Thresholds decision method for fast object detection systems

Hideaki Sato, Yasue Mitsukura, Minoru Fukumi, Norio Akamatsu

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

2 Citations (Scopus)

Abstract

In this paper, we propose a new determination method of color thresholds for extracting objects. In order to obtain the optimal color threshold, it is necessary to determine RGB values all together because one color consists of a combination of RGB values. The two optimal thresholds, an upper and a lower, are determined for object extraction by applying genetic algorithm. Moreover, in the proposed method, individuals are evaluated using two fitness functions for obtaining the optimal color thresholds, and initial population is generated with color histograms for fast convergence. Finally, computer simulations are performed, and the result images are shown.

Original languageEnglish
Title of host publicationProceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1075-1080
Number of pages6
Volume3
ISBN (Print)0780378660
DOIs
Publication statusPublished - 2003
Externally publishedYes
Event2003 IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 2003 - Kobe, Japan
Duration: 2003 Jul 162003 Jul 20

Other

Other2003 IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 2003
CountryJapan
CityKobe
Period03/7/1603/7/20

Fingerprint

Object Detection
Color
Color Histogram
Fitness Function
Computer Simulation
Genetic Algorithm
Genetic algorithms
Necessary
Object detection
Computer simulation
Object

Keywords

  • fitness function
  • genetic algorithm
  • image processing
  • object extraction
  • threshold

ASJC Scopus subject areas

  • Computational Mathematics

Cite this

Sato, H., Mitsukura, Y., Fukumi, M., & Akamatsu, N. (2003). Thresholds decision method for fast object detection systems. In Proceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA (Vol. 3, pp. 1075-1080). [1222146] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CIRA.2003.1222146

Thresholds decision method for fast object detection systems. / Sato, Hideaki; Mitsukura, Yasue; Fukumi, Minoru; Akamatsu, Norio.

Proceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA. Vol. 3 Institute of Electrical and Electronics Engineers Inc., 2003. p. 1075-1080 1222146.

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

Sato, H, Mitsukura, Y, Fukumi, M & Akamatsu, N 2003, Thresholds decision method for fast object detection systems. in Proceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA. vol. 3, 1222146, Institute of Electrical and Electronics Engineers Inc., pp. 1075-1080, 2003 IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 2003, Kobe, Japan, 03/7/16. https://doi.org/10.1109/CIRA.2003.1222146
Sato H, Mitsukura Y, Fukumi M, Akamatsu N. Thresholds decision method for fast object detection systems. In Proceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA. Vol. 3. Institute of Electrical and Electronics Engineers Inc. 2003. p. 1075-1080. 1222146 https://doi.org/10.1109/CIRA.2003.1222146
Sato, Hideaki ; Mitsukura, Yasue ; Fukumi, Minoru ; Akamatsu, Norio. / Thresholds decision method for fast object detection systems. Proceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA. Vol. 3 Institute of Electrical and Electronics Engineers Inc., 2003. pp. 1075-1080
@inproceedings{b7e96c3f0357432b8a695383bdb00c81,
title = "Thresholds decision method for fast object detection systems",
abstract = "In this paper, we propose a new determination method of color thresholds for extracting objects. In order to obtain the optimal color threshold, it is necessary to determine RGB values all together because one color consists of a combination of RGB values. The two optimal thresholds, an upper and a lower, are determined for object extraction by applying genetic algorithm. Moreover, in the proposed method, individuals are evaluated using two fitness functions for obtaining the optimal color thresholds, and initial population is generated with color histograms for fast convergence. Finally, computer simulations are performed, and the result images are shown.",
keywords = "fitness function, genetic algorithm, image processing, object extraction, threshold",
author = "Hideaki Sato and Yasue Mitsukura and Minoru Fukumi and Norio Akamatsu",
year = "2003",
doi = "10.1109/CIRA.2003.1222146",
language = "English",
isbn = "0780378660",
volume = "3",
pages = "1075--1080",
booktitle = "Proceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Thresholds decision method for fast object detection systems

AU - Sato, Hideaki

AU - Mitsukura, Yasue

AU - Fukumi, Minoru

AU - Akamatsu, Norio

PY - 2003

Y1 - 2003

N2 - In this paper, we propose a new determination method of color thresholds for extracting objects. In order to obtain the optimal color threshold, it is necessary to determine RGB values all together because one color consists of a combination of RGB values. The two optimal thresholds, an upper and a lower, are determined for object extraction by applying genetic algorithm. Moreover, in the proposed method, individuals are evaluated using two fitness functions for obtaining the optimal color thresholds, and initial population is generated with color histograms for fast convergence. Finally, computer simulations are performed, and the result images are shown.

AB - In this paper, we propose a new determination method of color thresholds for extracting objects. In order to obtain the optimal color threshold, it is necessary to determine RGB values all together because one color consists of a combination of RGB values. The two optimal thresholds, an upper and a lower, are determined for object extraction by applying genetic algorithm. Moreover, in the proposed method, individuals are evaluated using two fitness functions for obtaining the optimal color thresholds, and initial population is generated with color histograms for fast convergence. Finally, computer simulations are performed, and the result images are shown.

KW - fitness function

KW - genetic algorithm

KW - image processing

KW - object extraction

KW - threshold

UR - http://www.scopus.com/inward/record.url?scp=77956616425&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956616425&partnerID=8YFLogxK

U2 - 10.1109/CIRA.2003.1222146

DO - 10.1109/CIRA.2003.1222146

M3 - Conference contribution

AN - SCOPUS:77956616425

SN - 0780378660

VL - 3

SP - 1075

EP - 1080

BT - Proceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA

PB - Institute of Electrical and Electronics Engineers Inc.

ER -