Image segmentation with context

Summary, in English

We present a technique for simultaneous segmentation and classification of image partitions using combinatorial optimization techniques. By combining existing image segmentation approaches with simple learning techniques we show how prior knowledge can be incorporated into the visual grouping process through the formulation of a quadratic binary optimization problem. We further show how such to efficiently solve such problems through relaxation techniques and trust, region methods. This has resulted in an method that partitions images into a number of disjoint regions based on previously learned example segmentations. Preliminary experimental results are also presented in support of our suggested approach.

• Author: Anders P Eriksson; Carl Olsson; Fredrik Kahl
• Department/s: Mathematics (Faculty of Engineering)
• Publishing year: 2007
• Language: English
• Pages: 283-292
• Publication/Series: Proceedings 15th Scandinavian Image Analysis Conference
• Volume: 4522
• Links: http://dx.doi.org/10.1007/978-3-540-73040-8_29
• Document type: Conference paper
• Publisher: Springer
• Topic: Mathematics
• Keywords: visual grouping process; learning technique; combinatorial optimization technique; image segmentation; image classification; relaxation technique; quadratic binary optimization problem
• Conference name: 15th Scandinavian Image Analysis Conference
• Conference date: 2007-06-10 - 2007-06-14
• Conference place: Aalborg, Denmark
• Status: Published