Fish classification based on robust features extraction from color signature using back-propagation classifier

Mutasem Khalil Alsmadi, Khairuddin Omar, Shahrul Azman Mohd Noah

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

Problem statement: Image recognition was a challenging problem researchers had been research into this area for so long especially in the recent years, due to distortion, noise, segmentation errors, overlap and occlusion of objects in digital images. In our study, there are many fields concern with pattern recognition, for example, fingerprint verification, face recognition, iris discrimination, chromosome shape discrimination, optical character recognition, texture discrimination and speech recognition, the subject of pattern recognition appears. A system for recognizing isolated pattern of interest may be as an approach for dealing with such application. Scientists and engineers with interests in image processing and pattern recognition have developed various approaches to deal with digital image recognition problems such as, neural network, contour matching and statistics. Approach: In this study, our aim was to recognize an isolated pattern of interest (fish) in the image based robust features extraction. Where depend on color signatures that are extracted by RGB color space, color histogram and gray level co-occurrence matrix. Results: We presented a system prototype for dealing with such problem. The system started by acquiring an image containing pattern of fish, then the image segmentation was performed relying on color signature. Our system has been applied on 20 different fish families, each family has a different number of fish types and our sample consists of distinct 610 of fish images. These images are divided into two datasets: 400 training images and 210 testing images. An overall accuracy was obtained using back-propagation classifier was 84% on the test dataset used. Conclusion: We developed a classifier for fish images recognition. We efficiently have chosen an image segmentation method to fit our demands. Our classifier successfully design and implement a decision which performed efficiently without any problems. Eventually, the classifier was able to categorize the given fish into its cluster and categorize the clustered fish into its poison or non-poison fish and categorizes the poison and non-poison fish into its family.

Original languageEnglish
Pages (from-to)52-58
Number of pages7
JournalJournal of Computer Science
Volume7
Issue number1
DOIs
Publication statusPublished - 2011

Fingerprint

Backpropagation
Fish
Feature extraction
Classifiers
Color
Image recognition
Pattern recognition
Image segmentation
Optical character recognition
Chromosomes
Face recognition
Speech recognition
Image processing
Textures
Statistics
Neural networks
Engineers
Testing

Keywords

  • Back-propagation classifier (BPC)
  • Color histogram
  • Color signature
  • Digital image recognition
  • Grey level co-occurrence matrix (GLCM)
  • Image analysis
  • Image segmentation
  • Neural network
  • Poison and non-poison fish
  • RGB color space

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this

@article{166590cf6e284dc49d270b1bba20dbdd,
title = "Fish classification based on robust features extraction from color signature using back-propagation classifier",
abstract = "Problem statement: Image recognition was a challenging problem researchers had been research into this area for so long especially in the recent years, due to distortion, noise, segmentation errors, overlap and occlusion of objects in digital images. In our study, there are many fields concern with pattern recognition, for example, fingerprint verification, face recognition, iris discrimination, chromosome shape discrimination, optical character recognition, texture discrimination and speech recognition, the subject of pattern recognition appears. A system for recognizing isolated pattern of interest may be as an approach for dealing with such application. Scientists and engineers with interests in image processing and pattern recognition have developed various approaches to deal with digital image recognition problems such as, neural network, contour matching and statistics. Approach: In this study, our aim was to recognize an isolated pattern of interest (fish) in the image based robust features extraction. Where depend on color signatures that are extracted by RGB color space, color histogram and gray level co-occurrence matrix. Results: We presented a system prototype for dealing with such problem. The system started by acquiring an image containing pattern of fish, then the image segmentation was performed relying on color signature. Our system has been applied on 20 different fish families, each family has a different number of fish types and our sample consists of distinct 610 of fish images. These images are divided into two datasets: 400 training images and 210 testing images. An overall accuracy was obtained using back-propagation classifier was 84{\%} on the test dataset used. Conclusion: We developed a classifier for fish images recognition. We efficiently have chosen an image segmentation method to fit our demands. Our classifier successfully design and implement a decision which performed efficiently without any problems. Eventually, the classifier was able to categorize the given fish into its cluster and categorize the clustered fish into its poison or non-poison fish and categorizes the poison and non-poison fish into its family.",
keywords = "Back-propagation classifier (BPC), Color histogram, Color signature, Digital image recognition, Grey level co-occurrence matrix (GLCM), Image analysis, Image segmentation, Neural network, Poison and non-poison fish, RGB color space",
author = "Alsmadi, {Mutasem Khalil} and Khairuddin Omar and {Mohd Noah}, {Shahrul Azman}",
year = "2011",
doi = "10.3844/jcssp.2011.52.58",
language = "English",
volume = "7",
pages = "52--58",
journal = "Journal of Computer Science",
issn = "1549-3636",
publisher = "Science Publications",
number = "1",

}

TY - JOUR

T1 - Fish classification based on robust features extraction from color signature using back-propagation classifier

AU - Alsmadi, Mutasem Khalil

AU - Omar, Khairuddin

AU - Mohd Noah, Shahrul Azman

PY - 2011

Y1 - 2011

N2 - Problem statement: Image recognition was a challenging problem researchers had been research into this area for so long especially in the recent years, due to distortion, noise, segmentation errors, overlap and occlusion of objects in digital images. In our study, there are many fields concern with pattern recognition, for example, fingerprint verification, face recognition, iris discrimination, chromosome shape discrimination, optical character recognition, texture discrimination and speech recognition, the subject of pattern recognition appears. A system for recognizing isolated pattern of interest may be as an approach for dealing with such application. Scientists and engineers with interests in image processing and pattern recognition have developed various approaches to deal with digital image recognition problems such as, neural network, contour matching and statistics. Approach: In this study, our aim was to recognize an isolated pattern of interest (fish) in the image based robust features extraction. Where depend on color signatures that are extracted by RGB color space, color histogram and gray level co-occurrence matrix. Results: We presented a system prototype for dealing with such problem. The system started by acquiring an image containing pattern of fish, then the image segmentation was performed relying on color signature. Our system has been applied on 20 different fish families, each family has a different number of fish types and our sample consists of distinct 610 of fish images. These images are divided into two datasets: 400 training images and 210 testing images. An overall accuracy was obtained using back-propagation classifier was 84% on the test dataset used. Conclusion: We developed a classifier for fish images recognition. We efficiently have chosen an image segmentation method to fit our demands. Our classifier successfully design and implement a decision which performed efficiently without any problems. Eventually, the classifier was able to categorize the given fish into its cluster and categorize the clustered fish into its poison or non-poison fish and categorizes the poison and non-poison fish into its family.

AB - Problem statement: Image recognition was a challenging problem researchers had been research into this area for so long especially in the recent years, due to distortion, noise, segmentation errors, overlap and occlusion of objects in digital images. In our study, there are many fields concern with pattern recognition, for example, fingerprint verification, face recognition, iris discrimination, chromosome shape discrimination, optical character recognition, texture discrimination and speech recognition, the subject of pattern recognition appears. A system for recognizing isolated pattern of interest may be as an approach for dealing with such application. Scientists and engineers with interests in image processing and pattern recognition have developed various approaches to deal with digital image recognition problems such as, neural network, contour matching and statistics. Approach: In this study, our aim was to recognize an isolated pattern of interest (fish) in the image based robust features extraction. Where depend on color signatures that are extracted by RGB color space, color histogram and gray level co-occurrence matrix. Results: We presented a system prototype for dealing with such problem. The system started by acquiring an image containing pattern of fish, then the image segmentation was performed relying on color signature. Our system has been applied on 20 different fish families, each family has a different number of fish types and our sample consists of distinct 610 of fish images. These images are divided into two datasets: 400 training images and 210 testing images. An overall accuracy was obtained using back-propagation classifier was 84% on the test dataset used. Conclusion: We developed a classifier for fish images recognition. We efficiently have chosen an image segmentation method to fit our demands. Our classifier successfully design and implement a decision which performed efficiently without any problems. Eventually, the classifier was able to categorize the given fish into its cluster and categorize the clustered fish into its poison or non-poison fish and categorizes the poison and non-poison fish into its family.

KW - Back-propagation classifier (BPC)

KW - Color histogram

KW - Color signature

KW - Digital image recognition

KW - Grey level co-occurrence matrix (GLCM)

KW - Image analysis

KW - Image segmentation

KW - Neural network

KW - Poison and non-poison fish

KW - RGB color space

UR - http://www.scopus.com/inward/record.url?scp=79251591042&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79251591042&partnerID=8YFLogxK

U2 - 10.3844/jcssp.2011.52.58

DO - 10.3844/jcssp.2011.52.58

M3 - Article

AN - SCOPUS:79251591042

VL - 7

SP - 52

EP - 58

JO - Journal of Computer Science

JF - Journal of Computer Science

SN - 1549-3636

IS - 1

ER -