A Bag of Strings Representation for Image Categorization
Journal of Mathematical Imaging and Vision
A cascade of unsupervised and supervised neural networks for natural image classification
CIVR'06 Proceedings of the 5th international conference on Image and Video Retrieval
Objectionable image detection by ASSOM competition
CIVR'06 Proceedings of the 5th international conference on Image and Video Retrieval
Hi-index | 0.00 |
Nowadays, most of the research works in the area of image retrieval try to build an image signature by considering the image as a whole. In this paper, we proposed an alternative based on the detection of some salient points in the image. For this purpose, we propose a new efficient salient point detector based on a wavelet transform. The efficiency of our detector lies in the representation of the wavelet coefficients by a zerotree data structure and by a saliency formulation that does not favor any direction. Thus, the detected salient points are located on sharp region boundaries whatever their direction. From the detected salient points, we build a color/texture signature by using jointly the well-known color correlogram extended to salient features and rotated wavelet filter responses. Experimental results conducted by adopting a global salient approach and a local salient approach show the effectiveness of the proposed scheme.