Filters








3,254 Hits in 5.5 sec

Self-training for Handwritten Text Line Recognition [chapter]

Volkmar Frinken, Horst Bunke
2010 Lecture Notes in Computer Science  
Off-line handwriting recognition deals with the task of automatically recognizing handwritten text from images, for example from scanned sheets of paper.  ...  The current paper is the first one, to the knowledge of the authors, where semi-supervised learning for unconstrained handwritten text line recognition is proposed.  ...  Acknowledgments We thank Alex Graves for kindly providing us with the BLSTM Neural Network source code.  ... 
doi:10.1007/978-3-642-16687-7_18 fatcat:qwebrfs5hvh6zisno7e5swwm7m

Construction of language models for an handwritten mail reading system

Olivier Morillot, Laurence Likforman-Sulem, Emmanuèle Grosicki, Christian Viard-Gaudin, Richard Zanibbi
2012 Document Recognition and Retrieval XIX  
Word Error Rate and Perplexity values are compared to show the interest of specific language models, fit to handwritten mail recognition task.  ...  This recognition system does not require any segmentation into words or characters and directly works at line level.  ...  ACKNOWLEDGMENTS The authors would like to thank A-L Bianne-Bernard from Télécom ParisTech and Gilles Adda from LIMSI for fruitful discussions.  ... 
doi:10.1117/12.911965 dblp:conf/drr/MorillotLG12 fatcat:ug66hd42zjbanidwyc4fuvgsui

The segmentation of cursive handwriting: an approach based on off-line recovery of the motor-temporal information

R. Plamondon, C.M. Privitera
1999 IEEE Transactions on Image Processing  
The algorithm scans the word, following the natural course of the line, and attempts to reproduce the same movement as executed by the writer during the generation of the word.  ...  In this way, it is possible to detect the parts of the image where the original odometric information is lost or ambiguous (such as, for example, at an intersection of the handwritten lines) and interpret  ...  CONCLUSION In the field of off-line handwriting recognition, the possibility of analyzing the word image by means of a temporal unfolding of the handwritten word into a sequence of primitive strokes representing  ... 
doi:10.1109/83.736691 pmid:18262867 fatcat:q26tesim2zat7ezabf3zzr4hea

New Segmentation Method for Analytical Recognition of Arabic Handwriting Using a Neural-Markovian Method

Khaoula Fergani, Abdelhak Bennia
2018 International Journal of Engineering and Technologies  
This description is based on statistical and structural characteristics extraction of the significant character of the handwritten Arabic words, which can be used in the MLP classification module to estimate  ...  A new hybrid system of off-line analytical recognition of Arabic handwriting combining a neural network type multi-layer perceptron (MLP) and hidden Markov models (HMM) is presented.  ...  Acknowledgments The authors would like to thank the anonymous reviewers for any comments and suggestions that enhance the technical and scientific quality of this paper.  ... 
doi:10.18052/www.scipress.com/ijet.14.14 fatcat:sw6klcfc5ncrrghnxfsnu5yqvy

The State of the Art Recognize in Arabic Script through Combination of Online and Offline [article]

Dr. Firoj Parwej
2013 arXiv   pre-print
In this paper primarily discussed On-line and Off-line handwriting recognition methods for Arabic words which are often used among then across the Middle East and North Africa People.  ...  To combine the Arabic script output sequences of the recognizers, we incrementally align the word sequences using a norm string matching algorithm.  ...  After that we must expect more noise and deformations in whiteboard handwriting than in normal on-line or off-line handwritten an Arabic script data.  ... 
arXiv:1303.4839v1 fatcat:poj6fvvn3be77emjmw272bpsti

Semi-continuous HMMs with explicit state duration for unconstrained Arabic word modeling and recognition

A. Benouareth, A. Ennaji, M. Sellami
2008 Pattern Recognition Letters  
General characteristics of Arabic writing Arabic writing, both handwritten and printed, is semi-cursive (i.e. the word is a sequence of disjointed, but connected components called sub-words and each sub-word  ...  Khorsheed (2003) has presented a method for off-line handwritten script recognition, using a single HMM with structural features extracted from the manuscript words.  ... 
doi:10.1016/j.patrec.2008.05.008 fatcat:wb5kigunqbcylgflwrpw24uq34

Arabic handwritten words off-line recognition based on HMMs and DBNs

Akram Khemiri, Afef Kacem Echi, Abdel Belaid, Mourad Elloumi
2015 2015 13th International Conference on Document Analysis and Recognition (ICDAR)  
Experiments on handwritten Arabic words from IFN/ENIT strongly support the feasibility of the proposed approach.  ...  In this work, we investigate the combination of PGM (Propabilistic Graphical Models) classifiers, either independent or coupled, for the recognition of Arabic handwritten words.  ...  uncertainly of human writing, we investigate in this work their use for off-line recognition of Arabic handwritten words.  ... 
doi:10.1109/icdar.2015.7333724 dblp:conf/icdar/KhemiriEBE15 fatcat:6ekbkzwchvcmjcekvleeofrlca

Confidence Measures for Error Correction in Interactive Transcription Handwritten Text [chapter]

Lionel Tarazón, Daniel Pérez, Nicolás Serrano, Vicent Alabau, Oriol Ramos Terrades, Alberto Sanchis, Alfons Juan
2009 Lecture Notes in Computer Science  
detection and handwritten text transcription.  ...  An effective approach to transcribe old text documents is to follow an interactive-predictive paradigm in which both, the system is guided by the human supervisor, and the supervisor is assisted by the  ...  It has typical characteristics of historical documents that make things difficult: spots, writing from the verso appearing on the recto, unusual characters and words, etc.  ... 
doi:10.1007/978-3-642-04146-4_61 fatcat:z4dpamndmnfl3nbyq55lekxoxa

A PGM-based System for Arabic HandwrittenWord Recognition

Afef Kacem, Akram Khémiri, Abdel Belaid
2014 ELCVIA Electronic Letters on Computer Vision and Image Analysis  
This paper describes a system for off-line recognition of handwritten Arabic words. It uses simple and easily extractable features to construct feature vectors for words in the vocabulary.  ...  Experiments on handwritten Arabic words from IFN/ENIT database and ancient manuscripts strongly support the feasibility of the proposed system.  ...  In sum, we can conclude that most of PGM-based systems, proposed for off-line handwritten digit, character or word recognition, are able to recognize the writing from limited and noisy (artificially or  ... 
doi:10.5565/rev/elcvia.575 fatcat:sb2dxkvti5gevkvv6yxxpk2y6q

Automatic Arabic Hand Written Text Recognition System

Ismael Ahmad Jannoud
2007 American Journal of Applied Sciences  
The main difficulty encountered when dealing with Arabic text is the cursive nature of Arabic writing in both printed and handwritten forms.  ...  After a word has been extracted from the scanned image, it is thinned and its base line is calculated by analysis of horizontal density histogram.  ...  This word file will have all the text in the Arabic handwritten input document. The proposed system was efficient and the performance was about 90 s % differs from types of the characters.  ... 
doi:10.3844/ajassp.2007.857.864 fatcat:pjtztapn2rgf5aakgxggdfiyvq

Online and off-line handwriting recognition: a comprehensive survey

R. Plamondon, S.N. Srihari
2000 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Both the on-line case (which pertains to the availability of trajectory data during writing) and the off-line case (which pertains to scanned images) are considered.  ...  The image of the word is converted into gray-level pixels using a scanner. (b) On-line word. The xY y coordinates of the pentip are recorded as a function of time with a digitizer.  ...  The success of on-line systems makes it attractive to consider developing off-line systems that first estimate the trajectory of the writing from off-line data and then use on-line recognition algorithms  ... 
doi:10.1109/34.824821 fatcat:d2pq2n2yhra65cq2h7zzllhctm

An HMM-based approach for off-line unconstrained handwritten word modeling and recognition

A. El-Yacoubi, M. Gilloux, R. Sabourin, C.Y. Suen
1999 IEEE Transactions on Pattern Analysis and Machine Intelligence  
AbstractÐThis paper describes a hidden Markov model-based approach designed to recognize off-line unconstrained handwritten words for large vocabularies.  ...  After preprocessing, a word image is segmented into letters or pseudoletters and represented by two feature sequences of equal length, each consisting of an alternating sequence of shape-symbols and segmentationsymbols  ...  ACKNOWLEDGMENTS This work was supported by the Service de Recherche Technique de la Poste (SRTP) at Nantes, France, 1 Ecole de Technologie Supe Ârieure (ETS) at Montre Âal, Canada, and the Centre of Pattern  ... 
doi:10.1109/34.784288 fatcat:dfpd4bi2jrazzlxpzsx3tbqthq

InfraNotes: Inconspicuous Handwritten Trajectory Tracking for Lecture Note Recording with Infrared Sensors [article]

Steve Chang
2016 arXiv   pre-print
In this paper, we design and implement an infrared sensor based system, InfraNotes, to automatically record the notes on the board by sensing and analyzing hand gestures of the lecturer.  ...  Instead, it only has an infrared-sensor module on the eraser holder of black/white board to capture handwritten trajectories.  ...  Preprocessing of off-line recognition includes setting thresholds to extract writing points, removal of noise, segmentation of writing lines, and finally segmentation of characters and words.  ... 
arXiv:1610.02442v1 fatcat:f55hao5osbh7lh7wmiijmg3gte

A Survey of Contextual Handwritten Recognition Systems based HMMs for Cursive Arabic and Latin Script

Mouhcine Rabi, Mustapha Amrouch, Zouhir Mahani
2017 International Journal of Computer Applications  
It examines the literature on the most significant work in contextual handwritten text recognition for two different alphabets, Latin and Arabic.  ...  Offline handwriting recognition has become lately a very popular research area and the number of its possible application is very large.  ...  In general, handwritten recognition is classified into two types as on-line and off-line recognition methods [01] .  ... 
doi:10.5120/ijca2017912982 fatcat:snfu4lcbizcxvci274uyidithu

Generalized hidden Markov models. II. Application to handwritten word recognition

M.A. Mohamed, P. Gader
2000 IEEE transactions on fuzzy systems  
Methods for training the classical and generalized (fuzzy) models are described. Experiments were performed on a standard data set of handwritten word images obtained from the U. S.  ...  of handwritten word recognition.  ...  Blackwell of the University of Missouri at Columbia for their valuable discussions and suggestions.  ... 
doi:10.1109/91.824774 fatcat:xqvbsi6tzvfmvhtg63l3audkpm
« Previous Showing results 1 — 15 out of 3,254 results