计算机工程 ›› 2019, Vol. 45 ›› Issue (9): 248-252.doi: 10.19678/j.issn.1000-3428.0051158

• 图形图像处理 • 上一篇    下一篇

基于图像显著性识别的自动抠图系统

曹春红, 孙榕, 钟琴   

  1. 东北大学 计算机科学与工程学院, 沈阳 110189
  • 收稿日期:2018-04-10 修回日期:2018-07-22 出版日期:2019-09-15 发布日期:2019-09-03
  • 作者简介:曹春红(1976-),女,副教授、博士,主研方向为计算机图形学、计算机辅助设计;孙榕、钟琴,本科生。
  • 基金项目:
    中央高校基本科研业务费专项资金(N161602001);辽宁省自然科学基金(20170540312,20180520001)。

Automatic Matting System Based on Image Saliency Recognition

CAO Chunhong, SUN Rong, ZHONG Qin   

  1. School of Computer Science and Engineering, Northeastern University, Shenyang 110189, China
  • Received:2018-04-10 Revised:2018-07-22 Online:2019-09-15 Published:2019-09-03

摘要: RC算法引入区域级别的对比度,对颜色模型进行重新量化,能大幅提高处理速度、突出显著目标,然而其基于图的分割算法易出现分割区域不能较好地贴合物体边缘的问题。引入优化的SLIC算法代替基于图的分割算法,对RC算法进行改进,并实现一个基于图像显著性识别的自动抠图系统,克服传统抠图系统必须人工标记的缺点。实验结果表明,相比IT、MZ、GB、RC等经典算法,改进的RC算法抠取的显著目标更精确,其查准率、查全率、F值分别为0.82、0.85和0.83,系统能自动抠取显著目标并提供图片合成应用。

关键词: 显著性识别, SLIC分割, 区域对比度, 自动抠图, 三分图

Abstract: The RC algorithm introduces regional-level contrast and re-quantizes the color model,which can greatly improve processing speed and highlight salient targets.However,the graph-based segmentation algorithm is prone to have the problem that the segmented region cannot fit the edge of the object well.This paper introduces an optimized SLIC algorithm instead of a graph-based segmentation algorithm to improve the RC algorithm,and implements an automatic matting system based on image saliency recognition,which overcomes the shortcomings of traditional matting systems that must be manually labeled.Experimental results show that compared with other classical algorithms such as IT,MZ,GB,RC,etc.,the improved RC algorithm captures salient targets with greater accuracy,its Precision,Recall,and F value are 0.82,0.85,and 0.83,respectively.The system can automatically capture salient targets and provide image synthesis applications.

Key words: saliency recognition, SLIC segmentation, regional contrast, automatic matting, trimap

中图分类号: