Seminar: Saliency Moments for Image Categorization
Miriam REDI - PhD student
Date: April 14, 2011
Location: Eurecom - salle EN05
In this presentation we present Saliency Moments, a new, holistic descriptor for image recognition inspired by two biological vision principles: the gist perception and the selective visual attention. While traditional image features extract either local or global discriminative properties from the visual content, we use a hybrid approach that exploits some coarsely localized information, i.e. the salient regions shape and contours, to build a global, low-dimensional image signature. Results show that this new type of image description out performs the traditional global features on scene and object categorization, for a variety of challenging datasets. Moreover, we show that, when combined with other existing descriptors (SIFT, Color Moments, Wavelet Feature and Edge Histogram), the saliency-based features provide complementary information, improving the precision of a retrieval system we built for the TRECVID 2010 dataset.
Saliency Moments for Image Categorization