Abstract
Multiclass pattern recognition systems based on independently designed subrecognition systems (MURISS) are presented. Each subrecognition system is essentially a dichotomizer. As the models of MURISS we discuss MURIDDS (Multiclass pattern recognition system based on independently designed dual class recognition systems) and MURICS (Multiclass pattern recognition system based on independent classwise recognition systems). The performance of these systems is specified with respect to the total error and the rejection probabilities. For these probabilities we derive upper bounds which are composed of the error probabilities of subrecognition systems. These upper bounds yield a theoretical validity of MURIDDS and MURICS since the minimization of subsystem error probabilities will minimize the upper bound for the sum of the total error and the rejection probabilities. In order to illustrate the importance of MURIDDS and MURICS, we present several examples and the results of computer simulation.
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 callMore From: IEEE Transactions on Systems, Man, and Cybernetics
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.
