Fruit recognition system / Nurul Husna Mohd Hofni

Recognition system becomes an important field of computer science due to rapid development of technology. Several fruit recognitions have been developed to fulfill the needs on research based on image processing. Fruits can be recognized based on their basic features such as shape, color and texture...

Full description

Saved in:

Bibliographic Details
Main Author:	Nurul Husna, Mohd Hofni
Format:	Thesis
Language:	English
Published:	2011
Subjects:	Application software Algorithms
Online Access:	https://ir.uitm.edu.my/id/eprint/34265/1/34265.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-uitm-ir.34265
record_format	uketd_dc
spelling	my-uitm-ir.342652023-10-26T00:17:35Z Fruit recognition system / Nurul Husna Mohd Hofni 2011-04-01 Nurul Husna, Mohd Hofni Application software Algorithms Algorithms Recognition system becomes an important field of computer science due to rapid development of technology. Several fruit recognitions have been developed to fulfill the needs on research based on image processing. Fruits can be recognized based on their basic features such as shape, color and texture. However, using color features and shape features analysis methods are still not robust and effective enough to identify and distinguish fruit images. A Fruit Recognition System has been proposed, which combines four features analysis methods which are edge-based, color-based, shape-based and size-based in order to increase accuracy of recognition. The objective of this project is to develop an automatic system for fruits recognition. Proposed method recognized fruit images based on obtained features. The recognition was done by calculating the properties of the shape of objects such as diameter, area, and also perimeter. Mean score from these three properties was calculated to recognize the fruits types. Then, the color of an image was extracted to find its dominant color by using RGB and HSV color space. 60 samples of fruits images from five different types of fruits were used to confirm the effectiveness of the proposed approach. Based on experimental results, approximately 96% of the fruits were recognized successfully. Future work could be directed to recognize more types of fruits images. Besides, the texture based analysis technique could be implemented with the existing four features analysis in order to obtain more accurate results for fruits recognition. This system can be applied in a variety fields such as educational, and image retrieval. 2011-04 Thesis https://ir.uitm.edu.my/id/eprint/34265/ https://ir.uitm.edu.my/id/eprint/34265/1/34265.pdf text en public degree Universiti Teknologi MARA Cawangan Perak Faculty of Computer and Mathematical Sciences Prof Madya Dr. Puteri Nor Hashimah, Megat Abdul Rahman
institution	Universiti Teknologi MARA
collection	UiTM Institutional Repository
language	English
advisor	Prof Madya Dr. Puteri Nor Hashimah, Megat Abdul Rahman
topic	Application software Algorithms Algorithms
spellingShingle	Application software Algorithms Algorithms Nurul Husna, Mohd Hofni Fruit recognition system / Nurul Husna Mohd Hofni
description	Recognition system becomes an important field of computer science due to rapid development of technology. Several fruit recognitions have been developed to fulfill the needs on research based on image processing. Fruits can be recognized based on their basic features such as shape, color and texture. However, using color features and shape features analysis methods are still not robust and effective enough to identify and distinguish fruit images. A Fruit Recognition System has been proposed, which combines four features analysis methods which are edge-based, color-based, shape-based and size-based in order to increase accuracy of recognition. The objective of this project is to develop an automatic system for fruits recognition. Proposed method recognized fruit images based on obtained features. The recognition was done by calculating the properties of the shape of objects such as diameter, area, and also perimeter. Mean score from these three properties was calculated to recognize the fruits types. Then, the color of an image was extracted to find its dominant color by using RGB and HSV color space. 60 samples of fruits images from five different types of fruits were used to confirm the effectiveness of the proposed approach. Based on experimental results, approximately 96% of the fruits were recognized successfully. Future work could be directed to recognize more types of fruits images. Besides, the texture based analysis technique could be implemented with the existing four features analysis in order to obtain more accurate results for fruits recognition. This system can be applied in a variety fields such as educational, and image retrieval.
format	Thesis
qualification_level	Bachelor degree
author	Nurul Husna, Mohd Hofni
author_facet	Nurul Husna, Mohd Hofni
author_sort	Nurul Husna, Mohd Hofni
title	Fruit recognition system / Nurul Husna Mohd Hofni
title_short	Fruit recognition system / Nurul Husna Mohd Hofni
title_full	Fruit recognition system / Nurul Husna Mohd Hofni
title_fullStr	Fruit recognition system / Nurul Husna Mohd Hofni
title_full_unstemmed	Fruit recognition system / Nurul Husna Mohd Hofni
title_sort	fruit recognition system / nurul husna mohd hofni
granting_institution	Universiti Teknologi MARA Cawangan Perak
granting_department	Faculty of Computer and Mathematical Sciences
publishDate	2011
url	https://ir.uitm.edu.my/id/eprint/34265/1/34265.pdf
_version_	1783734260852588544

Fruit recognition system / Nurul Husna Mohd Hofni

Similar Items