Fast approximate kernel-based similarity search for image retrieval task

In content based image retrieval, the success of any distance-based indexing scheme depends critically on the quality of the chosen distance metric. We propose in this paper a kernel-based similarity approach working on sets of vectors to represent images. We introduce a method for fast approximate similarity search in large image databases with our kernel-based similarity metric. We evaluate our algorithm on image retrieval task and show it to be accurate and faster than linear scanning.

• Type: Conference
• Year: 2008
• Where: ICPR
• Authors: David Gorisse, Matthieu Cord, Frédéric Precioso, Sylvie Philipp-Foliguet
• Keywords: Computer Vision, Content Based Image Retrieval, ICPR 2008, Kernel-based Similarity, Kernel-based Similarity Approach