Abstract

Recognition systems for complex and deformable objects must handle a variety of possible object appearances. In this paper, a compositional approach to this problem is studied which splits the set of possible appearances into easier sub-problems. To this end, a grammar is introduced that represents objects by a hierarchy of increasingly abstract visual alphabets. These alphabets store features, complex patterns and different views of objects. The geometrical constraints are optimised to the respective level of abstraction. The performance of the method is demonstrated on a cartoon data base with high intra-class variance.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.