Classification of fish images based on shape characteristic

This research work has been conducted to analyze and classify the types of fish image based on shape characteristic. The features of characteristic of fish image are extracted by using three Moment Invariants (MI) techniques and Fourier descriptors (FD). The types of Moment invariants are Geometr...

Full description

Saved in:

Bibliographic Details
Main Author:	Mohd Wafi, Nasrudin
Format:	Thesis
Language:	English
Subjects:	Image analysis Moment Invariants (MI) Fourier descriptors (FD) Extraction Fish image classification
Online Access:	http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/61988/1/Page%201-24.pdf http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/61988/2/Full%20text.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-unimap-61988
record_format	uketd_dc
spelling	my-unimap-619882019-09-25T04:15:49Z Classification of fish images based on shape characteristic Mohd Wafi, Nasrudin Dr. Shahrul Nizam Yaakob This research work has been conducted to analyze and classify the types of fish image based on shape characteristic. The features of characteristic of fish image are extracted by using three Moment Invariants (MI) techniques and Fourier descriptors (FD). The types of Moment invariants are Geometric moment invariant (GMI), United moment invariant (UMI), Zernike moment invariant (ZMI). In the FD’s technique, there are two edge detection have been used to create the boundary of the image, namely Robert cross detection and Sobel cross detection. These feature extraction techniques have been used to analyze the image due to its invariant features of an image based on translation, scaling factor and rotation. There are two ways to examine the performance of feature extraction techniques, namely intra-class analysis and classification analysis. For the intra-class analysis, a set of equations has been implemented to find the best technique among the three different types of moments and Fourier descriptors based on the low value of Total Percentage Min Absolute Error (TPMAE). Meanwhile, for the classification analysis, the Artificial Neural Network (ANN) is explored and adapted to classify the fish images. The feature vectors produce by feature extraction techniques that represent the image are used as the input of classification. The results of the intraclass analysis indicate that the UMI was the best technique among the moment techniques while Fourier descriptor by using the Sobel edge detection shows the lower TPMAE as compared to Robert edge detection. For the classification part, two types of ANN’s which are Multilayer Perceptron (MLP) and Simplified Fuzzy ARTMAP (SFAM) neural networks have been used to classify the image based on fish category. The Leverberg-Marquardt (LM) algorithm is used to train the MLP network in order to check the applicability. Based on the classification that has been computed, the results show that all networks perform good classification performance with overall accuracy is around 90%. However, the MLP trained by Leverberg-Marquardt shows the highest classification performance in classifying the fish images as compared to the SFAM network. Universiti Malaysia Perlis (UniMAP) 2015 Thesis en http://dspace.unimap.edu.my:80/xmlui/handle/123456789/61988 http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/61988/1/Page%201-24.pdf 2c006e22b68e4bbd8b0de6d438797c3b http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/61988/2/Full%20text.pdf 2350ab1ab9dbe2b77f853d56e0371ec7 http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/61988/3/license.txt 8a4605be74aa9ea9d79846c1fba20a33 Image analysis Moment Invariants (MI) Fourier descriptors (FD) Extraction Fish image classification School of Computer and Communication Engineering
institution	Universiti Malaysia Perlis
collection	UniMAP Institutional Repository
language	English
advisor	Dr. Shahrul Nizam Yaakob
topic	Image analysis Moment Invariants (MI) Fourier descriptors (FD) Extraction Fish image classification
spellingShingle	Image analysis Moment Invariants (MI) Fourier descriptors (FD) Extraction Fish image classification Mohd Wafi, Nasrudin Classification of fish images based on shape characteristic
description	This research work has been conducted to analyze and classify the types of fish image based on shape characteristic. The features of characteristic of fish image are extracted by using three Moment Invariants (MI) techniques and Fourier descriptors (FD). The types of Moment invariants are Geometric moment invariant (GMI), United moment invariant (UMI), Zernike moment invariant (ZMI). In the FD’s technique, there are two edge detection have been used to create the boundary of the image, namely Robert cross detection and Sobel cross detection. These feature extraction techniques have been used to analyze the image due to its invariant features of an image based on translation, scaling factor and rotation. There are two ways to examine the performance of feature extraction techniques, namely intra-class analysis and classification analysis. For the intra-class analysis, a set of equations has been implemented to find the best technique among the three different types of moments and Fourier descriptors based on the low value of Total Percentage Min Absolute Error (TPMAE). Meanwhile, for the classification analysis, the Artificial Neural Network (ANN) is explored and adapted to classify the fish images. The feature vectors produce by feature extraction techniques that represent the image are used as the input of classification. The results of the intraclass analysis indicate that the UMI was the best technique among the moment techniques while Fourier descriptor by using the Sobel edge detection shows the lower TPMAE as compared to Robert edge detection. For the classification part, two types of ANN’s which are Multilayer Perceptron (MLP) and Simplified Fuzzy ARTMAP (SFAM) neural networks have been used to classify the image based on fish category. The Leverberg-Marquardt (LM) algorithm is used to train the MLP network in order to check the applicability. Based on the classification that has been computed, the results show that all networks perform good classification performance with overall accuracy is around 90%. However, the MLP trained by Leverberg-Marquardt shows the highest classification performance in classifying the fish images as compared to the SFAM network.
format	Thesis
author	Mohd Wafi, Nasrudin
author_facet	Mohd Wafi, Nasrudin
author_sort	Mohd Wafi, Nasrudin
title	Classification of fish images based on shape characteristic
title_short	Classification of fish images based on shape characteristic
title_full	Classification of fish images based on shape characteristic
title_fullStr	Classification of fish images based on shape characteristic
title_full_unstemmed	Classification of fish images based on shape characteristic
title_sort	classification of fish images based on shape characteristic
granting_institution	Universiti Malaysia Perlis (UniMAP)
granting_department	School of Computer and Communication Engineering
url	http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/61988/1/Page%201-24.pdf http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/61988/2/Full%20text.pdf
_version_	1747836852008648704

Classification of fish images based on shape characteristic

Similar Items