Development of a rapid and accurate system to differentiate Malaysian honey samples using UV and color image
Malaysia is a country rich with natural forest resources such as spices, herbs and honey. Honey and honey-based products in Malaysia is gaining popularity as a result to the healthy lifestyle promotions by various groups including the government. This leads to the business opportunities to provide h...
Saved in:
Format: | Thesis |
---|---|
Language: | English |
Subjects: | |
Online Access: | http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/77903/1/Page%201-24.pdf http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/77903/2/Full%20text.pdf http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/77903/4/Abdul%20Alazeez.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my-unimap-77903 |
---|---|
record_format |
uketd_dc |
spelling |
my-unimap-779032023-02-21T07:42:58Z Development of a rapid and accurate system to differentiate Malaysian honey samples using UV and color image Abdul Hamid, Adom, Prof. Dr. Malaysia is a country rich with natural forest resources such as spices, herbs and honey. Honey and honey-based products in Malaysia is gaining popularity as a result to the healthy lifestyle promotions by various groups including the government. This leads to the business opportunities to provide honey and its derivatives into the market. However, this also creates another problem in determining the quality, and types of honey offered by the market. This is because different honey types, for example, have different properties, which may be desirable for different purposes, and market segments. At the moment, the methods in determining the botanical origins of honey are all laboratory-based, which may be tedious, not portable, involve chemical synthesis, time consuming and required expert personal. This research introduces a more efficient approach using UV for honey classification. This research work also shows that a low-cost approach using RGB digital camera, can also be used for the same purpose. In addition to that, the work introduces the idea of fusion using the two approaches and shows an improvement in classification. The work presented the classification of the honey based on two characteristics from three (3) types of local honey, namely the antioxidant contents and colour variations. The former uses the UV spectroscopy of selected wavelength range, and the latter using RGB digital camera. Principal Component Analysis (PCA) was used for both methods to reduce the dimension of extracted data. Support Vector Machine (SVM) was used for the classification of honey. The assessment was done separately for each of the methods, and also on the fusion of both data after features extraction. The overall classification of the fusion method improved significantly compared to single modality. Honey classification based on the fusion method was able to achieve 94% accuracy. Hence, the proposed methods have the ability to provide accurate and rapid classification of honey products in terms of its origin. The proposed system can be applied to the Malaysian honey industry and further improve the quality assessment and provide tracebility. Universiti Malaysia Perlis (UniMAP) Thesis en http://dspace.unimap.edu.my:80/xmlui/handle/123456789/77903 http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/77903/3/license.txt 8a4605be74aa9ea9d79846c1fba20a33 http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/77903/1/Page%201-24.pdf f63ae1b9d751c9d76c3e5761bc008ce0 http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/77903/2/Full%20text.pdf ecbbe2f43f0dfed4df42b312ba9267a8 http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/77903/4/Abdul%20Alazeez.pdf df90281eff1a9839dc8c7d58892b0080 Universiti Malaysia Perlis (UniMAP) Honey Multisensor data fusion Honey origins Support Vector Machine (SVM) School of Mechatronic Engineering |
institution |
Universiti Malaysia Perlis |
collection |
UniMAP Institutional Repository |
language |
English |
advisor |
Abdul Hamid, Adom, Prof. Dr. |
topic |
Honey Multisensor data fusion Honey origins Support Vector Machine (SVM) |
spellingShingle |
Honey Multisensor data fusion Honey origins Support Vector Machine (SVM) Development of a rapid and accurate system to differentiate Malaysian honey samples using UV and color image |
description |
Malaysia is a country rich with natural forest resources such as spices, herbs and honey. Honey and honey-based products in Malaysia is gaining popularity as a result to the healthy lifestyle promotions by various groups including the government. This leads to the business opportunities to provide honey and its derivatives into the market. However, this also creates another problem in determining the quality, and types of honey offered by the market. This is because different honey types, for example, have different properties, which may be desirable for different purposes, and market segments. At the moment, the methods in determining the botanical origins of honey are all laboratory-based, which may be tedious, not portable, involve chemical
synthesis, time consuming and required expert personal. This research introduces a more efficient approach using UV for honey classification. This research work also shows that a low-cost approach using RGB digital camera, can also be used for the
same purpose. In addition to that, the work introduces the idea of fusion using the two approaches and shows an improvement in classification. The work presented the classification of the honey based on two characteristics from three (3) types of local
honey, namely the antioxidant contents and colour variations. The former uses the UV spectroscopy of selected wavelength range, and the latter using RGB digital camera. Principal Component Analysis (PCA) was used for both methods to reduce the
dimension of extracted data. Support Vector Machine (SVM) was used for the classification of honey. The assessment was done separately for each of the methods, and also on the fusion of both data after features extraction. The overall classification of
the fusion method improved significantly compared to single modality. Honey classification based on the fusion method was able to achieve 94% accuracy. Hence, the proposed methods have the ability to provide accurate and rapid classification of
honey products in terms of its origin. The proposed system can be applied to the Malaysian honey industry and further improve the quality assessment and provide tracebility. |
format |
Thesis |
title |
Development of a rapid and accurate system to differentiate Malaysian honey samples using UV and color image |
title_short |
Development of a rapid and accurate system to differentiate Malaysian honey samples using UV and color image |
title_full |
Development of a rapid and accurate system to differentiate Malaysian honey samples using UV and color image |
title_fullStr |
Development of a rapid and accurate system to differentiate Malaysian honey samples using UV and color image |
title_full_unstemmed |
Development of a rapid and accurate system to differentiate Malaysian honey samples using UV and color image |
title_sort |
development of a rapid and accurate system to differentiate malaysian honey samples using uv and color image |
granting_institution |
Universiti Malaysia Perlis (UniMAP) |
granting_department |
School of Mechatronic Engineering |
url |
http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/77903/1/Page%201-24.pdf http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/77903/2/Full%20text.pdf http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/77903/4/Abdul%20Alazeez.pdf |
_version_ |
1776104253581950976 |