文章基本信息

标题：Automatic Matting Using Edge Feature-Based Scribbles
本地全文：下载
作者：Meidya Koeshardianto ; Eko Mulyanto Yuniarno ; Mochamad Hariadi 等
期刊名称：IAENG International Journal of Computer Science
印刷版ISSN：1819-656X
电子版ISSN：1819-9224
出版年度：2019
卷号：46
期号：3
页码：459-466
出版社：IAENG - International Association of Engineers
摘要：Foreground and background extraction, or commonlycalled matting, is still widely used in computer visionapplications. Most of the matting, constraints of the foregroundare determined manually. However, it is more efficient if donewithout human intervention. We proposed a method to determineconstraint, scribbles, automatically using edge featureon image matting. Edge features are used to find gradientvector from each RGB color channel to obtain automaticscribbles. Our result will compare with a manual process usingMean Absolute Error (MAE). All of the experiment in thisresearch were used several images from some previous work.The experimental result shows our proposed method has onlydiffered 0,0336 from a current state of the art research and itdone automatically without human effort.
关键词：image matting; edge feature; automatic scribbles.