Filters








35,206 Hits in 2.8 sec

Discriminative learning for script recognition

Sheikh Faisal Rashid, Faisal Shafait, Thomas M. Breuel
2010 2010 IEEE International Conference on Image Processing  
In this paper we propose a discriminative learning approach for multi-script recognition at connected component level by using a convolutional neural network.  ...  The convolutional neural network combines feature extraction and script recognition process in one step and discriminative features for script recognition are extracted and learned as convolutional kernels  ...  We use a convolutional neural network as discriminative learning model to extract and learn suitable features for multi-script recognition task.  ... 
doi:10.1109/icip.2010.5650928 dblp:conf/icip/RashidSB10 fatcat:vjzxc4gtjvaabgoldizuijromy

Exploiting Multimedia Content: A Machine Learning Based Aproach

Ehtesham Hassan
2014 ELCVIA Electronic Letters on Computer Vision and Image Analysis  
The evaluation is shown for Indian script character recognition, and MPEG7 shape symbol recognition.  ...  A multi-modal indexing framework for such documents is presented by a learning based combination of text and image based properties. Experimental results are shown on Devanagari script documents.  ...  The evaluation is shown for Indian script character recognition, and MPEG7 shape symbol recognition.  ... 
doi:10.5565/rev/elcvia.598 fatcat:mmeqgte4pzedzbtuukeepqxlgm

A fine-grained approach to scene text script identification [article]

Lluis Gomez, Dimosthenis Karatzas
2016 arXiv   pre-print
Script identification is an important prerequisite to recognition, and an indispensable condition for automatic text understanding systems designed for multi-language environments.  ...  In addition, we propose a new public benchmark dataset for the evaluation of joint text detection and script identification in natural scenes.  ...  Our work takes inspiration from recent methods in finegrained recognition. In particular, Krause et al. [10] focus on learning expressive appearance descriptors and localizing discriminative parts.  ... 
arXiv:1602.07475v1 fatcat:xesy7sxekvcwvdzsuxfg6ygfcu

Comparative Study of Devnagari Handwritten Character Recognition Using Different Feature and Classifiers

Umapada Pal, Tetsushi Wakabayashi, Fumitaka Kimura
2009 2009 10th International Conference on Document Analysis and Recognition  
Projection distance, subspace method, linear discriminant function, support vector machines, modified quadratic discriminant function, mirror image learning, Euclidean distance, nearest neighbour, k-Nearest  ...  Many approaches have been proposed by the researchers towards handwritten Indian character recognition and many recognition systems for isolated handwritten numerals/characters are available in the literature  ...  The authors hope this benchmark of results will be helpful to the researchers for future work.  ... 
doi:10.1109/icdar.2009.244 dblp:conf/icdar/PalWK09 fatcat:q4ehkas5jjdqrf35cutb4hsjmu

Multilingual Scene Character Recognition System using Sparse Auto-Encoder for Efficient Local Features Representation in Bag of Features [article]

Maroua Tounsi, Ikram Moalla, Frank Lebourgeois, Adel M. Alimi
2018 arXiv   pre-print
In this paper, we extended the Bag of Features (BoF)-based model using deep learning for representing features for accurate SCR of different languages.  ...  This deep learning architecture provides more efficient features representation and therefore a better recognition accuracy.  ...  (b) (c) (d) (e) Scene character recognition based on deep learning So far, learning features directly from data through deep learning methods has become increasingly popular and effective for visual  ... 
arXiv:1806.07374v4 fatcat:edkrvvarazaurok7cql2aot74a

Chinese character acquisition and visual skills in two Chinese scripts

Catherine Mcbride-Chang, Bonnie W. Y. Chow, Yiping Zhong, Stephen Burgess, William G. Hayward
2005 Reading and writing  
Across testing times, visual skills of the Xiangtan children, who learn simplified script, were significantly higher than those of the Hong Kong children, learning traditional script.  ...  Hydesville, CA: Psychological and Educational Publications] predicted unique variance in Chinese character recognition, controlling for other skills, at Time 1 among Hong Kong children and at Time 2 in  ...  Acknowledgments Thanks to the parents, teachers, and kindergartners of Xiangtan and Hong Kong, China, for facilitating the testing done for this study.  ... 
doi:10.1007/s11145-004-7343-5 fatcat:2ld4agujg5f35gbggokwsdjbei

Recognizing Human Action in the Wild [chapter]

Ivan Laptev
2010 Lecture Notes in Computer Science  
With this approach we automatically retrieve action samples for training and learn discriminative visual action models from a large set of movies.  ...  We also address the temporal uncertainty of script-based action supervision and present a discriminative clustering algorithm that compensates for this uncertainty and provides substantially improved results  ...  With this approach we automatically retrieve action samples for training and learn discriminative visual action models from a large set of movies.  ... 
doi:10.1007/978-3-642-14715-9_9 fatcat:ebylkh6vzfbt5nsioftlp3x4vq

Learning from Video and Text via Large-Scale Discriminative Clustering [article]

Antoine Miech, Jean-Baptiste Alayrac, Piotr Bojanowski, Ivan Laptev, Josef Sivic
2017 arXiv   pre-print
Discriminative clustering has been successfully applied to a number of weakly-supervised learning tasks.  ...  We apply the proposed method to the problem of weakly supervised learning of actions and actors from movies together with corresponding movie scripts.  ...  While actors are learned separately for each movie, differently from [4] , our method simultaneously learns actions from all movies and movie scripts available for training.  ... 
arXiv:1707.09074v1 fatcat:bxup4vtk5nh6xd7zw2vnrog6je

Learning from Video and Text via Large-Scale Discriminative Clustering

Antoine Miech, Jean-Baptiste Alayrac, Piotr Bojanowski, Ivan Laptev, Josef Sivic
2017 2017 IEEE International Conference on Computer Vision (ICCV)  
Discriminative clustering has been successfully applied to a number of weakly-supervised learning tasks.  ...  We apply the proposed method to the problem of weakly-supervised learning of actions and actors from movies together with corresponding movie scripts.  ...  While actors are learned separately for each movie, differently from [4] , our method simultaneously learns actions from all movies and movie scripts available for training.  ... 
doi:10.1109/iccv.2017.562 dblp:conf/iccv/MiechABLS17 fatcat:ykvnmiatrzfmxfxkcemxy4y32e

ThaiWritableGAN: Handwriting Generation under Given Information

Lawankorn Mookdarsanit, Pakpoom Mookdarsanit
2021 International Journal of Computing and Digital Systems  
For the local technique challenge, Thai has different symbols' vertical positions with no space between characters and words. Thai handwriting recognition has been a long time research problem.  ...  D is assigned to discriminate an unknown handwritten image that it is real or generated.  ...  WER was used as metric for Thai script recognition [61] and also in this composing Thai handwritten content. D.  ... 
doi:10.12785/ijcds/100165 fatcat:v46prnxovbdspplgugy5o2plge

Comparative Analysis of Gabor and Discriminating Feature Extraction Techniques for Script Identification [chapter]

Rajneesh Rani, Renu Dhir, G. S. Lehal
2011 Communications in Computer and Information Science  
In this work, for script identification discriminating and Gabor filter based features are computed of Punjabi words and English numerals.  ...  Extracted feature are simulated with Knn and SVM classifiers to identify the script and then recognition rates are compared.  ...  The second technique is based on the identification of the script of each character before taking the characters for recognition.  ... 
doi:10.1007/978-3-642-19403-0_27 fatcat:r7l7tlhxh5bxdgjjfpm5ntn4yq

Script processing in a natural situation

Glenn V. Nakamura, Arthur C. Graesser, Judy A. Zimmerman, James Riha
1985 Memory & Cognition  
First, the SC + T model predicts that recognition memory discrimination should be better for irrelevant than for relevant actions.  ...  We define recognition memory discrimination for relevant and irrelevant actions as the ability to discriminate between target and distractor test actions.  ... 
doi:10.3758/bf03197006 pmid:4033416 fatcat:4koui5mpkra63mqrul5nd23ehq

A Review on Offline Handwritten Recognition of Devnagari Script

Snehal S. Patwardhan, R.R Deshmukh
2015 International Journal of Computer Applications  
This paper gives a detailed overview of different feature extraction and classification techniques for recognition process Devanagari script by the researchers over the past few decades.  ...  In country like India, where many languages and scripts exist , Devanagari is third most widely used script, used for several major languages such as Marathi ,Hindi, Sanskrit, and Nepali, and is used by  ...  [18] on Devanagari handwritten character recognition using 12 different classifiers like PD, subspace method (SM), linear discriminant function (LDF), SVM, MQDF, mirror image learning (MIL), Euclidean  ... 
doi:10.5120/20669-3300 fatcat:reze23pmevfqnd7ohdhzvbdtwq

The representational and processing characteristics of scripts

Francis S. Bellezza, Gordon H. Bower
1981 Bulletin of the Psychonomic Society  
However, recognition of the typical actions was inferior to recognition performance on atypical actions, probably because subjects had difficulty discriminating between those typical actions that were  ...  In the experiment reported here, decision times, recall performance, and recognition performance were either typical or atypical of the scripts in which they were embedded.  ...  There was better discrimination for atypical than for typical old and new actions.  ... 
doi:10.3758/bf03333553 fatcat:hpmybhajzbf3lktaml5tzzetgi

A Novel Deep Convolutional Neural Network Architecture Based on Transfer Learning for Handwritten Urdu Character Recognition

2020 Tehnički Vjesnik  
For character recognition, where the training images are usually inadequate, mostly transfer learning of pre-trained CNN is often utilized.  ...  In this paper, we propose a novel deep convolutional neural network for handwritten Urdu character recognition by transfer learning three pre-trained CNN models.  ...  Acknowledgement We are very much thankful to Saad bin Ahmed, ELDA,Hossein Khosravi and SAAD for providing us the UNHD, EMILLE, CDB/Farsi and DBAHCL dataset respectively.  ... 
doi:10.17559/tv-20190319095323 fatcat:42pfouhqbrgwvgwxppkxzrpoly
« Previous Showing results 1 — 15 out of 35,206 results