Filters








10,559 Hits in 4.7 sec

Large-Scale Printed Chinese Character Recognition for ID Cards Using Deep Learning and Few Samples Transfer Learning

Yi-Quan Li, Hao-Sen Chang, Daw-Tung Lin
2022 Applied Sciences  
In this study, we developed an automatic OCR system designed to identify up to 13,070 large-scale printed Chinese characters by using deep learning neural networks and fine-tuning techniques.  ...  With the ongoing advances in deep learning and optical character recognition (OCR) technologies, neural networks designed to perform large-scale classification play an essential role in facilitating OCR  ...  Methodology The main objective of this study was the construction of an automatic OCR system designed to identify up to 13,070 large-scale printed Chinese characters using deep learning neural networks  ... 
doi:10.3390/app12020907 fatcat:xzn6warh4raffkfhxeppn7n3im

SwiftPost — A vision-based fast postal envelope identification system

Xue Gao, Lianwen Jin
2009 2009 IEEE International Conference on Systems, Man and Cybernetics  
This paper describes a method of real-time processing of machine-printed Chinese postage envelopes in an automated postal system.  ...  The character recognition rate of postal addresses is 98.72%.  ...  To evaluate the performance of our system and construct a recognition model in the training phase, a database of machine-printed Chinese characters and a live mail image database were constructed.  ... 
doi:10.1109/icsmc.2009.5346224 dblp:conf/smc/GaoJ09 fatcat:ty7vbre32rc7jja43mn7a6zyl4

SPEEDING UP CHINESE CHARACTER RECOGNITION IN AN AUTOMATIC DOCUMENT READING SYSTEM

YI-HONG TSENG, CHI-CHANG KUO, HSI-JIAN LEE
1998 Pattern Recognition  
The system then recognizes all printed Chinese characters between pairs of punctuation marks. The results are then spoken aloud by a speech-synthesis system.  ...  In the automatic document reading system, characters and punctuation marks are first extracted from printed document images and sorted according to their positions and the document orientation.  ...  An automatic reading system for printed Chinese documents has been successfully implemented.  ... 
doi:10.1016/s0031-3203(98)00043-0 fatcat:bdrwqmwkjrd25otrbqbcnu7zka

human-machine interface [chapter]

Martin H. Weik
2000 Computer Science and Communications Dictionary  
categorization, information retrieval, character recognition, and face detection and recognition.  ...  From 1991 to 2005, China's High Technology Research and Development Program (HTRDP) sponsored a series of technology evaluations on Chinese information processing and intelligent human-machine interface  ...  0.6840 0.4800 0.7040 Table 67 Chinese 67 character recognition evaluations supported by Chinese 863 Program 1991 1992 1994 1995 1997 1998 2003 Printed character recognition √ √ √ √ √  ... 
doi:10.1007/1-4020-0613-6_8515 fatcat:tpuxzafzlzantksjlax6e2unai

HTRDP evaluations on Chinese information processing and intelligent human-machine interface

Qun Liu, Xiangdong Wang, Hong Liu, Le Sun, Sheng Tang, Deyi Xiong, Hongxu Hou, Yuanhua Lv, Wenbo Li, Shouxun Lin, Yueliang Qian
2007 Frontiers of Computer Science in China  
categorization, information retrieval, character recognition, and face detection and recognition.  ...  From 1991 to 2005, China's High Technology Research and Development Program (HTRDP) sponsored a series of technology evaluations on Chinese information processing and intelligent human-machine interface  ...  0.6840 0.4800 0.7040 Table 67 Chinese 67 character recognition evaluations supported by Chinese 863 Program 1991 1992 1994 1995 1997 1998 2003 Printed character recognition √ √ √ √ √  ... 
doi:10.1007/s11704-007-0007-2 fatcat:wlnyx6n65ze7dkrr3i7wowtwqq

Different approach to designing neural networks for similar handwritten Chinese character recognition

Devil H. Yip, William W. Yu, Bruno Bosacchi, David B. Fogel, James C. Bezdek
1998 Applications and Science of Neural Networks, Fuzzy Systems, and Evolutionary Computation  
The input images of Chinese characters are normally preprocessed using different image processing techniques before the main classification in the handwritten Chinese character recognition.  ...  The authors proposed a different approach to the system philosophy of solving the handwritten Chinese character recognition problem where no preprocessing is necessary.  ...  The handwritten Chinese characters are much more difficult than the automatic recognition of the printed Chinese characters because of the different written styles.  ... 
doi:10.1117/12.326723 fatcat:ut7koe6i4rgfxi4dwbsxqsarzi

A Review on Optical Character Recognition Techniques

Hiral Modi, M. C.
2017 International Journal of Computer Applications  
Various techniques are determined that have been proposed to realize the center of character recognition in an optical character recognition system.  ...  This paper presents detailed review in the field of Optical Character Recognition.  ...  The grading system is used to evaluate the performance of printed text using various quality measures.  ... 
doi:10.5120/ijca2017913061 fatcat:dnhnbiv4nzhrpcobkvrkijooiy

Script Recognition—A Review

D Ghosh, T Dube, A P Shivaprasad
2010 IEEE Transactions on Pattern Analysis and Machine Intelligence  
In a multi-script, multilingual environment, it is essential to know the script used in writing a document before an appropriate character recognition and document analysis algorithm can be chosen.  ...  In view of this, several methods for automatic script identification have been developed so far. They mainly belong to two broad categories -structure-based and visual appearance-based techniques.  ...  Later, they proposed an automatic system for identification of Latin, Chinese, Arabic, Devnagari and Bengali textlines in printed documents [29] .  ... 
doi:10.1109/tpami.2010.30 pmid:20975114 fatcat:3ysyxmflovej5f7gy2z7ogffou

Experimental evaluation of Arabic OCR systems

Mansoor Alghamdi, William Teahan
2017 PSU Research Review  
Design/methodology/approach -This paper describes an experiment to automatically evaluate four well-known Arabic OCR systems using a set of performance metrics.  ...  Purpose -The aim of this paper is to experimentally evaluate the effectiveness of the state-of-the-art printed Arabic text recognition systems to determine open areas for future improvements.  ...  evaluated Arabic OCR systems in printed Arabic text recognition.  ... 
doi:10.1108/prr-05-2017-0026 fatcat:cebs257pgncvbnmfgwz3xexdyy

HANDWRITTEN AMHARIC CHARACTER RECOGNITION SYSTEM USING CONVOLUTIONAL NEURAL NETWORKS

Fetulhak Abdurahman
2019 E-journal of New World Sciences Academy  
Handwritten Amharic character recognition system becomes a challenging task due to inconsistency of a writer, variability in writing styles of different writers, relatively large number of characters of  ...  In order to recognize handwritten Amharic character a novel method based on deep neural networks is used which has recently shown exceptional performance in various pattern recognition and machine learning  ...  The performance of our recognition system was evaluated by using the collected dataset discussed earlier.  ... 
doi:10.12739/nwsa.2019.14.2.1a0433 fatcat:27puhli73zh2fpfd2c2ttvwi3y

Automatic detection and translation of text from natural scenes

Jie Yang, Xilin Chen, Jing Zhang, Ying Zhang, Alex Waibel
2002 IEEE International Conference on Acoustics Speech and Signal Processing  
This system is capable of capturing images, automatically detecting and recognizing text, and translating the text into English.  ...  We extend example based machine translation technology for sign translation and present a prototype system for Chinese sign translation.  ...  We would also like to thank other members in the Interactive Systems Labs for their inspiring discussions and support. This research is partially supported by DARPA under TIDES project.  ... 
doi:10.1109/icassp.2002.5745049 dblp:conf/icassp/YangCZZW02 fatcat:a6ief2hyqbaghi4vhtsn6jo3wy

Automatic detection and translation of text from natural scenes

Jie Yang, Xilin Chen, Jing Zhang, Ying Zhang, Waibel
2002 IEEE International Conference on Acoustics Speech and Signal Processing  
This system is capable of capturing images, automatically detecting and recognizing text, and translating the text into English.  ...  We extend example based machine translation technology for sign translation and present a prototype system for Chinese sign translation.  ...  We would also like to thank other members in the Interactive Systems Labs for their inspiring discussions and support. This research is partially supported by DARPA under TIDES project.  ... 
doi:10.1109/icassp.2002.1006190 fatcat:ihnz7tdx3bcvtmyglg4rz4qizy

Separating Chinese Character from Noisy Background Using GAN

Bin Huang, Jiaqi Lin, Jinming Liu, Jie Chen, Jiemin Zhang, Yendo Hu, Erkang Chen, Jingwen Yan, Philippe Fournier-Viger
2021 Wireless Communications and Mobile Computing  
The complex structure of Chinese characters makes it difficult to obtain the goal because of easy loss of fine details and overall structure in reconstructed characters.  ...  In particular, our methods achieve better results in terms of Intersection over Union (IoU) and optical character recognition (OCR) accuracy.  ...  In the results, we show the visual effect of separating the handwritten part and the printed part, respectively, of four different common Chinese fonts.  ... 
doi:10.1155/2021/9922017 fatcat:gx4ofxf33rg2lgcun2bdlvmg3m

A Deep Learning Technology based OCR Framework for Recognition Handwritten Expression and Text

Tuanji Gong, Xuanxia Yao
2021 Converter  
However it still faces many challenging problems in handwritten text recognition and mathematical expression recognition, such as handwritten Chinese recognition, mixture of printed and handwritten Chinese  ...  The second component consists of text recognition and ME recognition models. The final component merges multiple outputs of the second stage into a whole text.  ...  DCN performance and our framework performance. 4.4.1 Experiment I In OCR system, the precision is the important evaluation metric.  ... 
doi:10.17762/converter.259 fatcat:4j6jbjanvjd5ne5c32me5nfm2e

A Tool for Ground-Truthing Text Lines and Characters in Off-Line Handwritten Chinese Documents

Fei Yin, Qiu-feng Wang, Cheng-lin Liu
2009 2009 10th International Conference on Document Analysis and Recognition  
We have validated the effectiveness of this tool and have used it for annotating a large number of handwritten Chinese documents. 978-0-7695-3725-2/09 $25.00  ...  The alignment process is formulated as an optimization problem involving candidate character segmentation and recognition.  ...  Acknowledgements This work is supported by the National Natural Science Foundation of China (NSFC) under grants no.60775004 and no.60825301.  ... 
doi:10.1109/icdar.2009.93 dblp:conf/icdar/YinWL09 fatcat:mcjdxnspaze53nhuw4kaeovcpa
« Previous Showing results 1 — 15 out of 10,559 results