自然图像中的对象自动检测和提取.pdf

35 2 2009 1 Vol.35 No.2 Computer Engineering January 2009 ·· 2009 A TP391.41 1 2 (1. 100081 2. 100081) graph-cut Pascal VOC2006 Automatical Object Detection and Extraction in Real-world Image 1 2 NIE Qing , ZHAN Shou-yi (1. School of Information Science and Technology, Beijing Institute of Technology, Beijing 100081; 2. School of Computer, Beijing Institute of Technology, Beijing 100081) AbstractThis paper introduces a matting model based on exemplar to realize automatical training and detection in real-world image. Combined with spatial histogram of visual words improve the performance of order less bag-of-features image representation. Background and foreground information can be got automatically from the phase of localization. It uses graph-cut technique to accomplish matting automatically. The test results on Pascal VOC2006 test set show that the detection rate of this method is high, and its automatically matting effect is as well as existing interactive image cutout tool. Key wordsobject detection; matting; bag of feature; object classification [3] 1 SIFT k-meansSIFT2 000 [4] D (w) Knockout, Ruzon Tomasi, Hillman, Bayesian, Poisson, D (w) w (1) w Energy Matting, Grabcut, Lazy