Structure-based evaluation methodology for curvilinear structure detection algorithms

Authors:
Xiaoyi Jiang;Martin Lambers;Horst Bunke
Affiliations:
Department of Computer Science, University of Münster, Germany;Computer Graphics Group, University of Siegen, Germany;Institute of Computer Science and Applied Mathematics, University of Bern, Switzerland
Venue:
GbRPR'11 Proceedings of the 8th international conference on Graph-based representations in pattern recognition
Year:
2011

Citing 6
Cited 1

Faster scaling algorithms for network problems

SIAM Journal on Computing
An efficient cost scaling algorithm for the assignment problem

Mathematical Programming: Series A and B
Residuals + directional gaps = skeletons

Pattern Recognition Letters
Adaptive Local Thresholding by Verification-Based Multithreshold Probing with Application to Vessel Detection in Retinal Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Linear Time Algorithm for Computing Exact Euclidean Distance Transforms of Binary Images in Arbitrary Dimensions

IEEE Transactions on Pattern Analysis and Machine Intelligence
Supervised Evaluation Methodology for Curvilinear Structure Detection Algorithms

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1 - Volume 1

Structural performance evaluation of curvilinear structure detection algorithms with application to retinal vessel segmentation

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

Curvilinear structures are useful features, particularly in medical image analysis. Typically, a pixel-wise comparison with manually specified ground truth is used for performance evaluation. In this paper we propose a novel structure-based methodology for evaluating the performance of curvilinear structure detection algorithms. We consider the two aspects of performance, namely detection rate and detection accuracy, separately. This is in contrast to their mixed handling in earlier approaches that typically produces biased impression of detection quality. The proposed performance measures provide a more informative and precise performance characterization. A series of experiments in the context of retinal vessel detection are presented to demonstrate the advantages of our approach.