Anima Recognition

Using Joint Visual Vocabulary



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.

People: Heydar Maboudi Afkham, Alireza Tavakoli Targhi, Jan-oluf Eklundh, and Andrzej Pronobis

Different difficulties that can be faced when dealing with the animal classification problem. The images in each row present some sample images of one class. These variations in view point, shape, illumination, color and etc. makes the task of animal recognition a challenging task.

Examples of intra-class similarities and inter-class differences in the database. The two images on the left show two different goats that vary in both texture and color, while the two images on the right show a female lion and a cougar which look similar with respect to both texture and color.

KTH-Animal Database


Images ( Will be available soon)


Example of Annotation:


Related Publication

Joint Visual Vocabulary for Animal Classification

Heydar Maboudi Afkham, Alireza Tavakoli Targhi, Jan-oluf Eklundh, and Andrzej Pronobis

In Proceedings of the International Conference on Pattern Recognition (ICPR08), Tampa, FL, USA, December 2008.  [Paper PDF][Presentation PPT]