Delayed reinforcement learning for closed-loop object recognition

Jing Peng, Bir Bhanu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations


Object recognition is a multi-level process requiring a sequence of algorithms at low, intermediate and high levels. Generally, such systems are open loop with no feedback between levels and assuring their robustness is a key challenge in computer vision research. A robust closed-loop system based on delayed reinforcement learning is introduced in this paper. The parameters of a multi-level system employed for model-based object recognition are learned. The method improves recognition results over time by using the output at the highest level as feedback for the learning system. It has been experimentally validated by learning the parameters of image segmentation and feature extraction and thereby recognizing 2D objects. The approach systematically controls feedback in a multi-level vision system and provides a potential solution to a long-standing problem in the field of computer vision.

Original languageEnglish
Title of host publicationTrack D
Subtitle of host publicationParallel and Connectionist Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages5
ISBN (Print)081867282X, 9780818672828
StatePublished - 1996
Event13th International Conference on Pattern Recognition, ICPR 1996 - Vienna, Austria
Duration: 25 Aug 199629 Aug 1996

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651


Other13th International Conference on Pattern Recognition, ICPR 1996


Dive into the research topics of 'Delayed reinforcement learning for closed-loop object recognition'. Together they form a unique fingerprint.

Cite this