. pp. 333-336
@inproceedings{00d85124a7084a5883ea7376184d1217,
title = "An accurate and low complexity approach of detecting circular shape objects in still color images",
abstract = "Object detection is a critical step of many image recognition systems. In this paper, we discussed the circular shape object detection problem in still color images. The proposed method has an important feature of integrating color image edge extraction result with a novel circle parameter determination algorithm efficiently. First, an accurate isotropic edge detector is introduced to extract color image edge and calculate precise gradient direction of each potential edge pixel, which assures the high accuracy of subsequent circle detection. Then the detected potential edge results are verified by integrating them with spatial information and the result of region based analysis. Second we utilize just only one 2-dimensional accumulator array and one 1-dimensional accumulator array, which greatly reduce storage requirement and time complexity, to detect circles of any radius. Furthermore, the validity of detected potential circle centers is checked to avoid detecting false circles. Experimental results show that our method is robust and effective in locating objects with complete or incomplete or concentric circle boundary in real color images without any prior knowledge.",
author = "Yangxing Liu and Satoshi Goto and Takeshi Ikenaga",
year = "2005",
doi = "10.1109/ICIP.2005.1529755",
language = "English",
isbn = "0780391349",
volume = "1",
pages = "333--336",
booktitle = "Proceedings - International Conference on Image Processing, ICIP",

}

TY - GEN

T1 - An accurate and low complexity approach of detecting circular shape objects in still color images

AU - Liu, Yangxing

AU - Goto, Satoshi

AU - Ikenaga, Takeshi

PY - 2005

Y1 - 2005

N2 - Object detection is a critical step of many image recognition systems. In this paper, we discussed the circular shape object detection problem in still color images. The proposed method has an important feature of integrating color image edge extraction result with a novel circle parameter determination algorithm efficiently. First, an accurate isotropic edge detector is introduced to extract color image edge and calculate precise gradient direction of each potential edge pixel, which assures the high accuracy of subsequent circle detection. Then the detected potential edge results are verified by integrating them with spatial information and the result of region based analysis. Second we utilize just only one 2-dimensional accumulator array and one 1-dimensional accumulator array, which greatly reduce storage requirement and time complexity, to detect circles of any radius. Furthermore, the validity of detected potential circle centers is checked to avoid detecting false circles. Experimental results show that our method is robust and effective in locating objects with complete or incomplete or concentric circle boundary in real color images without any prior knowledge.

AB - Object detection is a critical step of many image recognition systems. In this paper, we discussed the circular shape object detection problem in still color images. The proposed method has an important feature of integrating color image edge extraction result with a novel circle parameter determination algorithm efficiently. First, an accurate isotropic edge detector is introduced to extract color image edge and calculate precise gradient direction of each potential edge pixel, which assures the high accuracy of subsequent circle detection. Then the detected potential edge results are verified by integrating them with spatial information and the result of region based analysis. Second we utilize just only one 2-dimensional accumulator array and one 1-dimensional accumulator array, which greatly reduce storage requirement and time complexity, to detect circles of any radius. Furthermore, the validity of detected potential circle centers is checked to avoid detecting false circles. Experimental results show that our method is robust and effective in locating objects with complete or incomplete or concentric circle boundary in real color images without any prior knowledge.

UR - http://www.scopus.com/inward/record.url?scp=33749646520&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33749646520&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2005.1529755

DO - 10.1109/ICIP.2005.1529755

M3 - Conference contribution

SN - 0780391349

SN - 9780780391345

VL - 1

SP - 333

EP - 336

BT - Proceedings - International Conference on Image Processing, ICIP

ER -