135,329 Hits in 3.7 sec

A Persian Ocr System Using Morphological Operators

M. Salmani Jelodar, M.J. Fadaeieslam, N. Mozayani, M. Fazeli
2007 Zenodo  
Optical Character Recognition (OCR) is a very old and of great interest in pattern recognition field. In this paper we introduce a very powerful approach to recognize Persian text.  ...  Persian characters used as the script for languages such as Farsi, Arabic, and Urdu, are among those characters developing a recognition system for them have not received so much attention [1] [8] [12  ...  proposed for other classes of characters to Persian characters.  ... 
doi:10.5281/zenodo.1331556 fatcat:ckaupdituje4lcfo2mbad5y7q4

Handwritten character recognition using some (anti)-diagonal structural features [article]

José Manuel Casas, Nick Inassaridze, Manuel Ladra, Susana Ladra
2018 arXiv   pre-print
In this paper, we present a methodology for off-line handwritten character recognition.  ...  Namely, the recognition system was trained using 1000 samples and 64 classes for each symbol and was tested on 500 samples for each symbol.  ...  [11] also developed a structural feature set for recognition of printed text.  ... 
arXiv:1707.08951v3 fatcat:5zimtxfdsnghbj6m3j26jcds6i

Implementation of ANPR System based on Image Extraction and Segmentation

2015 International Journal of Science and Research (IJSR)  
Keywords: Automatic parking system, autocorrelation, image processing, mean square error, plate number recognition structural similarity index. 1.  ...  Proposed Algorithm for Character combine the close objects, by using structure element value equals to 8 pixels in 0 degree (0°).  ... 
doi:10.21275/v4i11.sub159026 fatcat:rmskbjzow5be7fcz3lcapihv6i

Substructure shape analysis for Kanji character recognition [chapter]

Jairo Rocha, Hiromichi Fujisawa
1996 Lecture Notes in Computer Science  
A method towards analytical recognition of Chinese characters is described.  ...  The algorithm performs skeleton extraction, skeleton grouping, indexing of structural features on a previously generated look-up table, structural verification of hypothesis using model graphs, and geometrical  ...  Strategies for recognition of individual characters report above 95% on printed characters [5] , and from 85% to 95% on hand-printed characters [7] .  ... 
doi:10.1007/3-540-61577-6_37 fatcat:lxo3ai5uwbebrhguhlxggzezlu

A Lattice-Based Method for Keyword Spotting in Online Chinese Handwriting

Heng Zhang, Cheng-Lin Liu
2011 2011 International Conference on Document Analysis and Recognition  
Using a character string recognition algorithm, the lattice-based method generates a candidate lattice of N-best list.  ...  This paper proposes a lattice-based method for keyword spotting in online Chinese handwriting to improve the trade-off between accuracy and speed, and to overcome the out-of-vocabulary (OOV) problem of  ...  For large database retrieval, it is necessary to build an index containing the candidate recognition results.  ... 
doi:10.1109/icdar.2011.215 dblp:conf/icdar/ZhangL11 fatcat:d4t4juwdnbel5knkiejk7nm2au

A sentence analysis method for a Japanese book reading machine for the blind

Yutaka Ohyama, Toshikazu Fukushima, Tomoki Shutoh, Masamichi Shutoh
1986 Proceedings of the 24th annual meeting on Association for Computational Linguistics -  
Using several recognized character candidates is more efficient than only using first ranked characters as the input for sentence analysis.  ...  This method is designed to allow for several candidates in case of ambiguous characters. Each sentence is analyzed to compose a data structure by defining the relationship between words and phrases.  ...  Hanaki for his constant encouragement and effective advice. The authors would also like to express their appreciation to Ms. A. Ohtake for her enthusiasm and cooperation throughout the research.  ... 
doi:10.3115/981131.981155 dblp:conf/acl/OhyamaFSS86 fatcat:ia32kh2mmbeerpuvisrbtvrjfm

Structuring lecture videos for distance learning applications

Chong-Wah Ngo, Feng Wang, Ting-Chuen Pong
2003 Fifth International Symposium on Multimedia Software Engineering, 2003. Proceedings.  
This paper presents an automatic and novel approach in structuring and indexing lecture videos for distance learning applications.  ...  By structuring video content, we can support both topic indexing and semantic querying of multimedia documents.  ...  Figure 1 presents our proposed framework for structuring lecture video content for effective indexing.  ... 
doi:10.1109/mmse.2003.1254444 dblp:conf/ismse/NgoWP03 fatcat:y3upus4yzbforkdc7ywf5jyh6y

Building a Compact On-Line MRF Recognizer for Large Character Set Using Structured Dictionary Representation and Vector Quantization Technique

Bilan Zhu, Masaki Nakagawa
2012 2012 International Conference on Frontiers in Handwriting Recognition  
This paper describes a method for building a compact on-line Markov random field (MRF) recognizer for large handwritten Japanese character set using structured dictionary representation and vector quantization  ...  By sharing a common parameter set for each group, the dictionary of the MRF recognizer can be greatly compressed without recognition accuracy loss.  ...  We can also search similar radicals from the registered radical dictionary then select a similar radical index to register it. Fig. 2 shows the split character models for characters [ ] and [ ].  ... 
doi:10.1109/icfhr.2012.188 dblp:conf/icfhr/ZhuN12 fatcat:px4pzoujjvg6posqofv2vtkx4i

A Survey on Document Image Analysis and Retrieval System

Umesh D. Dixit, Shirdhonkar M.S
2015 International Journal on Cybernetics & Informatics  
Signature, Logo and Layout of the documents present convincing evidence and provide an important form of indexing for effective document image retrieval in a variety of applications.  ...  This paper describes methods and techniques developed for document image analysis and retrieval by researchers.  ...  Traditional indexing: This method of indexing includes keyword spotting and document image indexing with Optical Character Recognition (OCR).  ... 
doi:10.5121/ijci.2015.4225 fatcat:qy5zdi2mmfgqhjoa5qreq3rr7q

Off-Line Hand Written Thai Character Recognition Using Ant-Miner Algorithm

P. Phokharatkul, K. Sankhuangaw, S. Somkuarnpanit, S. Phaiboon, C. Kimpan
2007 Zenodo  
Much research into handwritten Thai character recognition have been proposed, such as comparing heads of characters, Fuzzy logic and structure trees, etc.  ...  For this experiment, the Ant-miner algorithm is adapted, with a small change to increase the recognition rate.  ...  The disadvantage of the structure tree is wrong character recognition: when characters are written incorrectly.  ... 
doi:10.5281/zenodo.1333202 fatcat:wyjn4pawwfee3m4adlaouxgex4


2006 International journal of pattern recognition and artificial intelligence  
Then, a multiscale indexing paradigm for broadcast news retrieval was exploited to alleviate the problems caused by the speech recognition errors and the flexible wording structure of the Chinese language  ...  First, several unsupervised and data-driven approaches for broadcast news transcription were proposed to improve the speech recognition accuracy and efficiency.  ...  character-level and word-level indexing features.  ... 
doi:10.1142/s0218001406004521 fatcat:uhwa5rufhrcebm6635s7h7bfyq

From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network [article]

Yuxin Wang, Hongtao Xie, Shancheng Fang, Jing Wang, Shenggao Zhu, Yongdong Zhang
2021 arXiv   pre-print
Such operation guides the vision model to use not only the visual texture of characters, but also the linguistic information in visual context for recognition when the visual cues are confused (e.g. occlusion  ...  Specially, we introduce the text recognition of character-wise occluded feature maps in the training stage.  ...  Acknowledgments This work is supported by the National Nature Science Foundation of China (62121002, 62022076, U1936210), the Fundamental Research Funds for the Central Universities under Grant WK3480000011  ... 
arXiv:2108.09661v1 fatcat:qu5y2terk5bencrvfxdmf6izrm

Seal Detection and Recognition: An Approach for Document Indexing

Partha Pratim Roy, Umapada Pal, Josep Lladós
2009 2009 10th International Conference on Document Analysis and Recognition  
The seal model to which we get maximum hypothesis is selected for the recognition of the input seal.  ...  Given an input seal, we recognize the individual text characters and compute the code for pair-wise character based on the relative spatial organization.  ...  The seal model to which we get maximum hypothesis is selected for the recognition of the input seal. The rest of the paper is structured as follows.  ... 
doi:10.1109/icdar.2009.128 dblp:conf/icdar/RoyPL09 fatcat:sc4wosafujb5xbnwnn5jvrgpue

Handwritten Character Recognition Using Competitive Neural Trees

Theingi Htike, Yadana Thein
2013 International Journal of Engineering and Technology  
This paper discusses a global search method for the CNeT, which is utilized for training. Index Terms-Myanmar handwritten characters, CNeT, global search method.  ...  The goals of Myanmar handwritten character recognition are to obtain better recognition accuracy rate and robust in geometric character shapes of different writing styles.  ...  In Myanmar character recognition fields, competitive neural trees had not been applied for recognition.  ... 
doi:10.7763/ijet.2013.v5.574 fatcat:jkjwcosgobfzhdj4zs4qiayim4

A Partial String Matching Approach for Named Entity Recognition in Unstructured Bengali Data

Nabil Ibtehaz, Abdus Satter
2018 International Journal of Modern Education and Computer Science  
The texts experimented on was both structured and unstructured, and our algorithm managed to succeed in both the cases.  ...  This has been an active research topic for more than two decades and significant progresses have been made.  ...  For example, let us assume that an entity starts from index 15, surely we can skip the first 15 characters and then start matching.  ... 
doi:10.5815/ijmecs.2018.01.04 fatcat:oboura3kj5e4navtfzcjdkoqh4
« Previous Showing results 1 — 15 out of 135,329 results