A hybrid memetic algorithm with back-propagation classifier for fish classification based on robust features extraction from PLGF and shape measurements

M. Alsmadi, Khairuddin Omar, Shahrul Azman Mohd Noah, I. Almarashdeh

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

The aim of this study is a novel hybrid approach for optimizing the performance of back-propagation classifier (BPC) by utilizing the ability of Memetic algorithm (genetic algorithm and great deluge algorithm) to optimize the parameters (weight) of the PBC for fish classification problem. To recognize an isolated pattern of fish in the image based on the combination between robust features extraction which extracted based on Potential Local Geometric Features (PLGF) and shape measurements, which are extracted by measuring the edge detection method, distance and angle measurements. Typical the BPC has such disadvantage as slow practice speed and easy for running into local minimum. We presented a system prototype for dealing with such problem. The process started by acquiring an image-containing pattern of fish, then the image features extraction is performed relying on PLGF and shape measurements. The hybrid Memetic Algorithm (genetic algorithm and great deluge algorithm) with BPC (HGAGD-BPC) has outperformed BPC method and previous methodologies by obtaining better quality results but with a high cost of computational time compared to the BPC method. Where the overall accuracy obtained using the traditional BPC was 86%, while the overall accuracy obtained by the HGAGD-BPC was 96% on the test dataset used. We developed a classifier for fish images classification. Eventually, the classifier is able to classify the given fish into poison and non-poison fish and classify the poison and non-poison fish into its family.

Original languageEnglish
Pages (from-to)944-954
Number of pages11
JournalInformation Technology Journal
Volume10
Issue number5
DOIs
Publication statusPublished - 2011

Fingerprint

Backpropagation
Fish
Feature extraction
Classifiers
Genetic algorithms
Distance measurement
Image classification
Edge detection
Angle measurement

Keywords

  • Back-propagation classifier
  • Digital fish images
  • Edge detection method
  • Feature extraction
  • Memetic algorithm
  • Poison and non-poison fish
  • Potential local geometric feature

ASJC Scopus subject areas

  • Computer Science (miscellaneous)

Cite this

@article{7d3c08edacfc4feebe6aec5520fa49ca,
title = "A hybrid memetic algorithm with back-propagation classifier for fish classification based on robust features extraction from PLGF and shape measurements",
abstract = "The aim of this study is a novel hybrid approach for optimizing the performance of back-propagation classifier (BPC) by utilizing the ability of Memetic algorithm (genetic algorithm and great deluge algorithm) to optimize the parameters (weight) of the PBC for fish classification problem. To recognize an isolated pattern of fish in the image based on the combination between robust features extraction which extracted based on Potential Local Geometric Features (PLGF) and shape measurements, which are extracted by measuring the edge detection method, distance and angle measurements. Typical the BPC has such disadvantage as slow practice speed and easy for running into local minimum. We presented a system prototype for dealing with such problem. The process started by acquiring an image-containing pattern of fish, then the image features extraction is performed relying on PLGF and shape measurements. The hybrid Memetic Algorithm (genetic algorithm and great deluge algorithm) with BPC (HGAGD-BPC) has outperformed BPC method and previous methodologies by obtaining better quality results but with a high cost of computational time compared to the BPC method. Where the overall accuracy obtained using the traditional BPC was 86{\%}, while the overall accuracy obtained by the HGAGD-BPC was 96{\%} on the test dataset used. We developed a classifier for fish images classification. Eventually, the classifier is able to classify the given fish into poison and non-poison fish and classify the poison and non-poison fish into its family.",
keywords = "Back-propagation classifier, Digital fish images, Edge detection method, Feature extraction, Memetic algorithm, Poison and non-poison fish, Potential local geometric feature",
author = "M. Alsmadi and Khairuddin Omar and {Mohd Noah}, {Shahrul Azman} and I. Almarashdeh",
year = "2011",
doi = "10.3923/itj.2011.944.954",
language = "English",
volume = "10",
pages = "944--954",
journal = "Information Technology Journal",
issn = "1812-5638",
publisher = "Asian Network for Scientific Information",
number = "5",

}

TY - JOUR

T1 - A hybrid memetic algorithm with back-propagation classifier for fish classification based on robust features extraction from PLGF and shape measurements

AU - Alsmadi, M.

AU - Omar, Khairuddin

AU - Mohd Noah, Shahrul Azman

AU - Almarashdeh, I.

PY - 2011

Y1 - 2011

N2 - The aim of this study is a novel hybrid approach for optimizing the performance of back-propagation classifier (BPC) by utilizing the ability of Memetic algorithm (genetic algorithm and great deluge algorithm) to optimize the parameters (weight) of the PBC for fish classification problem. To recognize an isolated pattern of fish in the image based on the combination between robust features extraction which extracted based on Potential Local Geometric Features (PLGF) and shape measurements, which are extracted by measuring the edge detection method, distance and angle measurements. Typical the BPC has such disadvantage as slow practice speed and easy for running into local minimum. We presented a system prototype for dealing with such problem. The process started by acquiring an image-containing pattern of fish, then the image features extraction is performed relying on PLGF and shape measurements. The hybrid Memetic Algorithm (genetic algorithm and great deluge algorithm) with BPC (HGAGD-BPC) has outperformed BPC method and previous methodologies by obtaining better quality results but with a high cost of computational time compared to the BPC method. Where the overall accuracy obtained using the traditional BPC was 86%, while the overall accuracy obtained by the HGAGD-BPC was 96% on the test dataset used. We developed a classifier for fish images classification. Eventually, the classifier is able to classify the given fish into poison and non-poison fish and classify the poison and non-poison fish into its family.

AB - The aim of this study is a novel hybrid approach for optimizing the performance of back-propagation classifier (BPC) by utilizing the ability of Memetic algorithm (genetic algorithm and great deluge algorithm) to optimize the parameters (weight) of the PBC for fish classification problem. To recognize an isolated pattern of fish in the image based on the combination between robust features extraction which extracted based on Potential Local Geometric Features (PLGF) and shape measurements, which are extracted by measuring the edge detection method, distance and angle measurements. Typical the BPC has such disadvantage as slow practice speed and easy for running into local minimum. We presented a system prototype for dealing with such problem. The process started by acquiring an image-containing pattern of fish, then the image features extraction is performed relying on PLGF and shape measurements. The hybrid Memetic Algorithm (genetic algorithm and great deluge algorithm) with BPC (HGAGD-BPC) has outperformed BPC method and previous methodologies by obtaining better quality results but with a high cost of computational time compared to the BPC method. Where the overall accuracy obtained using the traditional BPC was 86%, while the overall accuracy obtained by the HGAGD-BPC was 96% on the test dataset used. We developed a classifier for fish images classification. Eventually, the classifier is able to classify the given fish into poison and non-poison fish and classify the poison and non-poison fish into its family.

KW - Back-propagation classifier

KW - Digital fish images

KW - Edge detection method

KW - Feature extraction

KW - Memetic algorithm

KW - Poison and non-poison fish

KW - Potential local geometric feature

UR - http://www.scopus.com/inward/record.url?scp=79955887235&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79955887235&partnerID=8YFLogxK

U2 - 10.3923/itj.2011.944.954

DO - 10.3923/itj.2011.944.954

M3 - Article

AN - SCOPUS:79955887235

VL - 10

SP - 944

EP - 954

JO - Information Technology Journal

JF - Information Technology Journal

SN - 1812-5638

IS - 5

ER -