Abstract
A model-based recognition procedure for two-dimensional objects in different postures and occluded instances is proposed. Object description is based on a new shape decomposition technique that can take advantage from both geometrical and topological properties. A relational graph is constructed and the matching task is formulated as an optimization problem, quadratic assignment. The approach taken to solve the correspondence problem employs a Hopfield neural network. This leads to a reasonable computational time and a high degree of fault tolerance as shown in several experimental results.
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 callDisclaimer: 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.
