Image Classification with Higher-Dimension Watershed Classifier: A Test to Malaysian National Land Use Classification Scheme
Recent image classification based on watershed algorithm (Watson et. al.,1992) has reported as a potential method for producing accurate method of classifying satellite images. This method, however, can only be applied to 2-D feature space and hence several independen analysis had to be combined to...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
Fakulti Ukur dan Harta Tanah
1996
|
Subjects: | |
Online Access: | http://eprints.utm.my/4890/1/Image.pdf |
_version_ | 1825909638050086912 |
---|---|
author | Hashim, Mazlan |
author_facet | Hashim, Mazlan |
author_sort | Hashim, Mazlan |
collection | ePrints |
description | Recent image classification based on watershed algorithm (Watson et. al.,1992) has reported as a potential method for producing accurate method of classifying satellite
images. This method, however, can only be applied to 2-D feature space and hence several independen analysis had to be combined to give acceptable results. In this paper, a generalizat n of the watershed algorithm to enable classification of any n-D feature space is presented and analysed. Results are presented for 3 different models of
classification: (i) maximum likelihood, (ii) combinations of 2-D watersheds, and (iii) n-D watershed, tested over a relatively heterogeneous land cover of Malaysia. It is
shown that the n-D watershed method is the most superior, although it has not reported a substantial improvement in the classification accuracy from the 2-D approach. Given the elaborate computational time taken by the n-D watershed, it is concluded that the n-D watershed is no better than the 2-D approach. |
first_indexed | 2024-03-05T18:05:09Z |
format | Article |
id | utm.eprints-4890 |
institution | Universiti Teknologi Malaysia - ePrints |
language | English |
last_indexed | 2024-03-05T18:05:09Z |
publishDate | 1996 |
publisher | Fakulti Ukur dan Harta Tanah |
record_format | dspace |
spelling | utm.eprints-48902017-09-10T04:21:05Z http://eprints.utm.my/4890/ Image Classification with Higher-Dimension Watershed Classifier: A Test to Malaysian National Land Use Classification Scheme Hashim, Mazlan TA Engineering (General). Civil engineering (General) Recent image classification based on watershed algorithm (Watson et. al.,1992) has reported as a potential method for producing accurate method of classifying satellite images. This method, however, can only be applied to 2-D feature space and hence several independen analysis had to be combined to give acceptable results. In this paper, a generalizat n of the watershed algorithm to enable classification of any n-D feature space is presented and analysed. Results are presented for 3 different models of classification: (i) maximum likelihood, (ii) combinations of 2-D watersheds, and (iii) n-D watershed, tested over a relatively heterogeneous land cover of Malaysia. It is shown that the n-D watershed method is the most superior, although it has not reported a substantial improvement in the classification accuracy from the 2-D approach. Given the elaborate computational time taken by the n-D watershed, it is concluded that the n-D watershed is no better than the 2-D approach. Fakulti Ukur dan Harta Tanah 1996 Article PeerReviewed application/pdf en http://eprints.utm.my/4890/1/Image.pdf Hashim, Mazlan (1996) Image Classification with Higher-Dimension Watershed Classifier: A Test to Malaysian National Land Use Classification Scheme. Buletin Ukur, 7 (2). pp. 141-148. ISSN 0128-4274 |
spellingShingle | TA Engineering (General). Civil engineering (General) Hashim, Mazlan Image Classification with Higher-Dimension Watershed Classifier: A Test to Malaysian National Land Use Classification Scheme |
title | Image Classification with Higher-Dimension Watershed Classifier: A Test to Malaysian National Land Use Classification Scheme |
title_full | Image Classification with Higher-Dimension Watershed Classifier: A Test to Malaysian National Land Use Classification Scheme |
title_fullStr | Image Classification with Higher-Dimension Watershed Classifier: A Test to Malaysian National Land Use Classification Scheme |
title_full_unstemmed | Image Classification with Higher-Dimension Watershed Classifier: A Test to Malaysian National Land Use Classification Scheme |
title_short | Image Classification with Higher-Dimension Watershed Classifier: A Test to Malaysian National Land Use Classification Scheme |
title_sort | image classification with higher dimension watershed classifier a test to malaysian national land use classification scheme |
topic | TA Engineering (General). Civil engineering (General) |
url | http://eprints.utm.my/4890/1/Image.pdf |
work_keys_str_mv | AT hashimmazlan imageclassificationwithhigherdimensionwatershedclassifieratesttomalaysiannationallanduseclassificationscheme |