文章基本信息

标题：VIDEO OBJECT SEGMENTATION APPLYING SPECTRAL ANALYSIS AND BACKGROUND SUBTRACTION
本地全文：下载
作者：RURI SUKO BASUKI ; MOCH. ARIEF SOELEMAN ; RICARDUS ANGGI PRAMUNENDAR 等
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2015
卷号：72
期号：2
出版社：Journal of Theoretical and Applied
摘要：This study proposes an approach to segment video object semi-automatically. The issue of this study is the lack of semantic information on video object segmentation. Manual segmentation by human is not effective if the video has a large size. For initialization, we use scribble-based technique to differentiate between foreground and background. After the separation object from the background, the subtraction operation between the current and subsequent frame was performed by applying a background subtraction algorithm. Spectral analysis and background subtraction for video object segmentation becomes effective. The evaluation of this study is measured by Mean Square Error. Experiment results demonstrate the high precision of object segmentation.
关键词：Segmentation; Alpha Matting; Background Subtraction