460 Hits in 3.6 sec

From handwriting analysis to pen-computer applications

L. Schomaker
1998 Electronics & communication engineering journal  
The handwriting process and product are discussed and, finally, automatic recognition methodologies are considered.  ...  A handwriting recognition approach using segmentation into velocity-based strokes is considered in somewhat more detail.  ...  The handwriting-recognition research groups around the world are very small as compared to the effort spent in speech recognition.  ... 
doi:10.1049/ecej:19980302 fatcat:r3ynpkk7wvhffmuauiv4xbo3la

Keyword Spotting in Online Chinese Handwritten Documents with Candidate Scoring Based on Semi-CRF Model

Heng Zhang, Xiang-Dong Zhou, Cheng-Lin Liu
2013 2013 12th International Conference on Document Analysis and Recognition  
Character similarity (between character and class) scores are calculated on each edge, and the similarity between a query word and handwriting is obtained by combining these edge scores.  ...  For text-query-based keyword spotting from handwritten Chinese documents, the index is usually organized as a candidate lattice to overcome the ambiguity of character segmentation.  ...  ACKNOWLEDGMENT This work is supported by the National Natural Science Foundation of China (NSFC) under grants no. 60933010 and no. 61273269.  ... 
doi:10.1109/icdar.2013.118 dblp:conf/icdar/ZhangZL13 fatcat:32sw6juqmnbohetcqcrtinyqym

Derin Öğrenme Araştırma Alanlarının Literatür Taraması

M. Mutlu Yapıcı, Adem Tekerek, Nurettin Topaloğlu
2019 Gazi Mühendislik Bilimleri Dergisi  
In the last decade, the-state-of-the-art studies on many research areas such as computer vision, object recognition, speech recognition, and natural language processing were especially led to the awakening  ...  Furthermore, this study points out the remaining challenges of these research areas that can be solved by DL, and discusses future topics to help the researchers.  ...  [146] used DNN for speech enhancement and speech recognition.  ... 
doi:10.30855/gmbd.2019.03.01 fatcat:2sv7dg7elrfqppcjx5otzmb7pi

Improving Visibility and Reducing Resistance of Writers to Fusion of Handwritten and Type Characters [chapter]

Mikako Sasaki, Junki Saito, Satoshi Nakamura
2018 Lecture Notes in Computer Science  
In this study, we consider a technique that fuses handwriting with typeface in order to reduce the resistance to handwriting and improve the impression of the message.  ...  Most Japanese people feel happy to receive a handwritten message, but they often have resistance to writing a message by hand.  ...  This work was supported in part by JST, JST ACCEL Grant Number JPMJAC1602, Japan, and Meiji University Priority Research A.  ... 
doi:10.1007/978-3-319-98743-9_15 fatcat:4tbfhjwivvar5fl5iwdq6qkq7q

A Thresholded Gabor-CNN Based Writer Identification System for Indic Scripts

M. F. Mridha, Abu Quwsar Ohi, Jungpil Shin, Muhammad Mohsin Kabir, Muhammad Mostafa Monowar, Md. Abdul Hamid
2021 IEEE Access  
Writer identification is a common interest in biometric authentication and verification systems, and numerous studies are available for English, Chinese, Arabic, and Persian specific handwriting.  ...  Writer identification is the procedure of identifying individuals from handwriting.  ...  In this paper, by writer recognition, we term the text-independent writer recognition systems.  ... 
doi:10.1109/access.2021.3114799 fatcat:4ktqpgrl6fa6pcjmequfku7rpq

Minimum Risk Training for Handwritten Chinese/Japanese Text Recognition Using Semi-Markov Conditional Random Fields

Xiang-Dong Zhou, Feng Tian, Cheng-Lin Liu, Hong-An Wang
2013 2013 12th International Conference on Document Analysis and Recognition  
In this paper, based on our previous work on handwritten Chinese/Japanese text recognition (HCTR) using semi-CRFs, we propose an alternative parameter learning method by minimizing the risk, in which the  ...  Experimental results on two online handwriting databases: CASIA-OLHWDB and TUAT Kondate demonstrate that minimum-risk training can yield superior string recognition rates compared to MAP training.  ...  ACKNOWLEDGMENT This work is supported by the National Natural Science Foundation of China (NSFC) under grants no. 61232013, no. 61273269, no. 60933010, no. 61100151 and no. 61170182.  ... 
doi:10.1109/icdar.2013.191 dblp:conf/icdar/ZhouTLW13 fatcat:bbjqzdzidfhjtbi2zraxs36ovq

A Study on Speech Emotion Recognitions on Machine Learning Algorithms [chapter]

Shanmuk Srinivas Amiripalli, Potnuru Likhitha, Sisankita Patnaik, Suresh Babu K, Rampay Venkatarao
2021 Advances in Parallel Computing  
Following that, we cleaned the datasets by using the mask feature to eliminate unnecessary background noise, and then we applied all 10 algorithms to this clean speech dataset to improve accuracy.  ...  Finally, by using the algorithm, we could calculate the number of sound files correlated with each of the emotions described in those datasets.  ...  Speech Expression Recognition, Face Identification, Handwriting Recognition, Text Classification, and other classification problems are some of the most important.  ... 
doi:10.3233/apc210225 fatcat:frzbouasora7jn6puvgnmwcdba

The Optical Character Recognition for Cursive Script Using HMM: A Review

Saeeda Naz, Arif I. Umar, Syed H. Shirazi, Muhammad M. Ajmal, Salahuddin Salahuddin
2014 Research Journal of Applied Sciences Engineering and Technology  
Automatic Character Recognition has wide variety of applications such as automatic postal mail sorting, number plate recognition and automatic form of reader and entering text from PDA's etc.  ...  This paper present a comprehensive literature review of the Optical Character Recognition (OCR) for off-line and on-line character recognition for Urdu, Arabic and Persian languages, based on Hidden Markov  ...  The recognition rate was improved by 2.38%.  ... 
doi:10.19026/rjaset.8.1193 fatcat:7cpmia3vgrgttjahnkqqbvwaxy

An automatic sign recognition and translation system

Jie Yang, Jiang Gao, Ying Zhang, Xilin Chen, Alex Waibel
2001 Proceedings of the 2001 workshop on Percetive user interfaces - PUI '01  
This paper discusses problems of automatic sign recognition and translation.  ...  We are currently working on Chinese sign translation.  ...  This research is partially supported by DARPA under TIDES project.  ... 
doi:10.1145/971478.971490 fatcat:uhvlwate55f3dkhtr2ppjzghha

The W3C multimodal architecture and interfaces standard

Deborah A. Dahl
2013 Journal on Multimodal User Interfaces  
However, as technologies such as speech recognition, natural language understanding and gesture recognition become increasingly capable, it is becoming much more feasible to build applications that support  ...  But even in the earliest days of computing [1], it was recognized that computer-human interaction would be improved if the computer could interact with humans in the ways that humans are used to using  ...  These include speech recognition, text to speech, handwriting recognition and natural language processing. Other components, such as video capture, are not languagespecific.  ... 
doi:10.1007/s12193-013-0120-5 fatcat:it54uusehze3djxcnjgjdvbox4

Handwritten Character Recognition from Wearable Passive RFID [article]

Leevi Raivio, Han He, Johanna Virkki, Heikki Huttunen
2020 arXiv   pre-print
In this paper we study the recognition of handwritten characters from data captured by a novel wearable electro-textile sensor panel.  ...  We propose a preprocessing pipeline that fuses the sequence and bitmap representations together. The data is collected from ten subjects containing altogether 7500 characters.  ...  This is in line with many other modes of humancomputer interaction: for example, people automatically speak more clearly even to the most up to date speech recognition systems.  ... 
arXiv:2008.02543v1 fatcat:xrlmqna6hndoze4odu2iukcngq

Focal CTC Loss for Chinese Optical Character Recognition on Unbalanced Datasets

Xinjie Feng, Hongxun Yao, Shengping Zhang
2019 Complexity  
To solve this issue, we modify the traditional CTC by fusing focal loss with it and thus make the model attend to the low-frequent samples at training stage.  ...  In this paper, we propose a novel deep model for unbalanced distribution Character Recognition by employing focal loss based connectionist temporal classification (CTC) function.  ...  Acknowledgments This work was partly supported by the Science and Technology Funding of China (no. 61772158 and no. 61472103) and the Science and Technology Funding Key Program of China (no.  ... 
doi:10.1155/2019/9345861 fatcat:nenkoy6ryrda7eurzehtpkulgu

Rethinking Text Line Recognition Models [article]

Daniel Hernandez Diaz, Siyang Qin, Reeve Ingle, Yasuhisa Fujii, Alessandro Bissacco
2021 arXiv   pre-print
In this paper, we study the problem of text line recognition.  ...  Unlike the more common Transformer-based models, this architecture can handle inputs of arbitrary length, a requirement for universal line recognition.  ...  CTC: The CTC decoder was originally used in speech recognition, and researchers have had huge success adopting it to OCR tasks.  ... 
arXiv:2104.07787v2 fatcat:2ncwpg7mlfcc3e4i6v6tgiju7e

Offline handwritten Arabic cursive text recognition using Hidden Markov Models and re-ranking

Jawad H AlKhateeb, Jinchang Ren, Jianmin Jiang, Husni Al-Muhtaseb
2011 Pattern Recognition Letters  
recognition rate.  ...  2011) Offline handwritten Arabic cursive text recognition using hidden markov models and re-ranking. Pattern Recognition Letters, 32 (8).  ...  HWR for Latin and Chinese languages has been conducted and 43 significant achievements have been made. However, there has been less work in Arabic 44 handwriting recognition.  ... 
doi:10.1016/j.patrec.2011.02.006 fatcat:dvsxzyip75e6pisf3vpy6mrg2u

COMPASS2008: Multimodal, Multilingual and Crosslingual Interaction for Mobile Tourist Guide Applications [chapter]

Ilhan Aslan, Feiyu Xu, Hans Uszkoreit, Antonio Krüger, Jörg Steffen
2005 Lecture Notes in Computer Science  
dish from a list of dishes (3) speech: "compare this dish" + gesture + speech:"to this dish" + gesture (4) speech: "translate this Chinese writing" + handwriting (or gesture) For ordering the food by the  ...  We currently use IBM ViaVoice for speech input and Scansoft TTS for speech output, Chinese speech recognition and synthesis modules developed in the Chinese partner project MISS2 are also under consideration  ... 
doi:10.1007/11590323_1 fatcat:biwzi2cihnauplyep3j5it3ybm
« Previous Showing results 1 — 15 out of 460 results