{"title":"阿拉伯语可分解词识别的词缀方法:多字体打印脚本的验证","authors":"Souhir Ben Chobba, Sirine Barkallah, S. Kanoun","doi":"10.1109/ICTIA.2014.7883755","DOIUrl":null,"url":null,"abstract":"In this paper, we present a feasibility study and a validation of the affixal approach, dealing with Arabic decomposable word recognition, on multi-font and multi-size printed script, with the integration of several improvements. Our work details also a comparative study between this approach, based on linguistic concepts of vocabulary, and the different methods of lexical knowledge integration (dictionary of language and statistical model of language) used in the framework of the analytical approach. The obtained results with a dictionary of 159 661 words and a database of 2010 word images confirm the contribution of the affixal approach compared to the analytical approach on the level of the word hypotheses filtering which considerably improves the recognition rate.","PeriodicalId":390925,"journal":{"name":"2014 Information and Communication Technologies Innovation and Application (ICTIA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Affixal approach for Arabic decomposable word recognition: A validation on the multi-font printed script\",\"authors\":\"Souhir Ben Chobba, Sirine Barkallah, S. Kanoun\",\"doi\":\"10.1109/ICTIA.2014.7883755\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we present a feasibility study and a validation of the affixal approach, dealing with Arabic decomposable word recognition, on multi-font and multi-size printed script, with the integration of several improvements. Our work details also a comparative study between this approach, based on linguistic concepts of vocabulary, and the different methods of lexical knowledge integration (dictionary of language and statistical model of language) used in the framework of the analytical approach. The obtained results with a dictionary of 159 661 words and a database of 2010 word images confirm the contribution of the affixal approach compared to the analytical approach on the level of the word hypotheses filtering which considerably improves the recognition rate.\",\"PeriodicalId\":390925,\"journal\":{\"name\":\"2014 Information and Communication Technologies Innovation and Application (ICTIA)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2014-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2014 Information and Communication Technologies Innovation and Application (ICTIA)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICTIA.2014.7883755\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 Information and Communication Technologies Innovation and Application (ICTIA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICTIA.2014.7883755","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Affixal approach for Arabic decomposable word recognition: A validation on the multi-font printed script
In this paper, we present a feasibility study and a validation of the affixal approach, dealing with Arabic decomposable word recognition, on multi-font and multi-size printed script, with the integration of several improvements. Our work details also a comparative study between this approach, based on linguistic concepts of vocabulary, and the different methods of lexical knowledge integration (dictionary of language and statistical model of language) used in the framework of the analytical approach. The obtained results with a dictionary of 159 661 words and a database of 2010 word images confirm the contribution of the affixal approach compared to the analytical approach on the level of the word hypotheses filtering which considerably improves the recognition rate.