Dong-Sung Ryu, Soo-Hyun Park, Jeong-Won Lee, Do-Hoon Lee, Hwan-Gue Cho
{"title":"CINETOON: A Semi-automated System for Rendering Black/White Comic Books from Video Streams","authors":"Dong-Sung Ryu, Soo-Hyun Park, Jeong-Won Lee, Do-Hoon Lee, Hwan-Gue Cho","doi":"10.1109/CIT.2008.WORKSHOPS.42","DOIUrl":null,"url":null,"abstract":"In this paper we propose CINETOON, a semi-automated system which can generate black/white comic books from a sequence of video streams obtained from cinemas. CINETOON provides an intuitive interface to render comics. Our system consists of four major components : Key Frame Extractor, Image-based Comic Cut Converter, Background Effect Stylizer and Comic Elements Renderer. First, to capture the frame image from the video stream, we generate a workspace file which includes the frame images and script files. Second, the comic converter is decoupled into two processes: image binarization and stroke extraction. We introduce one novel black/white binarization algorithm for the frame images. Third, in order to segment foreground object, we propose a simple and straightforward algorithm implemented in the background effect stylizer. Also CINETOON provides some classes of shape-controllable icons such as word balloon, stylized fonts, speed line and specialized icons. The comic pages produced by our system show that CINETOON was so successful to make a comic book from a well-known cinema in a reasonable time and manual intervention.","PeriodicalId":155998,"journal":{"name":"2008 IEEE 8th International Conference on Computer and Information Technology Workshops","volume":"28 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2008-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2008 IEEE 8th International Conference on Computer and Information Technology Workshops","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CIT.2008.WORKSHOPS.42","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6
Abstract
In this paper we propose CINETOON, a semi-automated system which can generate black/white comic books from a sequence of video streams obtained from cinemas. CINETOON provides an intuitive interface to render comics. Our system consists of four major components : Key Frame Extractor, Image-based Comic Cut Converter, Background Effect Stylizer and Comic Elements Renderer. First, to capture the frame image from the video stream, we generate a workspace file which includes the frame images and script files. Second, the comic converter is decoupled into two processes: image binarization and stroke extraction. We introduce one novel black/white binarization algorithm for the frame images. Third, in order to segment foreground object, we propose a simple and straightforward algorithm implemented in the background effect stylizer. Also CINETOON provides some classes of shape-controllable icons such as word balloon, stylized fonts, speed line and specialized icons. The comic pages produced by our system show that CINETOON was so successful to make a comic book from a well-known cinema in a reasonable time and manual intervention.