Precise Candidate Selection for Large Character Set Recognition by Confidence Evaluation

Authors:
Cheng-Lin Liu;Masaki Nakagawa
Affiliations:
Central Research Lab, Tokyo, Japan;Tokyo Univ. of Agriculture and Technology, Tokyo, Japan
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2000

Citing 10
Cited 12

A nonlinear normalization method for handprinted Kanji character recognition—line density equalization

Pattern Recognition
On speeding candidate selection in handprinted Chinese character recognition

Pattern Recognition
A Method of Combining Multiple Experts for the Recognition of Unconstrained Handwritten Numerals

IEEE Transactions on Pattern Analysis and Machine Intelligence
Pattern classification: a unified view of statistical and neural approaches

Pattern classification: a unified view of statistical and neural approaches
The Optimum Class-Selective Rejection Rule

IEEE Transactions on Pattern Analysis and Machine Intelligence
Offline Recognition of Chinese Handwriting by Multifeature and Multilevel Classification

IEEE Transactions on Pattern Analysis and Machine Intelligence
Adaptive confidence transform based classifier combination for Chinese character recognition

Pattern Recognition Letters
A Methodology for Mapping Scores to Probabilities

IEEE Transactions on Pattern Analysis and Machine Intelligence
High Accuracy Handwritten Chinese Character Recognition by Improved Feature Matching Method

ICDAR '97 Proceedings of the 4th International Conference on Document Analysis and Recognition
On-Line Handwiting Recognition with Constrained N-Best Decoding

ICPR '96 Proceedings of the International Conference on Pattern Recognition (ICPR '96) Volume III-Volume 7276 - Volume 7276

Lexicon-Driven Segmentation and Recognition of Handwritten Character Strings for Japanese Address Reading

IEEE Transactions on Pattern Analysis and Machine Intelligence
Accelerating Large Character Set Recognition using Pivots

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Non-similar candidate removal method for off-line handwritten Korean character recognition

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Rejection Algorithm for Mis-segmented Characters In Multilingual Document Recognition

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Online Recognition of Chinese Characters: The State-of-the-Art

IEEE Transactions on Pattern Analysis and Machine Intelligence
Building Compact Classifier for Large Character Set Recognition Using Discriminative Feature Extraction

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Segmentation-driven offline handwritten Chinese and Arabic script recognition

SACH'06 Proceedings of the 2006 conference on Arabic and Chinese handwriting recognition
A novel multistage classification strategy for handwriting chinese character recognition using local linear discriminant analysis

ICONIP'06 Proceedings of the 13th international conference on Neural Information Processing - Volume Part II
Context driven chinese string segmentation and recognition

SSPR'06/SPR'06 Proceedings of the 2006 joint IAPR international conference on Structural, Syntactic, and Statistical Pattern Recognition
Application of bi-gram driven chinese handwritten character segmentation for an address reading system

DAS'06 Proceedings of the 7th international conference on Document Analysis Systems
A robust method for coarse classifier construction from a large number of basic recognizers for on-line handwritten Chinese/Japanese character recognition

Pattern Recognition
Character confidence based on N-best list for keyword spotting in online Chinese handwritten documents

Pattern Recognition

Quantified Score

Hi-index	0.14

Visualization

Abstract

This paper proposes a precise candidate selection method for large character set recognition by confidence evaluation of distance-based classifiers. The proposed method is applicable to a wide variety of distance metrics and experiments on Euclidean distance and city block distance have achieved promising results. By confidence evaluation, the distribution of distances is analyzed to derive the probabilities of classes in two steps: output probability evaluation and input probability inference. Using the input probabilities as confidences, several selection rules have been tested and the rule that selects the classes with high confidence ratio to the first rank class produced best results. The experiments were implemented on the ETL9B database and the results show that the proposed method selects about one-fourth as many candidates with accuracy preserved compared to the conventional method that selects a fixed number of candidates.