In this paper, we introduce a scale-invariant feature selection method that learns to recognize and detect object classes from images of natural scenes. The first step of our method consists of clustering local scale-invariant descriptors to characterize object class appearance. Next, we train on the groups, and perform feature selection to determine the most discriminative parts. We use local regions to realize robust and sparse part and texture selection invariant to changes in scale, orientation and affine deformation and, as a result, we avoid image normalization in both training and prediction phases. We train our object models without requiring image parts to be labeled or objects to be separated from the background. Moreover, our method continues to work well when images have cluttered background and occluded objects. We evaluate our method on seven recently proposed datasets, and quantitatively compare the effect of different types of local regions and feature selection criteria on object recognition. Our experiments show that local invariant descriptors are an appropriate representation for many different object classes. Our results also confirm the importance of appearance-based discriminative feature selection.
