Non-uniformly sampled feature extraction method for kanji character recognition

This paper proposes a new feature extraction method for off-line recognition of Myanmar printed documents. One of the most important factors to achieve high recognition performance in Optical Character Recognition (OCR) system is the selection of the feature extraction methods. Different types of existing OCR systems used various feature extraction methods because of the diversity of the scripts’ natures. One major contribution of the work in this paper is the design of logically rigorous coding based features. To show the effectiveness of the proposed method, this paper assumed the documents are successfully segmented into characters and extracted features from these isolated Myanmar characters. These features are extracted using structural analysis of the Myanmar scripts. The experimental results have been carried out using the Support Vector Machine (SVM) classifier and compare the pervious proposed feature extraction method.

Download Full-text

Robust Character Recognition Using Adaptive Feature Extraction Method

IEICE Transactions on Information and Systems ◽

10.1587/transinf.e93.d.125 ◽

2010 ◽

Vol E93-D (1) ◽

pp. 125-133

Author(s):

Minoru MORI ◽

Minako SAWAKI ◽

Junji YAMATO

Keyword(s):

Feature Extraction ◽

Character Recognition ◽

Extraction Method ◽

Feature Extraction Method ◽

Adaptive Feature Extraction

Download Full-text

A dictionary learning and KPCA-based feature extraction method for off-line handwritten Tibetan character recognition

Optik ◽

10.1016/j.ijleo.2015.07.144 ◽

2015 ◽

Vol 126 (23) ◽

pp. 3795-3800 ◽

Cited By ~ 3

Author(s):

He-ming Huang ◽

Fei-peng Da

Keyword(s):

Feature Extraction ◽

Dictionary Learning ◽

Character Recognition ◽

Extraction Method ◽

Feature Extraction Method

Download Full-text

Handwritten Character Recognition of MODI Script using Convolutional Neural Network Based Feature Extraction Method and Support Vector Machine Classifier

2020 IEEE 5th International Conference on Signal and Image Processing (ICSIP) ◽

10.1109/icsip49896.2020.9339435 ◽

2020 ◽

Author(s):

Solley Joseph ◽

Jossy George

Keyword(s):

Neural Network ◽

Support Vector Machine ◽

Feature Extraction ◽

Convolutional Neural Network ◽

Character Recognition ◽

Extraction Method ◽

Support Vector Machine Classifier ◽

Support Vector ◽

Handwritten Character Recognition ◽

Feature Extraction Method

Download Full-text

Neural-Based Hit-Count Feature Extraction Method for Telugu Script Optical Character Recognition

Lecture Notes in Networks and Systems - Innovations in Electronics and Communication Engineering ◽

10.1007/978-981-10-8204-7_48 ◽

2018 ◽

pp. 479-486 ◽

Cited By ~ 1

Author(s):

M. Swamy Das ◽

Kovvur Ram Mohan Rao ◽

P. Balaji

Keyword(s):

Feature Extraction ◽

Character Recognition ◽

Optical Character Recognition ◽

Extraction Method ◽

Feature Extraction Method ◽

Optical Character

Download Full-text

A Feature Extraction Method for Cursive Character Recognition Using Higher-Order Singular Value Decomposition

2014 14th International Conference on Frontiers in Handwriting Recognition ◽

10.1109/icfhr.2014.92 ◽

2014 ◽

Cited By ~ 1

Author(s):

Mohammad Reza Ameri ◽

Medhi Haji ◽

Andreas Fischer ◽

Dominique Ponson ◽

Tien D. Bui

Keyword(s):

Feature Extraction ◽

Singular Value Decomposition ◽

Character Recognition ◽

Extraction Method ◽

Higher Order ◽

Singular Value ◽

Feature Extraction Method ◽

Value Decomposition

Download Full-text

A Novel Blocked Winner Sequence Feature Extraction Method Based SOM For Large Set Chinese Character Recognition

Proceedings of the 2017 2nd Joint International Information Technology, Mechanical and Electronic Engineering Conference (JIMEC 2017) ◽

10.2991/jimec-17.2017.4 ◽

2017 ◽

Author(s):

Lei Wang ◽

Wenjuan Zhang ◽

Lianming Wang

Keyword(s):

Feature Extraction ◽

Character Recognition ◽

Extraction Method ◽

Chinese Character ◽

Large Set ◽

Sequence Feature ◽

Feature Extraction Method ◽

Chinese Character Recognition

Download Full-text

Research on Feature Extraction Method for Handwritten Chinese Character Recognition Based on Supervised Independent Component Analysis

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.774-776.1636 ◽

2013 ◽

Vol 774-776 ◽

pp. 1636-1641

Author(s):

Ze Min Liu ◽

Zhi Guo He ◽

Yu Dong Cao

Keyword(s):

Feature Extraction ◽

Independent Component Analysis ◽

Character Recognition ◽

Extraction Method ◽

Chinese Character ◽

Complex Structure ◽

Recognition Rate ◽

Component Analysis ◽

Independent Component ◽

Feature Extraction Method

Feature extraction is very difficult for handwritten Chinese character because of large Chinese characters set, complex structure and very large shape variations. The recognition rate by currently used feature extraction methods is far from the requirements of the people. For this problem, a new supervised independent component analysis (SICA) algorithm based on J-divergence entropy is proposed for feature extraction, which can measure the difference between different categories. The scheme takes full advantage of good extraction local features capability and powerful capability to handle data with non-Gaussian distribution by ICA, and the extracted feature component and classification can be tightly combined. The experiments show that the feature extraction method based on SICA is superior to that of gradient-based and that of ICA.

Download Full-text