Log in
Language:

MERAL Myanmar Education Research and Learning Portal

  • Top
  • Universities
  • Ranking


Index Link

Index Tree

  • RootNode

Please input email address.

WEKO

One fine body…

WEKO

One fine body…

Item

{"_buckets": {"deposit": "a9b8b914-cf94-4c2b-a528-330c451113bf"}, "_deposit": {"created_by": 30, "id": "5288", "owner": "30", "owners": [30], "owners_ext": {"displayname": "", "username": ""}, "pid": {"revision_id": 0, "type": "recid", "value": "5288"}, "status": "published"}, "_oai": {"id": "oai:meral.edu.mm:recid/5288", "sets": ["1596119372420", "user-ytu"]}, "communities": ["ytu"], "item_1583103067471": {"attribute_name": "Title", "attribute_value_mlt": [{"subitem_1551255647225": "Sign Language Recognition for Myanmar Number Using Three Different SVM", "subitem_1551255648112": "en"}]}, "item_1583103085720": {"attribute_name": "Description", "attribute_value_mlt": [{"interim": "People who are affected by hearing problems use a communication method called Sign Language. Sign Language differs from region to region, country to country and continent to continent. Machine learning can play a significant role in impacting lives of the hearing-impaired people and can help them to communicate with their environments more easily. This paper presents a very simple and efficient approach for Myanmar Sign Language (MSL) recognition system which is capable of recognizing the static hand gesture images that represent the Myanmar numbers from zero to ten. The main objective of this paper is to investigate the performance of three different Support Vector Machine (SVM) classifiers for Myanmar number sign recognition. The proposed system contains three stages, namely, pre-processing, feature extraction and classification. In the feature extraction stage, different features are extracted using Scale Invariant Feature Transform (SIFT) algorithm. In the classification stage, three different SVM classifiers (SVCs); SVC with linear kernel, SVC with polynomial kernel and LinearSVC are tested and evaluated. Among these three classifiers, SVC with polynomial kernel yielded the highest accuracy score with 87%. Although there are some limitations in the datasets, each classifier provides the encouraging results."}]}, "item_1583103108160": {"attribute_name": "Keywords", "attribute_value_mlt": [{"interim": "Myanmar Sign Language"}, {"interim": "SIFT"}, {"interim": "SVM"}, {"interim": "Myanmar number sign"}]}, "item_1583103120197": {"attribute_name": "Files", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_access", "date": [{"dateType": "Available", "dateValue": "2020-09-08"}], "displaytype": "preview", "download_preview_message": "", "file_order": 0, "filename": "Sign Language Recognition for Myanmar Number.pdf", "filesize": [{"value": "230 Kb"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_0", "mimetype": "application/pdf", "size": 230000.0, "url": {"url": "https://meral.edu.mm/record/5288/files/Sign Language Recognition for Myanmar Number.pdf"}, "version_id": "d02907c1-a1ed-4fe3-9778-a34e9fa35430"}]}, "item_1583103147082": {"attribute_name": "Conference papers", "attribute_value_mlt": [{"subitem_acronym": "NCSE", "subitem_c_date": "2019-06-27", "subitem_conference_title": "12th National Conference on Science and Engineering", "subitem_place": "Yangon Technological University"}]}, "item_1583105942107": {"attribute_name": "Authors", "attribute_value_mlt": [{"subitem_authors": [{"subitem_authors_fullname": "Ni Htwe Aung"}, {"subitem_authors_fullname": "Su Su Maung"}, {"subitem_authors_fullname": "Ye Kyaw Thu"}]}]}, "item_1583108359239": {"attribute_name": "Upload type", "attribute_value_mlt": [{"interim": "Publication"}]}, "item_1583108428133": {"attribute_name": "Publication type", "attribute_value_mlt": [{"interim": "Conference paper"}]}, "item_1583159729339": {"attribute_name": "Publication date", "attribute_value": "2019-06-27"}, "item_title": "Sign Language Recognition for Myanmar Number Using Three Different SVM", "item_type_id": "21", "owner": "30", "path": ["1596119372420"], "permalink_uri": "http://hdl.handle.net/20.500.12678/0000005288", "pubdate": {"attribute_name": "Deposited date", "attribute_value": "2020-09-08"}, "publish_date": "2020-09-08", "publish_status": "0", "recid": "5288", "relation": {}, "relation_version_is_last": true, "title": ["Sign Language Recognition for Myanmar Number Using Three Different SVM"], "weko_shared_id": -1}
  1. Yangon Technological University
  2. Department of Computer Engineering and Information Technology

Sign Language Recognition for Myanmar Number Using Three Different SVM

http://hdl.handle.net/20.500.12678/0000005288
http://hdl.handle.net/20.500.12678/0000005288
27f3a367-51da-484f-8d4c-01421e4638cd
a9b8b914-cf94-4c2b-a528-330c451113bf
None
Preview
Name / File License Actions
Sign Sign Language Recognition for Myanmar Number.pdf (230 Kb)
license.icon
Publication type
Conference paper
Upload type
Publication
Title
Title Sign Language Recognition for Myanmar Number Using Three Different SVM
Language en
Publication date 2019-06-27
Authors
Ni Htwe Aung
Su Su Maung
Ye Kyaw Thu
Description
People who are affected by hearing problems use a communication method called Sign Language. Sign Language differs from region to region, country to country and continent to continent. Machine learning can play a significant role in impacting lives of the hearing-impaired people and can help them to communicate with their environments more easily. This paper presents a very simple and efficient approach for Myanmar Sign Language (MSL) recognition system which is capable of recognizing the static hand gesture images that represent the Myanmar numbers from zero to ten. The main objective of this paper is to investigate the performance of three different Support Vector Machine (SVM) classifiers for Myanmar number sign recognition. The proposed system contains three stages, namely, pre-processing, feature extraction and classification. In the feature extraction stage, different features are extracted using Scale Invariant Feature Transform (SIFT) algorithm. In the classification stage, three different SVM classifiers (SVCs); SVC with linear kernel, SVC with polynomial kernel and LinearSVC are tested and evaluated. Among these three classifiers, SVC with polynomial kernel yielded the highest accuracy score with 87%. Although there are some limitations in the datasets, each classifier provides the encouraging results.
Keywords
Myanmar Sign Language, SIFT, SVM, Myanmar number sign
Conference papers
NCSE
2019-06-27
12th National Conference on Science and Engineering
Yangon Technological University
Back
0
0
views
downloads
See details
Views Downloads

Versions

Ver.2 2020-09-08 09:12:54.539006
Ver.1 2020-09-08 09:12:51.452980
Show All versions

Share

Mendeley Twitter Facebook Print Addthis

Export

OAI-PMH
  • OAI-PMH DublinCore
Other Formats
  • JSON

Confirm


Back to MERAL


Back to MERAL