This is an implementation of part of Kanan & Cottrell (2010), which extracts dense features from color images which can then be used for object or face classification. In our experiments they perform quite well, generally about as well as SIFT descriptors, if not better, on a variety of popular datasets like Caltech-101.
As a side effect the algorithm also produces saliency maps which can be used to find interest points or to predict eye movements.
See http://www.chriskanan.com/nimble for more information.
Great job, just one thing : I have try to use the sample code with the photo of they in your picture,but the saliency map is different respect your that i see on the, computer vision, great work, image descriptors, image processing, just one thing ihave try to use it just cat the photo of the lad, object recognition, saliency, why
Great descriptors. However it would be great to have also the script computing SUN parameters ...