Methods, Report and Survey for the Comparison of Diverse Isolated Character Recognition Results on the UNIPEN Database

Authors:
Eugene H. Ratzlaff
Affiliations:
-
Venue:
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Year:
2003

Citing 10
Cited 10

Modelizing character allographs in omni-scriptor frame: a new non-supervised clustering algorithm

Pattern Recognition Letters
Cursive Character Detection Using Incremental Learning

ICDAR '99 Proceedings of the Fifth International Conference on Document Analysis and Recognition
On-Line Handwriting Recognition with Support Vector Machines " A Kernel Approach

IWFHR '02 Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition (IWFHR'02)
Genetical Engineering of Handwriting Representations

IWFHR '02 Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition (IWFHR'02)
A Scanning n-tuple Classifier for Online Recognition of Handwritten Digits

ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
Character Recognition Experiments Using Unipen Data

ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
Strategies for Combining On-line and Off-line Information in an On-line Handwriting Recognition System

ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
Measuring HMM Similarity with the Bayes Probability of Error and its Application to Online Handwriting Recognition

ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
A New Fuzzy Geometric Representation for On-Line Isolated Character Recognition

ICPR '98 Proceedings of the 14th International Conference on Pattern Recognition-Volume 2 - Volume 2
Model-Based On-Line Handwritten Digit Recognition

ICPR '98 Proceedings of the 14th International Conference on Pattern Recognition-Volume 2 - Volume 2

Online Character Recognition Based on Elastic Matching and Quadratic Discrimination

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Fast Convolutional OCR with the Scanning N-Tuple Grid

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Online Handwritten Shape Recognition Using Segmental Hidden Markov Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Directional features in online handwriting recognition

Pattern Recognition
On-line handwritten digit recognition based on trajectory and velocity modeling

Pattern Recognition Letters
A large margin approach for writer independent online handwriting classification

Pattern Recognition Letters
Computer Assisted Transcription of Text Images and Multimodal Interaction

MLMI '08 Proceedings of the 5th international workshop on Machine Learning for Multimodal Interaction
Retrieval of online handwriting by synthesis and matching

Pattern Recognition
Multimodal interactive transcription of text images

Pattern Recognition
Global feature for online character recognition

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

A framework of data organization methods and correspondingrecognition results for UNIPEN databases ispresented to enable the comparison of recognition resultsfrom different isolated character recognizers. A reproduciblemethod for splitting the Train-R01/V07 data intoan array of multi-writer and omni-writer training andtesting pairs is proposed. Recognition results and uncertaintiesare provided for each pair, as well as results forthe DevTest-R01/V02 character subsets, using an onlinescanning n-tuple recognizer. Several other publishedresults are surveyed within this context. In sum, this reportprovides the reader multiple points of reference usefulfor comparing a number of published recognitionresults and a proposed framework that similarly allowsprivate evaluation of unpublished recognition results.