Sparse groups: A polynomial middle-level approach for object recognition

We present a method to significantly reduce the complexity of polynomial-time object recognition algorithms while guaranteeing high tolerance to noisy and clutter data. Our approach uses a middle-level representation based on sparse groups, a novel concept introduced in this paper This representation permits to break down the recognition algorithm into two (or more) simpler stages, where each stage works with only a portion of the image features. This way of handling image information leads the algorithm to a considerably reduction of complexity. We implement a geometric matching based on boundary points as features, with a polynomial complexity.