Incremental Object Matching with Bayesian Methods and Particle Filters

In batch learning all the training examples have to be available at once to train the model, which often leads to slow performance and large memory requirements. Little work has been done in developing incremental object learners. In this paper, we present an incremental method that finds corresponding points of similar object instances, appearing in natural grayscale images with arbitrary location, scale and orientation. The approach is Bayesian and combines the shape and appearance of the corresponding points into the posterior distribution for the location of them. The posterior distribution is recursively sampled with particle filters to locate the most probable corresponding point sets in the image being processed. The results indicate that the matched corresponding points can be used in forming a representation of the object, which can be used in detecting instances of the object in novel test images.