Dissimilarity criteria and their comparison for quantitative evaluation of image segmentation: application to human retina vessels
| Autor: | Johan Debayle, Jean-Charles Pinoli, Yann Gavet, Mathieu Fernandes |
|---|---|
| Přispěvatelé: | Centre Ingénierie et Santé (CIS-ENSMSE), École des Mines de Saint-Étienne (Mines Saint-Étienne MSE), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Institut Fédératif de Recherche en Sciences et Ingénierie de la Santé (IFRESIS-ENSMSE), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-IFR143, Laboratoire Georges Friedel (LGF-ENSMSE), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Lyon-Centre National de la Recherche Scientifique (CNRS), Surfaces et Tissus Biologiques (STBio-ENSMSE), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-CIS, Cytoo SA, Centre Sciences des Processus Industriels et Naturels (SPIN-ENSMSE), Département PROcédés Poudres, Interfaces, Cristallisation et Ecoulements (PROPICE-ENSMSE), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-SPIN, CYTOO SA, Grenoble, France |
| Rok vydání: | 2014 |
| Předmět: |
Quantitative evaluation
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Scale-space segmentation Retinal blood vessels Field (computer science) Segmentation evaluation Consistency (database systems) [SPI.GPROC]Engineering Sciences [physics]/Chemical and Process Engineering Computer vision Segmentation Mathematics Image segmentation Retina vessels Segmentation-based object categorization business.industry Pattern recognition Computer Science Applications Hardware and Architecture [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] Dissimilarity criteria Pattern recognition (psychology) Computer Vision and Pattern Recognition Artificial intelligence business Software |
| Zdroj: | Machine Vision and Applications Machine Vision and Applications, Springer Verlag, 2014, 25 (8), pp.1953-1966. ⟨10.1007/s00138-014-0625-2⟩ |
| ISSN: | 1432-1769 0932-8092 |
| Popis: | International audience; The quantitative evaluation of image segmentation is an important and difficult task that is required for making a decision on the choice of a segmentation method and for the optimal tuning of its parameter values. To perform this quantitative evaluation, dissimilarity criteria are relevant with respect to the human visual perception, contrary to metrics that have been shown to be visually not adapted. This article proposes to compare eleven dissimilarity criteria together. The field of retina vessels image segmentation is taken as an application issue to emphasize the comparison of five specific image segmentation methods, with regard to their degrees of consistency and discriminancy. The DRIVE and STARE databases of retina images are employed and the manual/visual segmentations are used as a reference and as a control method. The so-called ϵ criterion gives results in agreement with perceptually based criterions for achieving the quantitative comparison. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|