A Methodology and Metric for Quantitative Analysis and Parameter Optimization of Unsupervised, Multi-Region Image Segmentation

W.B. Kerr, L. Dettori, and L. Semler (USA)


Image Segmentation, Performance Evaluation, Unsuper vised, Multiple Regions


While image segmentation makes up a vital step in the pro cess of such tasks in the medical domain as tissue classifi cation, content-based image retrieval, and computer-aided diagnosis, it remains an area of much debate regarding how one interprets the results of machine segmented regions. Many segmentation methods are still evaluated using a sub jective human opinion of quality with a lack of quantita tive analysis. Ideally, segmentation would be performed on an image with as little aid from a human user as possible, so solid quantitative analysis of results and optimization of user-defined parameters are a must. This paper proposes the use of a methodology based on eight individual perfor mance measures. It then introduces a metric based on a sta tistical analysis of the overlap between machine segmented and corresponding ground truth images to evaluate and op timize algorithm parameters, and compare inter-algorithm performance for unsupervised segmentation algorithms.

Important Links:

Go Back