{"title":"绘图和计算-直观的计算器-","authors":"Barna Szocs, Szilárd Vajda, Judit Robu","doi":"10.1109/SISY.2012.6339507","DOIUrl":null,"url":null,"abstract":"This paper is presenting a complete system to recognize on-line handwritten digits and other mathematical symbols integrated in an intuitive calculator application running on an Android OS based smart device. Among the multitude of such existing calculator applications available on the market, this software framework provides not only an intuitive user interface (UI), but a special user experience too, allowing the user to input the algebraic formula using handwriting instead of classical buttons. The system uses not only the off-line information but also the on-line information available during the drawing process, and the combination of these aspects allowed the possibility to build a competitive real-time application. The used neural networks beside providing an accurate recognition for the different digits, operators and other symbols, provide a straightforward way to adapt the tool to the specific handwriting of each particular user. The experimental results proved an efficiency (91.57%) of the system using a rather large on-line dataset collected from users.","PeriodicalId":207630,"journal":{"name":"2012 IEEE 10th Jubilee International Symposium on Intelligent Systems and Informatics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"D.A.C Draw and Calc - the intuitive calculator -\",\"authors\":\"Barna Szocs, Szilárd Vajda, Judit Robu\",\"doi\":\"10.1109/SISY.2012.6339507\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper is presenting a complete system to recognize on-line handwritten digits and other mathematical symbols integrated in an intuitive calculator application running on an Android OS based smart device. Among the multitude of such existing calculator applications available on the market, this software framework provides not only an intuitive user interface (UI), but a special user experience too, allowing the user to input the algebraic formula using handwriting instead of classical buttons. The system uses not only the off-line information but also the on-line information available during the drawing process, and the combination of these aspects allowed the possibility to build a competitive real-time application. The used neural networks beside providing an accurate recognition for the different digits, operators and other symbols, provide a straightforward way to adapt the tool to the specific handwriting of each particular user. The experimental results proved an efficiency (91.57%) of the system using a rather large on-line dataset collected from users.\",\"PeriodicalId\":207630,\"journal\":{\"name\":\"2012 IEEE 10th Jubilee International Symposium on Intelligent Systems and Informatics\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2012-10-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2012 IEEE 10th Jubilee International Symposium on Intelligent Systems and Informatics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SISY.2012.6339507\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 IEEE 10th Jubilee International Symposium on Intelligent Systems and Informatics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SISY.2012.6339507","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
This paper is presenting a complete system to recognize on-line handwritten digits and other mathematical symbols integrated in an intuitive calculator application running on an Android OS based smart device. Among the multitude of such existing calculator applications available on the market, this software framework provides not only an intuitive user interface (UI), but a special user experience too, allowing the user to input the algebraic formula using handwriting instead of classical buttons. The system uses not only the off-line information but also the on-line information available during the drawing process, and the combination of these aspects allowed the possibility to build a competitive real-time application. The used neural networks beside providing an accurate recognition for the different digits, operators and other symbols, provide a straightforward way to adapt the tool to the specific handwriting of each particular user. The experimental results proved an efficiency (91.57%) of the system using a rather large on-line dataset collected from users.