Indexed by:
Abstract:
将机器学习运用到视网膜血管分割当中已成为一种趋势,然而选取什么特征作为血管与非血管的特征仍为众所思考的问题。该文利用将血管像素与非血管像素看作二分类的原理,提出一种混合的5D特征作为血管像素与非血管像素的表达,从而能够简单快速地将视网膜血管从背景中分割开来。其中5D特征向量包括CLAHE(Contrast Limited Adaptive Histgram Equalization),高斯匹配滤波,Hesse矩阵变换,形态学底帽变换,B-COSFIRE(Bar-selective Combination Of Shifted FIlter REsponses),通过将融合特征输入SVM(支持向...
Keyword:
Reprint Author's Address:
Email:
Source :
电子与信息学报
Year: 2017
Issue: 08
Volume: 39
Page: 1956-1963
Cited Count:
SCOPUS Cited Count:
ESI Highly Cited Papers on the List: 0 Unfold All
WanFang Cited Count:
Chinese Cited Count:
30 Days PV: 13
Affiliated Colleges: