Contextual classification of image patches with latent aspect models

We present a novel approach for contextual classification of image patches in complex visual scenes, based on the use of histograms of quantized features and probabilistic aspect models. Our approach uses context in two ways: (1) by using the fact that specific learned aspects correlate with the semantic classes, which resolves some cases of visual polysemy often present in patch-based representations, and (2) by formalizing the notion that scene context is image-specific -what an individual patch represents depends on what the rest of the patches in the same image are-. We demonstrate the validity of our approach on a man-made vs. natural patch classification problem. Experiments on an image collection of complex scenes show that the proposed approach improves region discrimination, producing satisfactory results, and outperforming two non-contextual methods. Furthermore, we also show that co-occurrence and traditional (Markov Random Field) spatial contextual information can be conveniently integrated for further improved patch classification.