Manifolds of Bag of Pixels: A Better Representation for Image Recognition

This paper reports a negative result of image recognition algorithm constructed on the bag of pixels, a new representation method of images, and the manifolds of configurations of representative vectors of images which is spanned by using soft permutation matrix. Rather than represented by a single conventional vector of intensity of pixels row by row, an image is described by a column vector whose entries are n-tuples (x,y,p₁,,..,ps), where pi,i=1...s is the i-th property of the pixel at (x,y) which can be intensity or color information. So the image can be viewed as a point in high dimensional feature space 5. On the ground of this representation method and the researches of others, a new recognition algorithm is presented and tested with results far from satisfaction. The main contribution of this paper is that by using the basic analytical method, it provides a tentative explanation which reveals that some faults of the model and optimization algorithm confined its application in recognition.