106 Hits in 7.7 sec

Recognition of Handwritten Chinese Characters Based on Concept Learning

Liang Xu, Yuxi Wang, Xiuxi Li, Ming Pan
2019 IEEE Access  
This paper is the first to propose a handwritten Chinese character recognition method based on concept learning.  ...  model based on stroke relationship learning using a character stroke extraction method and Bayesian program learning.  ...  CHARACTER CONCEPTUAL MODEL BUILDING AND RECOGNITION METHOD In the concept-learning-based handwritten Chinese character recognition method, the strokes constructing a certain character are extracted using  ... 
doi:10.1109/access.2019.2930799 fatcat:tcohxzjfonfdvkms4bgfwf5hye

Transcript mapping for handwritten Chinese documents by integrating character recognition model and geometric context

Fei Yin, Qiu-Feng Wang, Cheng-Lin Liu
2013 Pattern Recognition  
The tool based on the proposed approach has been practically used for labeling handwritten Chinese documents.  ...  This paper describes an effective recognition-based annotation approach for ground-truthing handwritten Chinese documents.  ...  Acknowledgment The authors would like to thank Tonghua Su for authorizing us to use the HIT-MW database.  ... 
doi:10.1016/j.patcog.2013.03.013 fatcat:loztug3py5g6nosf6r42le7aya

Sensing Analysis of Feature Extraction Types for Handwritten Character Recognition

Jin-feng Gao, Ru-xian Yao, Yu Zhang, Han Lai, Jun-ming Zhang, Ting-Cheng Chang
2020 Sensors and materials  
The experimental results demonstrate that convNet-based feature extraction is more robust and discriminating than LDD and GD, two traditional methods for both handwritten Chinese character recognition  ...  (HCCR) and handwritten Japanese character recognition (HJCR).  ...  As for online recognition, to achieve elastic matching between feature points, dynamic programming (DP) matching was introduced. (7) Thus, its greedy variation, named linear-time flexible matching, is  ... 
doi:10.18494/sam.2020.2688 fatcat:22humk5hsra3vkn7wwo34cabuy

Transcript Mapping for Handwritten Text Lines Using Conditional Random Fields

Xiang-Dong Zhou, Fei Yin, Da-Han Wang, Qiu-Feng Wang, Masaki Nakagawa, Cheng-Lin Liu
2011 2011 International Conference on Document Analysis and Recognition  
This paper presents a conditional random field (CRF) model for aligning online handwritten Chinese/Japanese text lines (character strings) with the corresponding transcripts.  ...  The feature functions characterize the shape and context dependences of characters, including the scores of character recognition and the geometric compatibilities between characters.  ...  ACKNOWLEDGEMENTS This work is supported by the R&D fund for "Development of Pen & Paper-Based User Interaction" of Japan Science and Technology Agency and the National Natural Science Foundation of China  ... 
doi:10.1109/icdar.2011.21 dblp:conf/icdar/ZhouYWWNL11 fatcat:nk3nemv2nvabvotqhjg3sujhoa

A Review on Feature Extraction and Feature Selection for Handwritten Character Recognition

Muhammad 'Arif, Haswadi Hassan, Dewi Nasien, Habibollah Haron
2015 International Journal of Advanced Computer Science and Applications  
The development of handwriting character recognition (HCR) is an interesting area in pattern recognition.  ...  HCR system consists of a number of stages which are preprocessing, feature extraction, classification and followed by the actual recognition.  ...  A handwritten character recognition system consists of a number of preprocessing steps, feature extraction, and classification.  ... 
doi:10.14569/ijacsa.2015.060230 fatcat:kaevu3rdnvehll5de7phax4u7e

A Survey of Elastic Matching Techniques for Handwritten Character Recognition

2005 IEICE transactions on information and systems  
Thus, by using the EM distance as a discriminant function, recognition systems robust to the deformations of handwritten characters can be realized.  ...  This paper presents a survey of elastic matching (EM) techniques employed in handwritten character recognition.  ...  Thus, by using the distance as a discriminant function, recognition systems robust to the deformations of handwritten characters can be realized.  ... 
doi:10.1093/ietisy/e88-d.8.1781 fatcat:zlcm7bwznvgb7bw4jqbi44dzcq

Intelligent Character Recognition System Using Convolutional Neural Network

S. Suriya, Dhivya S, Balaji M
2020 EAI Endorsed Transactions on Cloud Systems  
The proposed approach is capable of recognizing characters in a variety of challenging conditions using the Convolutional Neural Network, where traditional character recognition systems fail, notably in  ...  Intellectual Character Recognition System is an application that uses Convolutional Neural Network (CNN) to recognize the Tamil character dataset accurately developed by HP Labs India.  ...  [13] proposed Size Invariant Handwritten Character Recognition using Single Layer FeedforwardBackpropagation Neural Networks. a recognition system based on neural network that follows offline handwritten  ... 
doi:10.4108/eai.16-10-2020.166659 fatcat:rrv3tyk2ezegdhcwsvuvvkgbrq

Handwritten Hangul recognition using deep convolutional neural networks

In-Jung Kim, Xiaohui Xie
2014 International Journal on Document Analysis and Recognition  
Using our framework, we were able to achieve a recognition rate of 95.96% on SERI95a, and 92.92% on PE92.  ...  In spite of the advances in recognition technology, handwritten Hangul recognition (HHR) remains largely unsolved due to the presence of many confusing characters and excessive cursiveness in Hangul handwritings  ...  However, unlike handwritten Chinese character recognition (HCCR), structural methods outperformed statistical methods in HHR for a long time.  ... 
doi:10.1007/s10032-014-0229-4 fatcat:eaag6iwqz5ainegaw6hkosuhyy

Development of a Robust and Compact On-Line Handwritten Japanese Text Recognizer for Hand-Held Devices

Jinfeng GAO, Bilan ZHU, Masaki NAKAGAWA
2013 IEICE transactions on information and systems  
The paper describes how a robust and compact on-line handwritten Japanese text recognizer was developed by compressing each component of an integrated text recognition system including a SVM classifier  ...  The method is scalable so even systems of less than 11 MB or less than 6 MB still remain 92.80% or 90.02% accuracy, respectively.  ...  Introducton With the development of pen-based or touch-based handheld devices, handwritten text recognition system running on such hand-held devices needs to be developed.  ... 
doi:10.1587/transinf.e96.d.927 fatcat:ynynusm3czd6zkka67q6bku5ay

Mobile App Acceleration via Fine-Grain Offloading to the Cloud

Chit-Kwan Lin, H. T. Kung
2014 USENIX Workshop on Hot Topics in Cloud Computing  
Such workloads, originating from ARM-based mobile devices, are especially well-suited for offloading to emerging ARM-based data centers.  ...  Our prototype gives up to an order-of-magnitude acceleration and 60% longer battery life to the end user of an example handwriting recognition app.  ...  Acknowledgments This material is based upon work supported by the National Science Foundation under Grant No. IIP-1315617.  ... 
dblp:conf/hotcloud/LinK14 fatcat:ewg6lcvmhvhcvdpfqjpif4p6tm

On learning to recognize 3-D objects from examples

S. Edelman
1993 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Based on this model, character recognition is formulated as a constrained optimization problem, and a cooperative relaxation matching algorithm is developed for Chinese character recognition.  ...  We have developed a practical Chinese character recognition system on an IBM-PC with recognition rates from 95 to 99%.  ... 
doi:10.1109/34.236244 fatcat:5hddrh4hqvdfdjstvjdb2q6anu

Fast parallel thinning algorithms: parallel speed and connectivity preservation

R. W. Hall
1989 Communications of the ACM  
Based on this model, character recognition is formulated as a constrained optimization problem, and a cooperative relaxation matching algorithm is developed for Chinese character recognition.  ...  We have developed a practical Chinese character recognition system on an IBM-PC with recognition rates from 95 to 99%.  ... 
doi:10.1145/63238.63248 fatcat:smmmqjpyzfat3o7xnb2sr2vniq

Writing Order Recovery in Complex and Long Static Handwriting

Moises Diaz, Gioele Crispo, Antonio Parziale, Angelo Marcelli, Miguel A. Ferrer
2021 International Journal of Interactive Multimedia and Artificial Intelligence  
Once the stability and sensitivity of the system is analyzed, we describe a series of experiments with three publicly available databases, showing competitive results in all cases.  ...  In this paper, we introduce a new system to estimate the order recovery of thinned static trajectories, which allows to effectively resolve the clusters and select the order of the executed pendowns.  ...  recognition [16] - [18] , Indian and Chinese character recognition [19] , [20] , digit recognition [21] , historical document transcription [22] , mathematical symbol recognition [23] , signature  ... 
doi:10.9781/ijimai.2021.04.003 fatcat:27ch7cdao5fbxdpm7hgfjobfhu

One Shot Learning via Compositions of Meaningful Patches

Alex Wong, Alan Yuille
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
Using those patches as features, we build a compositional model that outperforms a number of popular algorithms on a one-shot learning task.  ...  We propose an unsupervised method for learning a compact dictionary of image patches representing meaningful components of an objects.  ...  Chan and Nunes [5] have suggested that a number of Asian scripts, in particular Chinese, follows a methodical approach of using strokes to (Preliminary) (Top) (Middle) (Bottom) Figure 6.  ... 
doi:10.1109/iccv.2015.142 dblp:conf/iccv/WongY15 fatcat:7qmkjps3prc2vmwcsyhytx3miq

FCN-LectureNet: Extractive Summarization of Whiteboard and Chalkboard Lecture Videos

Kenny Davila, Fei Xu, Srirangaraj Setlur, Venu Govindaraju
2021 IEEE Access  
on the audio, and recognition systems still struggle with handwritten mathematical expression recognition even when the step-wise stroke drawing information is available [1] .  ...  Binarization is used to automatically measure how much of the handwritten content is correctly extracted by matching connected components (CCs) without the need for handwriting recognition. B.  ...  He is a Senior Member of IEEE.  ... 
doi:10.1109/access.2021.3099427 fatcat:nrulxyap2nhrndxtvgjqjd74mq
« Previous Showing results 1 — 15 out of 106 results