A fruit recognition method via image conversion optimized through evolution strategy

Michael Vogl, Jang Yoon Kim, Shin Dug Kim

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

5 Citations (Scopus)

Abstract

This research is to propose a fast and highly accurate object recognition method especially for fruit recognition applications to be used in a mobile environment. Conventional techniques are based on one or more of the basic features that characterize an object: color, shape, texture and intensity, causing performance or accuracy limitations in a mobile environment. Thus, this paper presents a combined approach that transforms basic features into their associated code fields to generate an object code that could be used as a search key in a feature database. Parameters used in the experiment have been optimized by using Evolution Strategies and an increase in accuracy by up to 10% has been achieved. A fruit database consisting of 36 different classes of fruits and 1108 fruit images overall has been used to obtain the experimental results. The results show an average accuracy of more than 98% and performance increase compared to different approaches on fruit image recognition.

Original languageEnglish
Title of host publicationProceedings - 17th IEEE International Conference on Computational Science and Engineering, CSE 2014, Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014
EditorsXingang Liu, Didier El Baz, Ching-Hsien Hsu, Kai Kang, Weifeng Chen
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1497-1502
Number of pages6
ISBN (Electronic)9781479979813
DOIs
Publication statusPublished - 2015 Jan 26
Event17th IEEE International Conference on Computational Science and Engineering, CSE 2014 - Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014 - Chengdu, China
Duration: 2014 Dec 192014 Dec 21

Publication series

NameProceedings - 17th IEEE International Conference on Computational Science and Engineering, CSE 2014, Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014

Other

Other17th IEEE International Conference on Computational Science and Engineering, CSE 2014 - Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014
CountryChina
CityChengdu
Period14/12/1914/12/21

Fingerprint

Fruits
Image recognition
Object recognition
Textures
Color
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Industrial and Manufacturing Engineering

Cite this

Vogl, M., Kim, J. Y., & Kim, S. D. (2015). A fruit recognition method via image conversion optimized through evolution strategy. In X. Liu, D. El Baz, C-H. Hsu, K. Kang, & W. Chen (Eds.), Proceedings - 17th IEEE International Conference on Computational Science and Engineering, CSE 2014, Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014 (pp. 1497-1502). [07023789] (Proceedings - 17th IEEE International Conference on Computational Science and Engineering, CSE 2014, Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CSE.2014.278
Vogl, Michael ; Kim, Jang Yoon ; Kim, Shin Dug. / A fruit recognition method via image conversion optimized through evolution strategy. Proceedings - 17th IEEE International Conference on Computational Science and Engineering, CSE 2014, Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014. editor / Xingang Liu ; Didier El Baz ; Ching-Hsien Hsu ; Kai Kang ; Weifeng Chen. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 1497-1502 (Proceedings - 17th IEEE International Conference on Computational Science and Engineering, CSE 2014, Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014).
@inproceedings{eadf0f521f9a4bf6aa6aa33dcef507e0,
title = "A fruit recognition method via image conversion optimized through evolution strategy",
abstract = "This research is to propose a fast and highly accurate object recognition method especially for fruit recognition applications to be used in a mobile environment. Conventional techniques are based on one or more of the basic features that characterize an object: color, shape, texture and intensity, causing performance or accuracy limitations in a mobile environment. Thus, this paper presents a combined approach that transforms basic features into their associated code fields to generate an object code that could be used as a search key in a feature database. Parameters used in the experiment have been optimized by using Evolution Strategies and an increase in accuracy by up to 10{\%} has been achieved. A fruit database consisting of 36 different classes of fruits and 1108 fruit images overall has been used to obtain the experimental results. The results show an average accuracy of more than 98{\%} and performance increase compared to different approaches on fruit image recognition.",
author = "Michael Vogl and Kim, {Jang Yoon} and Kim, {Shin Dug}",
year = "2015",
month = "1",
day = "26",
doi = "10.1109/CSE.2014.278",
language = "English",
series = "Proceedings - 17th IEEE International Conference on Computational Science and Engineering, CSE 2014, Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1497--1502",
editor = "Xingang Liu and {El Baz}, Didier and Ching-Hsien Hsu and Kai Kang and Weifeng Chen",
booktitle = "Proceedings - 17th IEEE International Conference on Computational Science and Engineering, CSE 2014, Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014",
address = "United States",

}

Vogl, M, Kim, JY & Kim, SD 2015, A fruit recognition method via image conversion optimized through evolution strategy. in X Liu, D El Baz, C-H Hsu, K Kang & W Chen (eds), Proceedings - 17th IEEE International Conference on Computational Science and Engineering, CSE 2014, Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014., 07023789, Proceedings - 17th IEEE International Conference on Computational Science and Engineering, CSE 2014, Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014, Institute of Electrical and Electronics Engineers Inc., pp. 1497-1502, 17th IEEE International Conference on Computational Science and Engineering, CSE 2014 - Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014, Chengdu, China, 14/12/19. https://doi.org/10.1109/CSE.2014.278

A fruit recognition method via image conversion optimized through evolution strategy. / Vogl, Michael; Kim, Jang Yoon; Kim, Shin Dug.

Proceedings - 17th IEEE International Conference on Computational Science and Engineering, CSE 2014, Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014. ed. / Xingang Liu; Didier El Baz; Ching-Hsien Hsu; Kai Kang; Weifeng Chen. Institute of Electrical and Electronics Engineers Inc., 2015. p. 1497-1502 07023789 (Proceedings - 17th IEEE International Conference on Computational Science and Engineering, CSE 2014, Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014).

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

TY - GEN

T1 - A fruit recognition method via image conversion optimized through evolution strategy

AU - Vogl, Michael

AU - Kim, Jang Yoon

AU - Kim, Shin Dug

PY - 2015/1/26

Y1 - 2015/1/26

N2 - This research is to propose a fast and highly accurate object recognition method especially for fruit recognition applications to be used in a mobile environment. Conventional techniques are based on one or more of the basic features that characterize an object: color, shape, texture and intensity, causing performance or accuracy limitations in a mobile environment. Thus, this paper presents a combined approach that transforms basic features into their associated code fields to generate an object code that could be used as a search key in a feature database. Parameters used in the experiment have been optimized by using Evolution Strategies and an increase in accuracy by up to 10% has been achieved. A fruit database consisting of 36 different classes of fruits and 1108 fruit images overall has been used to obtain the experimental results. The results show an average accuracy of more than 98% and performance increase compared to different approaches on fruit image recognition.

AB - This research is to propose a fast and highly accurate object recognition method especially for fruit recognition applications to be used in a mobile environment. Conventional techniques are based on one or more of the basic features that characterize an object: color, shape, texture and intensity, causing performance or accuracy limitations in a mobile environment. Thus, this paper presents a combined approach that transforms basic features into their associated code fields to generate an object code that could be used as a search key in a feature database. Parameters used in the experiment have been optimized by using Evolution Strategies and an increase in accuracy by up to 10% has been achieved. A fruit database consisting of 36 different classes of fruits and 1108 fruit images overall has been used to obtain the experimental results. The results show an average accuracy of more than 98% and performance increase compared to different approaches on fruit image recognition.

UR - http://www.scopus.com/inward/record.url?scp=84925266580&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84925266580&partnerID=8YFLogxK

U2 - 10.1109/CSE.2014.278

DO - 10.1109/CSE.2014.278

M3 - Conference contribution

AN - SCOPUS:84925266580

T3 - Proceedings - 17th IEEE International Conference on Computational Science and Engineering, CSE 2014, Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014

SP - 1497

EP - 1502

BT - Proceedings - 17th IEEE International Conference on Computational Science and Engineering, CSE 2014, Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014

A2 - Liu, Xingang

A2 - El Baz, Didier

A2 - Hsu, Ching-Hsien

A2 - Kang, Kai

A2 - Chen, Weifeng

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Vogl M, Kim JY, Kim SD. A fruit recognition method via image conversion optimized through evolution strategy. In Liu X, El Baz D, Hsu C-H, Kang K, Chen W, editors, Proceedings - 17th IEEE International Conference on Computational Science and Engineering, CSE 2014, Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014. Institute of Electrical and Electronics Engineers Inc. 2015. p. 1497-1502. 07023789. (Proceedings - 17th IEEE International Conference on Computational Science and Engineering, CSE 2014, Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014). https://doi.org/10.1109/CSE.2014.278