Interactive contour extraction using NURBS-HMM

Authors:
Debin Lei;Chunhong Pan;Qing Yang;Minyong Shi
Affiliations:
Communication University of China, Beijing, China;National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, China;National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, China;Communication University of China, Beijing, China
Venue:
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part I
Year:
2006

Citing 6
Cited 1

Intelligent scissors for image composition

SIGGRAPH '95 Proceedings of the 22nd annual conference on Computer graphics and interactive techniques
Global Minimum for Active Contour Models: A Minimal Path Approach

International Journal of Computer Vision
The NURBS book (2nd ed.)

The NURBS book (2nd ed.)
User-steered image segmentation paradigms: live wire and live lane

Graphical Models and Image Processing
Lazy snapping

ACM SIGGRAPH 2004 Papers
"GrabCut": interactive foreground extraction using iterated graph cuts

ACM SIGGRAPH 2004 Papers

Multisource data registration based on NURBS description of contours

International Journal of Remote Sensing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In the paper, we attempt to develop a novel method to offer the possibility even for a non-expert to extract easily the contour of an object. A NURBS-HMM framework aiming at the interactive image contour extraction is proposed. We fit the initial points input by users with Non-Uniform Rational B-Spline(NURBS). Due to the local controllability of NURBS, the control points are considered as the states of Hidden Markov Model(HMM) framework, and the boundary features and uniformity along the boundary are integrated as the observations. The experimental results show the robustness of our method. As an interactive method, the method interacts with users in an efficient and comfortable way.