MERAL Myanmar Education Research and Learning Portal
Item
{"_buckets": {"deposit": "41b408f1-5784-4549-ad4a-05d4dbe4990c"}, "_deposit": {"created_by": 30, "id": "5289", "owner": "30", "owners": [30], "owners_ext": {"displayname": "", "username": ""}, "pid": {"revision_id": 0, "type": "recid", "value": "5289"}, "status": "published"}, "_oai": {"id": "oai:meral.edu.mm:recid/5289", "sets": ["1596119372420", "user-ytu"]}, "communities": ["ytu"], "item_1583103067471": {"attribute_name": "Title", "attribute_value_mlt": [{"subitem_1551255647225": "Transfer Learning Based Myanmar Sign Language Recognition for Myanmar Consonants", "subitem_1551255648112": "en"}]}, "item_1583103085720": {"attribute_name": "Description", "attribute_value_mlt": [{"interim": "Abstract— In this paper, a study on the different Transfer Learning models is made for the purpose\nof recognizing Myanmar Fingerspelling (Myanmar Sign Language) alphabets. This experiment shows\nthat Transfer Learning can play a significant role for sign language recognition system and is capable of\nrecognizing the static hand gesture images that represent the Myanmar consonants from က (ka) to အ (a).\nThe main objective of this paper is to investigate the performance of various Transfer Learning models\nfor Myanmar Fingerspelling recognition. We proposed 12 Transfer Learning models using TensorFlow\nlibrary and the accuracy for each model is compared. Among these 12 models, VGG16, ResNet50\nand MobileNet with epoch 50 yielded the highest accuracy score with 94%. Although there are some\nlimitations in the datasets, each model provides the encouraging results and thus, it can believe that\nthe fully generalizable recognition system based on Transfer Learning can be produced for all Myanmar\nSign Language Fingerspelling characters by doing further research with more data."}]}, "item_1583103108160": {"attribute_name": "Keywords", "attribute_value_mlt": [{"interim": "Myanmar Sign Language"}, {"interim": "Myanmar Fingerspelling"}, {"interim": "Transfer Learning"}, {"interim": "Myanmar consonants"}]}, "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": "Transfer Learning Based Myanmar Sign Language.pdf", "filesize": [{"value": "2.9 Mb"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_0", "mimetype": "application/pdf", "size": 2900000.0, "url": {"url": "https://meral.edu.mm/record/5289/files/Transfer Learning Based Myanmar Sign Language.pdf"}, "version_id": "c03c2444-c7e2-4a4f-a623-a86c68b44c77"}]}, "item_1583103131163": {"attribute_name": "Journal articles", "attribute_value_mlt": [{"subitem_issue": "1", "subitem_journal_title": "Journal of Intelligent Informatics and Smart Technology", "subitem_pages": "pp 35-44", "subitem_volume": "4"}]}, "item_1583105942107": {"attribute_name": "Authors", "attribute_value_mlt": [{"subitem_authors": [{"subitem_authors_fullname": "Ni Htwe Aung"}, {"subitem_authors_fullname": "Ye Kyaw Thu"}, {"subitem_authors_fullname": "Su Su Maung"}, {"subitem_authors_fullname": "Swe Zin Moe"}, {"subitem_authors_fullname": "Hlaing Myat Nwe"}]}]}, "item_1583108359239": {"attribute_name": "Upload type", "attribute_value_mlt": [{"interim": "Publication"}]}, "item_1583108428133": {"attribute_name": "Publication type", "attribute_value_mlt": [{"interim": "Journal article"}]}, "item_1583159729339": {"attribute_name": "Publication date", "attribute_value": "2020-04-30"}, "item_title": "Transfer Learning Based Myanmar Sign Language Recognition for Myanmar Consonants", "item_type_id": "21", "owner": "30", "path": ["1596119372420"], "permalink_uri": "http://hdl.handle.net/20.500.12678/0000005289", "pubdate": {"attribute_name": "Deposited date", "attribute_value": "2020-09-08"}, "publish_date": "2020-09-08", "publish_status": "0", "recid": "5289", "relation": {}, "relation_version_is_last": true, "title": ["Transfer Learning Based Myanmar Sign Language Recognition for Myanmar Consonants"], "weko_shared_id": -1}
Transfer Learning Based Myanmar Sign Language Recognition for Myanmar Consonants
http://hdl.handle.net/20.500.12678/0000005289
http://hdl.handle.net/20.500.12678/0000005289b4cba743-fa4d-462c-8953-bf431fb193c0
41b408f1-5784-4549-ad4a-05d4dbe4990c
Name / File | License | Actions |
---|---|---|
Transfer Learning Based Myanmar Sign Language.pdf (2.9 Mb)
|
Publication type | ||||||
---|---|---|---|---|---|---|
Journal article | ||||||
Upload type | ||||||
Publication | ||||||
Title | ||||||
Title | Transfer Learning Based Myanmar Sign Language Recognition for Myanmar Consonants | |||||
Language | en | |||||
Publication date | 2020-04-30 | |||||
Authors | ||||||
Ni Htwe Aung | ||||||
Ye Kyaw Thu | ||||||
Su Su Maung | ||||||
Swe Zin Moe | ||||||
Hlaing Myat Nwe | ||||||
Description | ||||||
Abstract— In this paper, a study on the different Transfer Learning models is made for the purpose of recognizing Myanmar Fingerspelling (Myanmar Sign Language) alphabets. This experiment shows that Transfer Learning can play a significant role for sign language recognition system and is capable of recognizing the static hand gesture images that represent the Myanmar consonants from က (ka) to အ (a). The main objective of this paper is to investigate the performance of various Transfer Learning models for Myanmar Fingerspelling recognition. We proposed 12 Transfer Learning models using TensorFlow library and the accuracy for each model is compared. Among these 12 models, VGG16, ResNet50 and MobileNet with epoch 50 yielded the highest accuracy score with 94%. Although there are some limitations in the datasets, each model provides the encouraging results and thus, it can believe that the fully generalizable recognition system based on Transfer Learning can be produced for all Myanmar Sign Language Fingerspelling characters by doing further research with more data. |
||||||
Keywords | ||||||
Myanmar Sign Language, Myanmar Fingerspelling, Transfer Learning, Myanmar consonants | ||||||
Journal articles | ||||||
1 | ||||||
Journal of Intelligent Informatics and Smart Technology | ||||||
pp 35-44 | ||||||
4 |