Abstract
The present approach which realizes a new interpretation of MFI (see Eq. 3.1) through back propagation-type neural network (Pao in Adaptive pattern recognition and neural networks. Addison Wesley Publishing Company, 1989) produces graded consequences which are most suitable for pattern recognition and object recognition problems as stated in the previous chapters. The object recognition scheme (similar to the concept depicted in Fig. 5.1), proposed in this chapter is a model-based system (Ray and Dutta Mazumder in Application of differential geometry to recognize and locate partially occluded objects. Pattern Recognition Lett., pp. 351–360, 1989) in which recognition involves matching the input image with a set of predefined models of objects. In such a system the known objects are precompiled, creating a model database and this database is used to recognize objects in an occluded scene.
Sign-in/Register to access full text options 
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.
