Detecting mango fruits by using randomized hough transform and backpropagation neural network

Kutiba Nanaa, Mohamed Rizon, Mohd Nordin Abd Rahman, Yahaya Ibrahim, Azim Zaliha Abd Aziz

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

10 Citations (Scopus)

Abstract

A new method for mango detection is presented in this paper. This method is based on preprocessing operators on image which includes converting to gray image, finding edges, calculating distances to edges, opening morphology and converting to binary color image. To take advantage of oval shaped mango fruit, we apply Randomized Hough Transform method to detect potential places for mango fruit in input images. By using Back propagation Neural Network, we recognize mango fruits from these potential places. The dataset used to implementing this paper is 50 RGB images captured of mango fruits on trees. As shown in experimental results, in the case of clear fruit in input images, the detection rates up to 96.26% while it decreases in the case of partially covering or overlapping. However, this method can be applied to detect other fruits in varied sizes and colors.

Original languageEnglish
Title of host publicationProceedings of the International Conference on Information Visualisation
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages388-391
Number of pages4
ISBN (Print)9781479941032
DOIs
Publication statusPublished - 18 Sep 2014
Externally publishedYes
Event2014 18th International Conference on Information Visualisation: Visualisation, BioMedical Visualization, Visualisation on Built and Rural Environments and Geometric Modelling and Imaging, IV 2014 - Paris
Duration: 16 Jul 201418 Jul 2014

Other

Other2014 18th International Conference on Information Visualisation: Visualisation, BioMedical Visualization, Visualisation on Built and Rural Environments and Geometric Modelling and Imaging, IV 2014
CityParis
Period16/7/1418/7/14

Fingerprint

Hough transforms
Fruits
Backpropagation
Neural networks
Color

Keywords

  • detecting Fruits
  • Detecting Mango
  • feature extraction
  • image recognition
  • image segmentation
  • neural network
  • Randomized Hough Transform
  • watershed algorithm

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Software
  • Signal Processing

Cite this

Nanaa, K., Rizon, M., Rahman, M. N. A., Ibrahim, Y., & Aziz, A. Z. A. (2014). Detecting mango fruits by using randomized hough transform and backpropagation neural network. In Proceedings of the International Conference on Information Visualisation (pp. 388-391). [6902938] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IV.2014.54

Detecting mango fruits by using randomized hough transform and backpropagation neural network. / Nanaa, Kutiba; Rizon, Mohamed; Rahman, Mohd Nordin Abd; Ibrahim, Yahaya; Aziz, Azim Zaliha Abd.

Proceedings of the International Conference on Information Visualisation. Institute of Electrical and Electronics Engineers Inc., 2014. p. 388-391 6902938.

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

Nanaa, K, Rizon, M, Rahman, MNA, Ibrahim, Y & Aziz, AZA 2014, Detecting mango fruits by using randomized hough transform and backpropagation neural network. in Proceedings of the International Conference on Information Visualisation., 6902938, Institute of Electrical and Electronics Engineers Inc., pp. 388-391, 2014 18th International Conference on Information Visualisation: Visualisation, BioMedical Visualization, Visualisation on Built and Rural Environments and Geometric Modelling and Imaging, IV 2014, Paris, 16/7/14. https://doi.org/10.1109/IV.2014.54
Nanaa K, Rizon M, Rahman MNA, Ibrahim Y, Aziz AZA. Detecting mango fruits by using randomized hough transform and backpropagation neural network. In Proceedings of the International Conference on Information Visualisation. Institute of Electrical and Electronics Engineers Inc. 2014. p. 388-391. 6902938 https://doi.org/10.1109/IV.2014.54
Nanaa, Kutiba ; Rizon, Mohamed ; Rahman, Mohd Nordin Abd ; Ibrahim, Yahaya ; Aziz, Azim Zaliha Abd. / Detecting mango fruits by using randomized hough transform and backpropagation neural network. Proceedings of the International Conference on Information Visualisation. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 388-391
@inproceedings{0d596b71654541a795df595dcd6c83fc,
title = "Detecting mango fruits by using randomized hough transform and backpropagation neural network",
abstract = "A new method for mango detection is presented in this paper. This method is based on preprocessing operators on image which includes converting to gray image, finding edges, calculating distances to edges, opening morphology and converting to binary color image. To take advantage of oval shaped mango fruit, we apply Randomized Hough Transform method to detect potential places for mango fruit in input images. By using Back propagation Neural Network, we recognize mango fruits from these potential places. The dataset used to implementing this paper is 50 RGB images captured of mango fruits on trees. As shown in experimental results, in the case of clear fruit in input images, the detection rates up to 96.26{\%} while it decreases in the case of partially covering or overlapping. However, this method can be applied to detect other fruits in varied sizes and colors.",
keywords = "detecting Fruits, Detecting Mango, feature extraction, image recognition, image segmentation, neural network, Randomized Hough Transform, watershed algorithm",
author = "Kutiba Nanaa and Mohamed Rizon and Rahman, {Mohd Nordin Abd} and Yahaya Ibrahim and Aziz, {Azim Zaliha Abd}",
year = "2014",
month = "9",
day = "18",
doi = "10.1109/IV.2014.54",
language = "English",
isbn = "9781479941032",
pages = "388--391",
booktitle = "Proceedings of the International Conference on Information Visualisation",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Detecting mango fruits by using randomized hough transform and backpropagation neural network

AU - Nanaa, Kutiba

AU - Rizon, Mohamed

AU - Rahman, Mohd Nordin Abd

AU - Ibrahim, Yahaya

AU - Aziz, Azim Zaliha Abd

PY - 2014/9/18

Y1 - 2014/9/18

N2 - A new method for mango detection is presented in this paper. This method is based on preprocessing operators on image which includes converting to gray image, finding edges, calculating distances to edges, opening morphology and converting to binary color image. To take advantage of oval shaped mango fruit, we apply Randomized Hough Transform method to detect potential places for mango fruit in input images. By using Back propagation Neural Network, we recognize mango fruits from these potential places. The dataset used to implementing this paper is 50 RGB images captured of mango fruits on trees. As shown in experimental results, in the case of clear fruit in input images, the detection rates up to 96.26% while it decreases in the case of partially covering or overlapping. However, this method can be applied to detect other fruits in varied sizes and colors.

AB - A new method for mango detection is presented in this paper. This method is based on preprocessing operators on image which includes converting to gray image, finding edges, calculating distances to edges, opening morphology and converting to binary color image. To take advantage of oval shaped mango fruit, we apply Randomized Hough Transform method to detect potential places for mango fruit in input images. By using Back propagation Neural Network, we recognize mango fruits from these potential places. The dataset used to implementing this paper is 50 RGB images captured of mango fruits on trees. As shown in experimental results, in the case of clear fruit in input images, the detection rates up to 96.26% while it decreases in the case of partially covering or overlapping. However, this method can be applied to detect other fruits in varied sizes and colors.

KW - detecting Fruits

KW - Detecting Mango

KW - feature extraction

KW - image recognition

KW - image segmentation

KW - neural network

KW - Randomized Hough Transform

KW - watershed algorithm

UR - http://www.scopus.com/inward/record.url?scp=84912121749&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84912121749&partnerID=8YFLogxK

U2 - 10.1109/IV.2014.54

DO - 10.1109/IV.2014.54

M3 - Conference contribution

AN - SCOPUS:84912121749

SN - 9781479941032

SP - 388

EP - 391

BT - Proceedings of the International Conference on Information Visualisation

PB - Institute of Electrical and Electronics Engineers Inc.

ER -