Numeral Recognition by Weighting Local Decisions

13 years 9 months ago

Download www.cse.salford.ac.uk

This paper presents a new technique to improve the combination of classification decisions obtained from local analysis of patterns. Specifically, a genetic algorithm is used to determine the optimal weight vector to balance the local decisions in the combination process. The experimental results, carried out in the field of hand-written numeral recognition, demonstrate the effectiveness of the new technique.

Giovanni Dimauro, Sebastiano Impedovo, Raffaele Mo

Real-time Traffic

Classification Decisions | Document Analysis | Hand-written Numeral Recognition | ICDAR 2003 | Optimal Weight Vector |

claim paper

» Local Boosting of Decision Stumps for Regression and Classification Problems

» Decision Fusion for PatchBased Face Recognition

» Correlationbased Feature Selection for Discrete and Numeric Class Machine Learning

» Local Steerable Phase LSP Feature for Face Representation and Recognition

» SVMbased discriminative accumulation scheme for place recognition

» An Adaptive Multiresolution Approach to Fingerprint Recognition

» Multimodal information fusion using the iterative decoding algorithm and its application t...

» Videobased Face Recognition on RealWorld Data

Post Info
More Details (n/a)

Added	04 Jul 2010
Updated	04 Jul 2010
Type	Conference
Year	2003
Where	ICDAR
Authors	Giovanni Dimauro, Sebastiano Impedovo, Raffaele Modugno, Giuseppe Pirlo

Comments (0)

Sciweavers

Numeral Recognition by Weighting Local Decisions

Classification Decisions | Document Analysis | Hand-written Numeral Recognition | ICDAR 2003 | Optimal Weight Vector |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers