Abstract

This paper proposes a new approach to learning a discrimi- native model of ob ject classes, incorporating appearance, shape and con- text information efficiently. The learned model is used for automatic visual recognition and semantic segmentation of photographs. Our dis- criminative model exploits novel features, based on textons, which jointly model shape and texture. Unary classification and feature selection is achieved using shared boosting to give an efficient classifier which can be applied to a large number of classes. Accurate image segmentation is achieved by incorporating these classifiers in a conditional random field. Efficient training of the model on very large datasets is achieved by ex- ploiting both random feature selection and piecewise training methods. High classification and segmentation accuracy are demonstrated on three different databases: i) our own 21-ob ject class database of pho- tographs of real ob jects viewed under general lighting conditions, poses and viewpoints, ii) the 7-class Corel subset and iii) the 7-class Sowerby database used in [1]. The proposed algorithm gives competitive results both for highly textured (e.g. grass, trees), highly structured (e.g. cars, faces, bikes, aeroplanes) and articulated ob jects (e.g. body, cow).