Meter Value Recognition using Locally Connected Hierarchical Networks

• Author: Sven Behnke

 
• In Proceedings of 11th European Symposium on Artificial Neural Networks ESANN'03 -- Bruges, Belgium, pp. 535-540, 2003.

 
• Abstract:
This paper describes a two-stage system for the recognition of postage meter values. A feed-forward Neural Abstraction Pyramid is initialized in an unsupervised manner and trained in a supervised fashion to classify an entire digit block. It does not need prior digit segmentation. If the block recognition is not confident enough, a second stage tries to recognize single digits, taking into account the block classifier output for a neighboring digit as context. The system is evaluated on a large database. It can recognize meter values that are hard to read for humans.

 
• Full paper: esann03.pdf