In Computer Vision we encounter textures at numerous places and are thus part of current research since many years.

Hereby, textures can have different roles. On one hand they can serve as feature for segmentation of images. With enough prior knowledge of the texture, it can also be used to determine the form of objects or the perspective in images. Last but not least, texture itself can be the center of classification.

In this seminar we focus on the following methods to cope with these problems:

• Classification of textures
• Texture based segmentation
• Texture as meta-feature: writer identification

Every participant will develop a prototype, based on current publications. The performed experiments for the individual task are then presented to the group and summarized in a short report.