Multi-Experts for Touching Digit String Recognition

Authors:
Xian Wang;Venu Govindaraju;Sargur Srihari
Affiliations:
-;-;-
Venue:
ICDAR '99 Proceedings of the Fifth International Conference on Document Analysis and Recognition
Year:
1999

Citing 0
Cited 3

StrCombo: combination of string recognizers

Pattern Recognition Letters - In memory of Professor E.S. Gelsema
Unconstrained Numeral Pair Recognition Using Enhanced Error Correcting Output Coding: A Holistic Approach

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Data-driven decomposition for multi-class classification

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

84.6% of touching digit strings have only two digits touching, 12.3% have three digits touching, and 3.1% have more than three digits touching. We present a multi-experts approach to recognize touching digit pairs (TDP) and touching digit triples (TDT). We combine holistic and traditional segmentation methods. 25,686 TDP training samples and 2778 TDP testing samples collected from USPS mail are used in our experiment. Holistic method outperforms the traditional segmentation based methods. The multi-experts combination has the best performance, a correct rate of 91.1% on TDP.