Image Classification Using Multiscale Information Fusion Based on Saliency Driven Nonlinear Diffusion Filtering

Weiming Hu, Ruiguang Hu, Nianhua Xie, Haibin Ling, Stephen Maybank
2014 IEEE Transactions on Image Processing  
In this paper, we propose saliency driven image multi-scale nonlinear diffusion filtering. The resulting scale space in general preserves or even enhances semantically important structures such as edges, lines, or flow like structures in the foreground, and inhibits and smoothes clutter in the background. The image is classified using multi-scale information fusion based on the original image, the image at the final scale at which the diffusion process converges, and the image at a mid-scale.
more » ... e at a mid-scale. Our algorithm emphasizes the foreground features which are important for image classification. The background image regions, whether considered as contexts of the foreground or noise to the foreground, can be globally handled by fusing information from different scales. Experimental tests of the effectiveness of the multi-scale space for image classification are conducted on the following publicly available datasets: the PASCAL 2005 dataset, the Oxford 102 flowers dataset, and the Oxford 17 flowers dataset, with high classification rates.
doi:10.1109/tip.2014.2303639 pmid:24569440 fatcat:dmdjois2irdqlkuryuzbt5pj2m