Search For:

Displaying 1-40 out of 40 total
Help-training semi-supervised LS-SVM
Found in: Neural Networks, IEEE - INNS - ENNS International Joint Conference on
By Mathias M. Adankon, Mohamed Cheriet
Issue Date:June 2009
pp. 49-56
Help-training for semi-supervised learning was proposed in our previous work in order to reinforce self-training strategy by using a generative classifier along with the main discriminative classifier. This paper extends the Help-training method to least s...
 
An Efficient Ground Truthing Tool for Binarization of Historical Manuscripts
Found in: 2013 12th International Conference on Document Analysis and Recognition (ICDAR)
By Hossein Ziaei Nafchi,Seyed Morteza Ayatollahi,Reza Farrahi Moghaddam,Mohamed Cheriet
Issue Date:August 2013
pp. 807-811
For the purpose of facilitating benchmark contributions for binarization methods, a new fast ground truthing approach, called the PhaseGT, is proposed. This approach is used for building the 1st groundtruthed Persian Heritage Image Binarization Dataset (PH...
 
Sketch-Based Retrieval of Document Illustrations and Regions of Interest
Found in: 2013 12th International Conference on Document Analysis and Recognition (ICDAR)
By Lukas Tencer,Marta Renakova,Mohamed Cheriet
Issue Date:August 2013
pp. 728-732
In this paper we present a novel approach towards retrieval of documents with pictorial data. Many prior works focused on word-spotting and text-based retrieval, but none of these techniques handled the retrieval of pictorial part of documents. In this pap...
 
Feature Design for Offline Arabic Handwriting Recognition: Handcrafted vs Automated?
Found in: 2013 12th International Conference on Document Analysis and Recognition (ICDAR)
By Youssouf Chherawala,Partha Pratim Roy,Mohamed Cheriet
Issue Date:August 2013
pp. 290-294
In handwriting recognition, design of relevant feature is a very important but daunting task. On one hand, handcraft design of features is difficult, depending on expert knowledge and on heuristics. On the other hand, biologically inspired neural networks ...
 
An Empirical Evaluation of Supervised Dimensionality Reduction for Recognition
Found in: 2013 12th International Conference on Document Analysis and Recognition (ICDAR)
By Guoqiang Zhong,Youssouf Chherawala,Mohamed Cheriet
Issue Date:August 2013
pp. 1315-1319
In the literature, many dimensionality reduction methods have been proposed and applied to recognition tasks, including handwritten digits recognition, character recognition and string recognition. However, it is usually difficult for the researchers to de...
 
Ground-Truth Estimation in Multispectral Representation Space: Application to Degraded Document Image Binarization
Found in: 2013 12th International Conference on Document Analysis and Recognition (ICDAR)
By Rachid Hedjam,Mohamed Cheriet
Issue Date:August 2013
pp. 190-194
Human ground-truthing is the manual labelling of samples (pixels for example) to generate reference data without any automatic algorithm help. Although a manual ground-truth is more accurate than a machine ground-truth, it still suffers from mislabeling an...
 
Application of Phase-Based Features and Denoising in Postprocessing and Binarization of Historical Document Images
Found in: 2013 12th International Conference on Document Analysis and Recognition (ICDAR)
By Hossein Ziaei Nafchi,Reza Farrahi Moghaddam,Mohamed Cheriet
Issue Date:August 2013
pp. 220-224
Preprocessing and post processing steps significantly improve the performance of binarization methods, especially in the case of severely-degraded historical documents. In this paper, an unsupervised post processing method is introduced based on the phase-...
 
Unsupervised Ensemble of Experts (EoE) Framework for Automatic Binarization of Document Images
Found in: 2013 12th International Conference on Document Analysis and Recognition (ICDAR)
By Reza Farrahi Moghaddam,Fereydoun Farrahi Moghaddam,Mohamed Cheriet
Issue Date:August 2013
pp. 703-707
In recent years, a large number of binarization methods have been developed, with varying performance generalization and strength against different benchmarks. In this work, to leverage on these methods, an ensemble of experts (EoE) framework is introduced...
 
ARTIST: ART-2A Driven Generation of Fuzzy Rules for Online Handwritten Gesture Recognition
Found in: 2013 12th International Conference on Document Analysis and Recognition (ICDAR)
By Marta Renakova,Lukas Tencer,Mohamed Cheriet
Issue Date:August 2013
pp. 354-358
Incremental learning, especially when learning from a scratch, has a lot of interest for online gesture recognition. However the lack of learning examplers combined to low computational cost suggests building robust and efficient learning machines. In this...
 
Powering a Data Center Network via Renewable Energy: A Green Testbed
Found in: IEEE Internet Computing
By Kim-Khoa Nguyen,Mohamed Cheriet,Mathieu Lemay,Michel Savoie,Bobby Ho
Issue Date:January 2013
pp. 40-49
Today's information and communications technology (ICT) services emit an increasing amount of greenhouse gases. Carbon footprint models can enable research into ICT energy efficiency and carbon reduction. The GreenStar Network (GSN) testbed is a prototype ...
 
Carbon Metering and Effective Tax Cost Modeling for Virtual Machines
Found in: 2012 IEEE 5th International Conference on Cloud Computing (CLOUD)
By Fereydoun Farrahi Moghaddam,Reza Farrahi Moghaddam,Mohamed Cheriet
Issue Date:June 2012
pp. 758-763
With raising concerns about global warming and environmental impacts of Greenhouse Gases (GhGs) emissions, energy efficiency and carbon footprint reduction attracted many researchers to provide efficient models and tools for energy, carbon, and cost estima...
 
Indexing On-line Handwritten Texts Using Word Confusion Networks
Found in: Document Analysis and Recognition, International Conference on
By Sebasti´n Peña Saldarriaga,Mohamed Cheriet
Issue Date:September 2011
pp. 197-201
In the context of handwriting recognition, word confusion networks (WCN) are convenient representations of alternative recognition candidates. They provide alignment for mutually exclusive words along with the posterior probability of each word. In this pa...
 
Novel Data Representation for Text Extraction from Multispectral Historical Document Images
Found in: Document Analysis and Recognition, International Conference on
By Rachid Hedjam,Mohamed Cheriet
Issue Date:September 2011
pp. 172-176
The extraction and analysis of useful information from old document images is very important into cultural heritage preservation. In advanced research, where the goal is to separate the foreground (in general, text) from the background, image restoration a...
 
Low Carbon Virtual Private Clouds
Found in: Cloud Computing, IEEE International Conference on
By Fereydoun Farrahi Moghaddam,Mohamed Cheriet,Kim Khoa Nguyen
Issue Date:July 2011
pp. 259-266
Data center energy efficiency and carbon footprint reduction have attracted a great deal of attention across the world for some years now, and recently more than ever. Live Virtual Machine (VM) migration is a prominent solution for achieving server consoli...
 
Personalizable Pen-Based Interface Using Lifelong Learning
Found in: Frontiers in Handwriting Recognition, International Conference on
By Abdullah Almaksour, Eric Anquetil, Solen Quiniou, Mohamed Cheriet
Issue Date:November 2010
pp. 188-193
In this paper, we present a new method to design customizable self-evolving fuzzy rule-based classifiers. The presented approach combines an incremental clustering algorithm with a fuzzy adaptation method in order to learn and maintain the model. We use th...
 
Evolving Fuzzy Classifiers: Application to Incremental Learning of Handwritten Gesture Recognition Systems
Found in: Pattern Recognition, International Conference on
By Abdullah Almaksour, Eric Anquetil, Solen Quiniou, Mohamed Cheriet
Issue Date:August 2010
pp. 4056-4059
In this paper, we present a new method to design customizable self-evolving fuzzy rule-based classifiers. The presented approach combines an incremental clustering algorithm with a fuzzy adaptation method in order to learn and maintain the model. We use th...
 
Application of Multi-Level Classifiers and Clustering for Automatic Word Spotting in Historical Document Images
Found in: Document Analysis and Recognition, International Conference on
By Reza Farrahi Moghaddam, Mohamed Cheriet
Issue Date:July 2009
pp. 511-515
A complete system for preprocessing and word spotting of very old historical document images is presented. Document images are processed for extraction of salient information using a word spotting technique which does not need line and word segmentation an...
 
Restoration and Segmentation of Highly Degraded Characters Using a Shape-Independent Level Set Approach and Multi-level Classifiers
Found in: Document Analysis and Recognition, International Conference on
By Reza Farrahi Moghaddam, David Rivest-Henault, Mohamed Cheriet
Issue Date:July 2009
pp. 828-832
Segmentation of ancient documents is challenging. In the worst cases, text characters become fragmented as the results of strong degradation processes. New active contour methods allow to handle difficult cases in a spatially coherent fashion. However, mos...
 
A New Approach for Skew Correction of Documents Based on Particle Swarm Optimization
Found in: Document Analysis and Recognition, International Conference on
By Javad Sadri, Mohamed Cheriet
Issue Date:July 2009
pp. 1066-1070
This paper presents a novel approach for skew correction of documents. Skew correction is modeled as an optimization problem, and for the first time, Particle Swarm Optimization (PSO) is used to solve skew optimization. Anew objective function based on loc...
 
A Unified Framework Based on the Level Set Approach for Segmentation of Unconstrained Double-Sided Document Images Suffering from Bleed-Through
Found in: Document Analysis and Recognition, International Conference on
By Reza Farrahi Moghaddam, David Rivest-Hénault, Itay Bar-Yosef, Mohamed Cheriet
Issue Date:July 2009
pp. 441-445
A novel method for the segmentation of double-sided ancient document images suffering from bleed-through effect is presented. It takes advantage of the level set framework to provide a completely integrated process for the segmentation of the text along wi...
 
Handling Out-of-Vocabulary Words and Recognition Errors Based on Word Linguistic Context for Handwritten Sentence Recognition
Found in: Document Analysis and Recognition, International Conference on
By Solen Quiniou, Mohamed Cheriet, Eric Anquetil
Issue Date:July 2009
pp. 466-470
In this paper we investigate the use of linguistic information given by language models to deal with word recognition errors on handwritten sentences. We focus especially on errors due to out-of-vocabulary (OOV) words. First, word posterior probabilities a...
 
A Variational Approach to Degraded Document Enhancement
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Reza Farrahi Moghaddam, Mohamed Cheriet
Issue Date:August 2010
pp. 1347-1361
The goal of this paper is to correct bleed-through in degraded documents using a variational approach. The variational model is adapted using an estimated background according to the availability of the verso side of the document image. Furthermore, for th...
 
Bayes Classification of Online Arabic Characters by Gibbs Modeling of Class Conditional Densities
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Neila Mezghani, Amar Mitiche, Mohamed Cheriet
Issue Date:July 2008
pp. 1121-1131
This study investigates Bayes classification of online Arabic characters represented by histograms of tangent differences and Gibbs modeling of the class-conditional probability density functions. The parameters of these Gibbs density functions are estimat...
 
A Threshlod Selection Method Based on Multiscale and Graylevel Co-occurrence Matrix Analysis
Found in: Document Analysis and Recognition, International Conference on
By Yun Li, Ching Y. Suen, Mohamed Cheriet
Issue Date:September 2005
pp. 575-579
Noises and complex backgrounds often make the thresholding of degraded document images a difficult job. In this paper, we propose a new threshold selection method to handle severely degraded document images. First, multiscale image description is adopted t...
 
Speeding Up the Decision Making of Support Vector Classifiers
Found in: Frontiers in Handwriting Recognition, International Workshop on
By Jonathan Milgram, Mohamed Cheriet, Robert Sabourin
Issue Date:October 2004
pp. 57-62
In this paper, we propose a new approach for speeding up the decision making of Support Vector Classifiers (SVC) in the context of multi-class classification. A two-stage system embedded within a probabilistic framework is presented. In the first stage we ...
 
Spiral Recognition Methodology and Its Application for Recognition of Chinese Bank Checks
Found in: Frontiers in Handwriting Recognition, International Workshop on
By Hanshen Tang, Emmanuel Augustin, Ching Y. Suen, Olivier Baret, Mohamed Cheriet
Issue Date:October 2004
pp. 263-268
This paper presents the spiral recognition methodology with its application in unconstrained handwritten Chinese legal amount recognition in a practical environment of a CheckReader™. This paper first describes the failed application of neural network - hi...
 
A Segmentation Method for Touching Italic Characters
Found in: Pattern Recognition, International Conference on
By Yun Li, Satoshi Naoi, Mohamed Cheriet, Ching Y. Suen
Issue Date:August 2004
pp. 594-597
Segmentation is an essential part of a recognition system. It is difficult to handle touching characters, especially for italic fonts. We present a method to achieve the accurate segmentation of touching italic characters. It is free of slant correction, s...
 
Recognition of Unconstrained Legal Amounts Handwritten on Chinese Bank Checks
Found in: Pattern Recognition, International Conference on
By Hanshen Tang, Emmanuel Augustin, Ching Y. Suen, Olivier Baret, Mohamed Cheriet
Issue Date:August 2004
pp. 610-613
This paper presents a novel research investigation on legal amount recognition of unconstrained cursive handwritten Chinese character in the environment of A2iA CheckReader™ - a commercial bank check recognition system. The following problems and their sol...
 
Two-Stage Classification System combining Model-Based and Discriminative Approaches
Found in: Pattern Recognition, International Conference on
By Jonathan Milgram, Robert Sabourin, Mohamed Cheriet
Issue Date:August 2004
pp. 152-155
For the tasks of classification, two types of patterns can generate problems: ambiguous patterns and outliers. Furthermore, it is possible to separate classification algorithms into two main categories. Discriminative approaches try to find the better sepa...
 
Shock Filters for Character Image Enhancement and Peeling
Found in: Document Analysis and Recognition, International Conference on
By Mohamed Cheriet
Issue Date:August 2003
pp. 1247
In this paper, we propose a generalized shock model for the enhancement and restoration of degraded gray-level character images. This model is a quasi-linear hyperbolic partial differential equation with discontinuous coefficients, based on a recently-publ...
 
Automatic Filter Selection Using Image Quality Assessment
Found in: Document Analysis and Recognition, International Conference on
By Andrea Souza, Mohamed Cheriet, Satoshi Naoi, Ching Y. Suen
Issue Date:August 2003
pp. 508
We present a method for automatically selecting the best filter to treat poor quality printed documents using image quality assessment. We introduce five quality measures to obtain information about the quality of the images, and morphological filters to i...
 
Combination of Pruned Kohonen Maps for On-line Arabic Characters Recognition
Found in: Document Analysis and Recognition, International Conference on
By Neila Mezghani, Mohamed Cheriet, Amar Mitiche
Issue Date:August 2003
pp. 900
The purpose of this study is to investigate a method for high performance on-line Arabic characters recognition. This method is based on the use of Kohonen maps and their corresponding confusion matrices which serve to prune them of error-causing nodes, an...
 
On-Line Recognition of Handwritten Arabic Characters Using a Kohonen Neural Network
Found in: Frontiers in Handwriting Recognition, International Workshop on
By Neila Mezghani, Amar Mitiche, Mohamed Cheriet
Issue Date:August 2002
pp. 490
Neural networks have been applied to various pattern classification and recognition problems for their learning ability, discrimination power, and generalization ability. The neural network most referenced in the pattern recognition literature are the mult...
 
Online Recognition of Sketched Electrical Diagrams
Found in: Document Analysis and Recognition, International Conference on
By Jean-Philippe Valois,Myriam Côté,Mohamed Cheriet
Issue Date:September 2001
pp. 0460
Abstract: In this paper, a model-based scheme for recognizing and beautifying online hand-drawn sketches of electric diagrams is presented. The system uses a structural and topological relations matching mechanism that allows scale, translation, rotation i...
 
Reduction of the Classification Cost Using Hierarchical Classifiers based on the k-NN Rule
Found in: Document Analysis and Recognition, International Conference on
By Xiangyun Ye,Mohamed Cheriet,Ching Y. Suen
Issue Date:September 2001
pp. 0716
Abstract: Although promising results on the combination of character recognizers have been reported recently, the combination strategies can not be readily applied to the recognition of character strings due to m-n correspondence problems caused by segment...
 
Model-Based Character Extraction from Complex Backgrounds
Found in: Document Analysis and Recognition, International Conference on
By Xiangyun Ye, Mohamed Cheriet, Ching Y. Suen
Issue Date:September 1999
pp. 511
This paper proposes a model-based character extraction method. We model a pixel belonging to a character as a double-edge, whose range is defined by the stroke width, and whose intensity is proportional to the local contrast. By extracting such double-edge...
 
Environment-aware Virtual Slice Provisioning in Green Cloud Environment
Found in: IEEE Transactions on Services Computing
By Kim Khoa Nguyen,Mohamed Cheriet
Issue Date:February 2015
pp. 1
Environmental footprint resulting from datacenters activities can be reduced by both energy efficiency and renewable energy in a complementary fashion thanks to cloud computing paradigms. In a cloud hosting multi-tenant applications, virtual service provid...
 
Virtual Slice Assignment in Large-Scale Cloud Interconnects
Found in: IEEE Internet Computing
By Kim-Khoa Nguyen,Mohamed Cheriet,Yves Lemieux
Issue Date:July 2014
pp. 37-46
Software-defined networking is an emerging method for providing flexible and scalable network connectivity in both intra- and inter-datacenter interconnects with regard to various requirements, including traffic-awareness, quality of service, energy effici...
 
An Empirical Evaluation of Supervised Dimensionality Reduction for Recognition
Found in: 2013 12th International Conference on Document Analysis and Recognition (ICDAR)
By Guoqiang Zhong,Youssouf Chherawala,Mohamed Cheriet
Issue Date:August 2013
pp. 1315-1319
In the literature, many dimensionality reduction methods have been proposed and applied to recognition tasks, including handwritten digits recognition, character recognition and string recognition. However, it is usually difficult for the researchers to de...
 
Automatic Reading of Cursive Scripts Using Human Knowledge
Found in: Document Analysis and Recognition, International Conference on
By Myriam Coté, Mohamed Cheriet, Eric Lecolinet, Chin Y. Suen
Issue Date:August 1997
pp. 107
This paper presents a model for reading cursive script which has an architecture inspired by a reading model and which is based on perceptual concepts. We limit the scope of our study to the off-line recognition of isolated cursive words. First of all, we ...
 
 1