Journal ArticleDOI
Recognition of handwritten Chinese characters by critical region analysis
Ka-Cheong Leung,C. H. Leung +1 more
TLDR
A ''critical region analysis'' technique which highlights the critical regions that distinguish one character from another similar character is proposed and a record high recognition rate of 99.53% on the ETL-9B database is obtained.About:
This article is published in Pattern Recognition.The article was published on 2010-03-01. It has received 49 citations till now. The article focuses on the topics: Intelligent word recognition & Pattern recognition (psychology).read more
Citations
More filters
Journal ArticleDOI
Online and offline handwritten Chinese character recognition: Benchmarking on new databases
TL;DR: In this paper, state-of-the-art methods were evaluated on the isolated character datasets OLHWDB1.0 and HWDB-1.1 for Chinese handwriting recognition.
Journal ArticleDOI
Handwritten character recognition using wavelet energy and extreme learning machine
TL;DR: An extremely fast leaning algorithm called ELM for single hidden layer feed forward networks (SLFN), which randomly chooses the input weights and analytically determines the output weights of SLFN, which learns much faster than traditional popular learning algorithms for feed forward neural networks.
Proceedings ArticleDOI
A Semi-supervised Ensemble Learning Approach for Character Labeling with Minimal Human Effort
TL;DR: An efficient and low-cost semi-automatic labeling system for character datasets that proves that labeling only less than 0.5% of the training data is sufficient to achieve 86.21% recognition rate for a brand new script and 94.81% for the MNIST benchmark dataset.
Journal Article
Two-dimensional Extension of Nonlinear Normalization Method Using Line Density
TL;DR: This article proposed an extended nonlinear normalization method which uses two-dimensional information of the line density, which is more powerful than conventional methods by experiments tested on the handwritten character database ETL-8.
Journal ArticleDOI
Similar handwritten Chinese character recognition by kernel discriminative locality alignment
TL;DR: Experimental results demonstrate that DLA and KDLA are more effective than representative discriminative information extraction algorithms in terms of recognition accuracy.
References
More filters
Journal ArticleDOI
Modified Quadratic Discriminant Functions and the Application to Chinese Character Recognition
TL;DR: Two types of modified quadratic disriminant functions (MQDF1, MQDF2) which are less sensitive to the estimation error of the covariance matrices are proposed.
Journal ArticleDOI
Fast SVM training algorithm with decomposition on very large data sets
TL;DR: The results show that the proposed algorithm has a much better scaling capability than Libsvm, SVM/sup light/, and SVMTorch and the good generalization performances on several large databases have also been achieved.
Journal ArticleDOI
A handwritten character recognition system using directional element feature and asymmetric Mahalanobis distance
TL;DR: A precise system for handwritten Chinese and Japanese character recognition using transformation based on partial inclination detection (TPID) and city block distance with deviation and asymmetric Mahalanobis distance (AMD) are presented.
Journal ArticleDOI
A nonlinear normalization method for handprinted Kanji character recognition—line density equalization
TL;DR: The line density in thespace is homogenized, the efficiency of utilization of the space is increased, and a stable normalization is obtained for partially irregular shape variations.
Related Papers (5)
High accuracy handwritten Chinese character recognition using LDA-based compound distances
Tian-Fu Gao,Cheng-Lin Liu +1 more
Classification of handprinted Chinese characters using nonlinear normalization and correlation methods
J. Tsukumo,H. Tanaka +1 more