Robust needle recognition using Artificial Neural Network (ANN) and Random Sample Consensus (RANSAC)

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 thr...

Full description

Saved in:
Bibliographic Details
Main Author: Jaewon Chang
Format: Conference Proceeding
Language:English
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1550-5219
2332-5615
DOI:10.1109/AIPR.2012.6528219