作者: Yannis Avrithis , Hervé Le Borgne , Evaggelos Spyrou , Noel O'Connor , Eddie Cooke
DOI: 10.1007/11550907_134
关键词:
摘要: This paper proposes three content-based image classification techniques based on fusing various low-level MPEG-7 visual descriptors. Fusion is necessary as descriptors would be otherwise incompatible and inappropriate to directly include e.g. in a Euclidean distance. Three approaches are described: A "merging" fusion combined with an SVM classifier, back-propagation KNN classifier Fuzzy-ART neurofuzzy network. In the latter case, fuzzy rules can extracted effort bridge "semantic gap" between high-level semantics of image. All networks were evaluated using content from repository aceMedia project1 more specifically beach/urban scene problem.