Adaptive integrated image segmentation and object recognition

Bir Bhanu, Jing Peng

Research output: Contribution to journalArticlepeer-review

100 Scopus citations


This paper presents a general approach to image segmentation and object recognition that can adapt the image segmentation algorithm parameters to the changing environmental conditions. Segmentation parameters are represented by a team of generalized stochastic learning automata and learned using connectionist reinforcement learning techniques. The edge-border coincidence measure is first used as reinforcement for segmentation evaluation to reduce computational expenses associated with model matching during the early stage of adaptation. This measure alone, however, can not reliably predict the outcome of object recognition. Therefore, it is used in conjunction with model matching where the matching confidence is used as a reinforcement signal to provide optimal segmentation evaluation in a closed-loop object recognition system. The adaptation alternates between global and local segmentation processes in order to achieve optimal recognition performance. Results are presented for both indoor and outdoor color images where the performance improvement over time is shown for both image segmentation and object recognition.

Original languageEnglish
Pages (from-to)427-441
Number of pages15
JournalIEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews
Issue number4
StatePublished - Nov 2000


Dive into the research topics of 'Adaptive integrated image segmentation and object recognition'. Together they form a unique fingerprint.

Cite this