Matching matching can be used to locate objects of

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: based segmentation. Matching: Matching can be used to locate objects of known appearance in an image, to search for specific patterns, etc. The best match is based on some criterion of optimality which depends on object properties and object relations. Matching criteria can be defined in many ways; in particular, correlation between a pattern and the searched image data is often used as a general matching criterion. Chamfer matching may be used to locate one-dimensional features that might otherwise defeat cost-based optimality approaches. Advanced optimal border and surface detection: Simultaneous border detection facilitates optimal identification of border pairs by finding an optimal path in a three-dimensional graph. It is based on the observation that there is information contained in the position of one border that might be useful in identifying the position of the other border. After a cost function that combines edge information from the left and right borders has been defined, either heuristic graph searching or dynamic programming methods can be used for optimal border detection. Optimal surface detection uses multi-dimensional graph for highly efficient determination of optimal surfaces in three- or higher-dimensional image data. The Faculty of Engineering Robotics Technology MECH 4041 23 B.Eng (Hons.) Mechatronics S. Venkannah Mechanical and Production Engineering Department method called surface growing is based on dynamic programming and avoids the problem of combinational explosion by introducing local conditions that must be satisfied by all legal surfaces. 2.0 Representing regions. Each algorithm that produces a set of image regions has to have a way to store them for future use. There are several possibilities including overlays on the original images, labeled images, boundary encodings, quad tree data structures, and property tables. 2.1 Overlays. An overlay is a method of showing the regions computed from an image by overlaying some color or colors on top of the orig...
View Full Document

This document was uploaded on 03/12/2014 for the course MECHANICAL 214 at University of Manchester.

Ask a homework question - tutors are online