To develop a discriminative local feature based approach for the recognition of object classes from unsegmented cluttered scenes that doesn.t need to assume the independence of local features.
The most widely used approach for part-based object recognition is the generative model proposed in (Fergus). This classification system models the appearance, spatial relations and co-occurrence of local features. One limitation of this framework is that to make the model computationally tractable one has to assume the independence of the observed data (i.e., local features) given their assignment to parts in the model. This assumption might be too restrictive for a considerable number of object classes made of structured patterns.
We model objects as flexible constellations of parts conditioned on local observations found by an interest operator. For each class the probability of a given assignment of model parts to local features is modeled by a Conditional Random Field (CRF). We propose an extension of the CRF framework that incorporates hidden variables and combines class conditional CRFs into a unified framework for part-based object recognition (hCRF). The main advantage of the proposed model is that it allows us to relax the assumption of conditional independence of the observed data (i.e. local features) often used in generative approaches.
[1] R. Fergus, P Perona, and A. Zisserman. "Object class recognition by unsupervised scale-invariant learning". In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.
[2] A. Quattoni, M. Collins and T. Darrell. "Conditional Random Fields for Object Recognition". In Neural Information Processing Systems, 2004.
[3] A. Quattoni, M. Collins and T. Darrell. "Incorporating Semantic Constraints into a Discriminative Categorization and Labeling Model". Workshop on Semantic Knowledge in Vision, ICCV 2005.