Hybrid model for Chinese character recognition based on Tesseract-OCR

被引：5

作者：

Wang, Bo ^{[1
]}

Ma, Yi-Wei ^{[2
,3
]}

Hu, Hong-Tao ^{[1
]}

机构：

[1] Shanghai Maritime Univ, Logist Engn Collage, Pudong New Area, Shanghai, Peoples R China

[2] Natl Taiwan Univ Sci & Technol, Dept Elect Engn, Taipei, Taiwan

[3] Shanghai Maritime Univ, China Inst FTZ Supply Chain, Pudong New Area, Shanghai, Peoples R China

来源：

INTERNATIONAL JOURNAL OF INTERNET PROTOCOL TECHNOLOGY | 2020年 / 13卷 / 02期

关键词：

hybrid model; image processing; Chinese character; optical character recognition; OCR; phrase processing; K-nearest neighbour; KNN; Tesseract-OCR; single char recognition;

D O I：

10.1504/IJIPT.2020.106316

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Optical character recognition (OCR) is an important way to input information into a computer. And text information can be extracted by OCR from an image. Currently, the accuracy rate of Chinese OCR can also be improved. This study proposes a hybrid Chinese character recognition model based on the characteristics of Chinese. Before the OCR engine works, the model first filters the interference information in the image. Then the model adjusts the aspect ratio of the character. After an image is identified by OCR, single character recognition result is obtained. Then the result is checked and corrected on the phrase level. The experimental results show that the hybrid model improves the accuracy rate of Chinese OCR. Through image processing, the correct rate of recognition by the Tesseract-OCR engine is increased by about 12%, and the natural language processing improves the accuracy of the recognition result by about 5%.

引用

页码：102 / 108

页数：7

共 50 条

[21] Applying SIMD to optical character recognition (OCR)
Yu, Guan
Gauthier, Lafruit
Stahl, Richard
Corporaal, Henk
Schelkens, Peter
[J]. OPTICAL AND DIGITAL IMAGE PROCESSING, 2008, 7000
[22] How to Improve Optical Character Recognition of Historical Finnish Newspapers Using Open Source Tesseract OCR Engine - Final Notes on Development and Evaluation
Koistinen, Mika
Kettunen, Kimmo
Kervinen, Jukka
[J]. HUMAN LANGUAGE TECHNOLOGY. CHALLENGES FOR COMPUTER SCIENCE AND LINGUISTICS, LTC 2017, 2020, 12598 : 17 - 30
[23] A new hybrid methodology for intelligent Chinese character recognition
Al-Dabass, D
Evans, D
Ren, ML
[J]. HIS'04: Fourth International Conference on Hybrid Intelligent Systems, Proceedings, 2005, : 104 - 109
[24] A hybrid post-processing system for offline handwritten Chinese character recognition based on a statistical language model
Xu, RF
Yeung, DS
Sh, DM
[J]. INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2005, 19 (03) : 415 - 428
[25] Offline handwritten Chinese character recognition based on DBN fusion model
Liu, Lu
Sun, Weiwei
Ding, Bo
[J]. 2016 IEEE INTERNATIONAL CONFERENCE ON INFORMATION AND AUTOMATION (ICIA), 2016, : 1807 - 1811
[26] When Tesseract Does It Alone Optical Character Recognition of Medieval Texts
Novotny, Vit
[J]. RECENT ADVANCES IN SLAVONIC NATURAL LANGUAGE PROCESSING (RASLAN 2020), 2020, : 3 - 12
[27] Optical Character Recognition (OCR) Performance in Server-based Mobile Environment
Mantoro, Teddy
Sobri, Abdul Muis
Usino, Wendi
[J]. 2013 International Conference on Advanced Computer Science Applications and Technologies (ACSAT), 2014, : 423 - 428
[28] Lexicon Reduction for Urdu/Arabic Script Based Character Recognition: A Multilingual OCR
Naz, Saeeda
Umar, Arif Iqbal
Razzak, Muhammad Imran
[J]. MEHRAN UNIVERSITY RESEARCH JOURNAL OF ENGINEERING AND TECHNOLOGY, 2016, 35 (02) : 209 - 216
[29] Shape decomposition-based handwritten compound character recognition for Bangla OCR
Pramanik, Rahul
Bag, Soumen
[J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2018, 50 : 123 - 134
[30] Hybrid GMDH Model for Handwritten Character Recognition
Dhawan, Parag
Dongre, Snehlata
Tidke, D. J.
[J]. 2013 IEEE INTERNATIONAL MULTI CONFERENCE ON AUTOMATION, COMPUTING, COMMUNICATION, CONTROL AND COMPRESSED SENSING (IMAC4S), 2013, : 698 - 703

← 1 2 3 4 5 →