%0 Journal Article %T Evaluation for Uncertain Image Classification and Segmentation %+ Extraction et Exploitation de l'Information en Environnements Incertains (E3I2) %A Martin, Arnaud %A Laanaya, Hicham %A Arnold-Bos, Andreas %Z WOS %< avec comité de lecture %@ 0031-3203 %J Pattern Recognition %I Elsevier %V 39 %N 11 %P 1987-1995 %8 2006-11-01 %D 2006 %Z 0806.1796 %K Image classification %K Image segmentation %K Uncertainty environment %K Sonar image %K Fusion of experts %K Fusion of classifiers %Z ACM: I.4, I.5 %Z Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] %Z Computer Science [cs]/Artificial Intelligence [cs.AI] %Z Engineering Sciences [physics]/Signal and Image processing %Z Computer Science [cs]/Signal and Image ProcessingJournal articles %X Each year, numerous segmentation and classification algorithms are invented or reused to solve problems where machine vision is needed. Generally, the efficiency of these algorithms is compared against the results given by one or many human experts. However, in many situations, the location of the real boundaries of the objects as well as their classes are not known with certainty by the human experts. Furthermore, only one aspect of the segmentation and classification problem is generally evaluated. In this paper we present a new evaluation method for classification and segmentation of image, where we take into account both the classification and segmentation results as well as the level of certainty given by the experts. As a concrete example of our method, we evaluate an automatic seabed characterization algorithm based on sonar images. %G English %2 https://hal.science/hal-00286593/document %2 https://hal.science/hal-00286593/file/paper_eval2.pdf %L hal-00286593 %U https://hal.science/hal-00286593 %~ ENSTA-BRETAGNE %~ ENSTA-BRETAGNE-STIC %~ ENSIETA-E3I2