Selected Chapters of Image Processing 183.151, 2011SS

• Lecturer: Walter G. Kropatsch
• Termin: March and Block in June
• Ort: Seminarraum 183/2

SS2011:  
Basic Methodology and Recent Developments in Structural Pattern Recognition

Guest-Professor: Horst Bunke

The King-Sun Fu Prize 2010 Award Winner in Istanbul

Research Group on Computer Vision and Artificial Intelligence IAM
University of Bern, Switzerland
bunke at iam.unibe.ch

Abstract:
Statistical pattern recognition is characterized by the use of feature vectors for pattern representation, while the structural approach is based on symbolic data structures, such as strings, trees, and graphs. Clearly, symbolic data structures have a higher representational power than feature vectors because they allows one to directly model relationships that may exist between the individual parts of a pattern. However, many operations that are needed in classification, clustering, and other pattern recognition tasks are not defined for graphs. Consequently, there has been a lack of algorithmic tools in the domain of structural pattern recognition since its beginning. This lecture gives an introduction to the basic methodology and recent developments in the field of structural pattern recognition. In particular, it shows various attempts to bridge the gap between statistical and structural pattern recognition, i.e. to make algorithmic tools originally developed for feature vectors applicable to symbolic data structures.

Coursework:

Download coursework sheet

Schedule:

May 4th: Coursework handed out

June 17th: draft version of coursework due

June 21-30, 2011: block lecture of Prof. Bunke

July 10th: final version of coursework due

Lecture Dates:

Download Invitation-Flyer