This paper describes a discriminatively trained, multiscale, deformable part model for object detection. Our system achieves a two-fold improvement in average precision over the best performance in the 2006 PASCAL person detection challenge. It also outperforms the best results in the 2007 challenge in ten out of twenty categories. The system relies heavily on deformable parts. While deformable...

We develop a new class of parameterized models based on the linear interpolation of two parameterized shapes using a blending function. Using a small number of additional parameters, blending extends the coverage of shape primitives. In particular, it offers the ability to construct shapes whose genus can change. Blended models are incorporated into our physics-based shape estimation framework ...

Following the success of applying deformable models to feature extraction, a natural next step is to apply such models to pattern classiication. Recently, we have cast a deformable model under a Bayesian framework for classiication, giving promising results. However, deformable model methods are computation-ally expensive due to the required iterative optimization process. The problem is even m...

This paper aims to make a brief survey on the current segmentation algorithms used for medical images. Instead of describing the detailed procedures, we will summarize their main ideas, enumerate their merits and drawbacks and discuss their possible applications. The algorithms are classified into three main categories: threshold-based models, pattern recognition models and deformable models. D...