DocumentCode :
669155
Title :
Merging discrepancy measures for region-based segmentation results evaluation and comparison: Application to thresholded weld defect radiographic images
Author :
Goumeidane, Aicha Baya ; Khamadja, Mohammed
Author_Institution :
Centre de Rech. en Soudage et Controle, Algiers, Algeria
fYear :
2013
fDate :
4-6 Sept. 2013
Firstpage :
78
Lastpage :
82
Abstract :
This paper presents a new method for evaluating and comparing image segmentation results. This method consists of an association of measures that have the purpose to compute, in the sense of segmentation evaluation, the difference between two regions, one extracted from an ideal segmentation map and the same region obtained with a segmentation algorithm. Those measures take into account many aspects of the miss-segmented pixels as connectivity, compactness, location and their influence on the segmentation result. The new measure which rates the overall segmentation results, is easier to use comparatively to several measures, especially for a machine or an inexperienced user.
Keywords :
automatic optical inspection; feature extraction; image segmentation; radiography; welds; ideal segmentation map; image quality measure; merging discrepancy measure; miss segmented pixel; region extraction; region-based segmentation; thresholded weld defect radiographic image; weld defect detection; Area measurement; Image segmentation; Measurement uncertainty; Signal processing; Signal processing algorithms; Weight measurement;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image and Signal Processing and Analysis (ISPA), 2013 8th International Symposium on
Conference_Location :
Trieste
Type :
conf
DOI :
10.1109/ISPA.2013.6703718
Filename :
6703718
Link To Document :
بازگشت