Animal Recognition using

This thesis presents a series of experiments on recognizing animals in complex scenes. Unlike usual objects used for the recognition task (cars, airplanes, ...) animals appear in a variety of poses and shapes in outdoor images. To perform this task a dataset of outdoor images should be provided. Among the available datasets there are some animal classes but as discussed in this thesis these datasets do not capture the necessary variations needed for realistic analysis. To overcome this problem a new extensive dataset, KTH-animals, containing realistic images of animals in complex natural environments. The methods designed on the other datasets do not preform well on the animals dataset due to the larger variations in this dataset. One of the methods that showed promising results on one of these datasets on the animals dataset was applied on KTH-animals and showed how it failed to encode the large variations in this dataset. To familiarize the reader with the concept of computer vision and the mathematics backgrounds a chapter of this thesis is dedicated to this matter. This section presents a brief review of the texture descriptors and several classification methods together with mathematical and statistical algorithms needed by them. To analyze the images of the dataset two different methodologies are introduced in this thesis. In the first methodology fuzzy classifiers we analyze the images solely based on the animals skin texture of the animals. To do so an accurate manual segmentation of the images is provided. Here the skin texture is judged using many different features and the results are combined with each other with fuzzy classifiers. Since the assumption of neglecting the background information in unrealistic the joint visual vocabularies are introduced. Joint visual vocabularies is a method for visual object categorization based on encoding the joint textural information in objects and the surrounding background, and requiring no segmentation during recognition. The framework can be used together with various learning techniques and model representations. Here we use this framework with simple probabilistic models and more complex representations obtained using Support Vector Machines. We prove that our approach provides good recognition performance for complex problems for which some of the existing methods have difficulties. The achievements of this thesis are a challenging database for animal recognition. A review of the previous work and related mathematical background. Texture feature evaluation on the "KTH-animal" dataset. Introduction a method for object recognition based on joint statistics over the image. Applying different model representation of different complexity within the same classification framework, simple probabilistic models and more complex ones based on Support Vector Machines.