Image annotation: which approach for realistic databases?

This paper describes an efficient approach to image annotation. It ranked first on the recent scene categorization track of the ImagEVAL1 benchmark. We show how homogeneous global image descriptors combined with a pool of Support Vector Machines achieve very good results. We also used this approach on several well known object recognition databases to emphasize two main aspects of this research domain : the importance of contextual information in object recognition and the unsuitability of many standard databases for this task. Categories and Subject Descriptors I.4.10 [Image Processing and Computer Vision]: Image Representation; I.5.4 [Pattern Recognition]: Applications—Computer vision General Terms Experimentation, Performance Keywords Scene Categorization, Image annotation, Object Recognition, Global Descriptor, Support Vector Machine

• Type: Conference
• Year: 2007
• Where: CIVR
• Authors: Nicolas Hervé, Nozha Boujemaa
• Keywords: CIVR 2007, Image Annotation, Object Recognition, Support Vector Machine