Meter value recognition using locally connected hierarchical networks

This paper describes a two-stage system for the recognition ge 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.

• Type: Conference
• Year: 2003
• Where: ESANN
• Authors: Sven Behnke
• Keywords: Entire Digit Block, ESANN 2003, ESANN 2007, Meter Values, Prior Digit Segmentation