Active Shape Models Using Scale Invariant Feature Transform  

作　　者：史勇红 戚飞虎 栾红霞 吴国荣 

机构地区：[1]Dept. of Computer Science and Eng., Shanghai Jiaotong Univ.

出　　处：《Journal of Shanghai Jiaotong university(Science)》2007年第6期713-718,共6页上海交通大学学报（英文版）

基　　金：The National Natural Science Foundation of China(No60271033)

摘　　要：A new active shape models (ASMs) was presented, which is driven by scale invariant feature transform (SIFT) local descriptor instead of normalizing first order derivative profiles in the original formulation, to segment lung fields from chest radiographs. The modified SIFT local descriptor, more distinctive than the general intensity and gradient features, is used to characterize the image features in the vicinity of each pixel at each resolution level during the segmentation optimization procedure. Experimental results show that the proposed method is more robust and accurate than the original ASMs in terms of an average overlap percentage and average contour distance in segmenting the lung fields from an available public database.A new active shape models (ASMs) was presented, which is driven by scale invariant feature transform (SIFT) local descriptor instead of normalizing first order derivative profiles in the original formulation, to segment lung fields from chest radiographs. The modified SIFT local descriptor, more distinctive than the general intensity and gradient features, is used to characterize the image features in the vicinity of each pixel at each resolution level during the segmentation optimization procedure. Experimental results show that the proposed method is more robust and accurate than the original ASMs in terms of an average overlap percentage and average contour distance in segmenting the lung fields from an available public database.

关 键 词：active shape model (ASM) deformable segmentation CHEST RADIOGRAPH scale INVARIANT feature transform (SIFT) local DESCRIPTOR 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]