Robust Needle Recognition using Artificial Neural Network (ANN) and Random Sample Consensus (RANSAC)

被引：0
作者：
Chang, Jaewon [1 ]
机构：
[1] Case Western Reserve Univ, Dept Elect Engn & Comp Sci, Cleveland, OH 44106 USA
来源：
2012 IEEE APPLIED IMAGERY PATTERN RECOGNITION WORKSHOP (AIPR) | 2012年
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper, we suggest an algorithm for a half-circle-like surgical needle recognition in stereo image. The recognition starts from segmentation of needle in both stereo images using Artificial Neural Network (ANN). Next, the points in the segments are being matched to each other stereo image through intensity based matching, and then re-projected to 3D space which will be fitted to 3D circle. Finally, estimate the circle of the needle using RANdom SAmple Consensus (RANSAC) and known specification of the needle.
引用
收藏
页数：3
相关论文
共 9 条
  • [1] [Anonymous], 1997, MACHINE LEARNING, MCGRAW-HILL SCIENCE/ENGINEERING/MATH
  • [2] Christian W., 2007, MICCAI
  • [3] Fischler Martin A., 1981, COMMUNICATIONS ACM
  • [4] Direct least square fitting of ellipses
    Fitzgibbon, A
    Pilu, M
    Fisher, RB
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1999, 21 (05) : 476 - 480
  • [5] Fleishman E.A., 1967, Learning and individual differences, P165
  • [6] Frangi A., 1998, MICCAI
  • [7] Padoy N., 2011, P IEEE RSJ INT C INT
  • [8] Padoy N., 2011, P IEEE INT C ROB AUT
  • [9] Reznick RK, 2006, NEJM
1