Gustavo Pfeiffer, R. Marroquim, Antonio A. F. Oliveira
{"title":"WebcamPaperPen: A Low-Cost Graphics Tablet","authors":"Gustavo Pfeiffer, R. Marroquim, Antonio A. F. Oliveira","doi":"10.1109/SIBGRAPI.2014.54","DOIUrl":null,"url":null,"abstract":"We present an inexpensive, practical, easy to set up and modestly precise system to generate computer mouse input in a similar fashion to a graphics tablet, using webcam, paper, pen and a desk lamp. None of the existing methods, to our knowledge, solves the task with all these qualities. Our method detects clicks using the pen shadow and computes the mouse cursor position by predicting where the pen tip and its shadow will hit each other. Our method employs a series of image processing algorithms and heuristics to extract interest features with subpixel precision, projective geometry operations to reconstruct the real-world position, and hysteresis filters to improve stability. We also provide an algorithm for easy calibration. Finally, the quality of our method is evaluated with user tests and a quantitative experiment.","PeriodicalId":146229,"journal":{"name":"2014 27th SIBGRAPI Conference on Graphics, Patterns and Images","volume":"5 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 27th SIBGRAPI Conference on Graphics, Patterns and Images","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SIBGRAPI.2014.54","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
We present an inexpensive, practical, easy to set up and modestly precise system to generate computer mouse input in a similar fashion to a graphics tablet, using webcam, paper, pen and a desk lamp. None of the existing methods, to our knowledge, solves the task with all these qualities. Our method detects clicks using the pen shadow and computes the mouse cursor position by predicting where the pen tip and its shadow will hit each other. Our method employs a series of image processing algorithms and heuristics to extract interest features with subpixel precision, projective geometry operations to reconstruct the real-world position, and hysteresis filters to improve stability. We also provide an algorithm for easy calibration. Finally, the quality of our method is evaluated with user tests and a quantitative experiment.