Special Issue on Selected Papers from Third international symposium on Automatic Amazigh processing SITACAM13

1

Application of Data Mining Tools for Recognition of Tifinagh Characters

Author 1: M. OUJAOURA Author 2: R. EL AYACHI Author 3: O. BENCHAREF Author 4: Y. CHIHAB Author 5: B. JARMOUNI

The majority of Tifinagh OCR presented in the literature does not exceed the scope of simulation software such as Matlab. In this work, the objective is to compare the classification data mining tool for Tifinagh character recognition. This comparison is performed in a working environment using an Oracle database and Oracle Data Mining tools (ODM) to determine the algorithms that gives the best Recognition rates (rate / time).

OCR Data Mining Classification Recognition Tifinagh geodesic descriptors Zernike Moments CART AdaBoost KNN SVM RNA ANFIS

Abstract doi.org/10.14569/SpecialIssue.2013.030201 PDF

2

Annotation and research of pedagogical documents in a platform of e-learning based on Semantic Web

Author 1: S. BOUKIL Author 2: C. DAOUI Author 3: B. BOUIKHALENE Author 4: M.FAKIR

E-learning is considered as one of the areas in which the Semantic Web can make a real improvement whatsoever in finding information, or reusing of educational resources or even personalized learning paths. This paper aimsto develop an educational ontology that will be used to annotate learning materials and pedagogical documents.

Ontologie Web sémantique XML RDF RDFS OWL métadonnées enseignement à distance.

Abstract doi.org/10.14569/SpecialIssue.2013.030202 PDF

3

Hierarchical Algorithm for Hidden Markov Model

Author 1: SANAA CHAFIK Author 2: DAOUI CHERKI

The Forward algorithm is an inference algorithm for hidden Markov models, which often leads to a very large hidden state space. The objective of this work is to reduce the task of solving the Forward algorithm, by offering faster improved algorithm which is based on divide and conquer technique.

Hidden Markov Model Forward Divide and Conquer Decomposition Communicating Class.

Abstract doi.org/10.14569/SpecialIssue.2013.030203 PDF

4

Review of Color Image Segmentation

Author 1: Abderrahmane ELBALAOUI Author 2: M.FAKIR Author 3: N.IDRISSI Author 4: A.MERBOUHA

This paper provides a review of methods advanced in the past few years for segmentation of color images. After a brief definition of the segmentation, we outline the various existing techniques, classified according to their approaches. We have identified five that are based approaches contours, those relying on notion of region, structural approaches, those based on the form and then using those notions of graphs. For each of these approaches, we then explained and illustrated their most important methods. This review is not intended to be exhaustive and the classification of certain methods may be discussed since at the boundary between different approaches.

Image segmentation k-means region and Boundary.

Abstract doi.org/10.14569/SpecialIssue.2013.030204 PDF

5

Invariant Descriptors and Classifiers Combination for Recognition of Isolated Printed Tifinagh Characters

Author 1: M. OUJAOURA Author 2: R. EL AYACHI Author 3: B. MINAOUI Author 4: M. FAKIR Author 5: B. BOUIKHALENE Author 6: O. BENCHAREF

In order to improve the recognition rate, this document proposes an automatic system to recognize isolated printed Tifinagh characters by using a fusion of 3 classifiers and a combination of some features extraction methods. The Legendre moments, Zernike moments and Hu moments are used as descriptors in the features extraction phase due to their invariance to translation, rotation and scaling changes. In the classification phase, the neural network, the multiclass SVM (Support Vector Machine) and the nearest neighbour classifiers are combined together. The experimental results of each single features extraction method and each single classification method are compared with our approach to show its robustness.

Recognition system Legendre moments Zernike moment Hu moments Neural Networks Multiclass SVM nearest neighbour classifier

Abstract doi.org/10.14569/SpecialIssue.2013.030205 PDF

6

Handwritten Tifinagh Text Recognition Using Fuzzy K-NN and Bi-gram Language Model

Author 1: Said Gounane Author 2: Mohammad Fakir Author 3: Belaid Bouikhalen

In this paper we present a new approach in Tifinagh character recognition using a combination of, k-nearest neighbor algorithm and the bigram language model. After the preprocessing of the text image, and the word segmentation, for each image character, the k-NN algorithm proposes candidates weighted of their membership degree. Then we use the bigram language model to choose the most appropriate sequence of characters. Results show that our method increases the recognition rate.

Tifinagh character recognition fuzzy k-nearest neighbor features extraction bigram language model.

Abstract doi.org/10.14569/SpecialIssue.2013.030206 PDF

7

Performance evaluation of ad hoc routing protocols in VANETs

Author 1: Mohammed ERRITALI Author 2: Bouabid El Ouahidi

The objective of this work is to compare with simulating, using OPNET the performance of five Ad hoc routing protocols: DSR, AODV, OLSR ,TORA and GRP , and to examine the impact of mobility and the density of nodes on the behavior of these protocols in a Vehicular Ad hoc NETwork (VANET). The results show that there is not a protocol that is favorite for all evaluation criteria. Indeed, each protocol has different behavior in relation to performance metrics considered, including the rate of routing packets sent, delay, and the debit.

Routing protocols OPNET Performance evaluation DSR AODV OLSR TORA GRP.

Abstract doi.org/10.14569/SpecialIssue.2013.030207 PDF

8

Recognition of Amazigh characters using SURF & GIST descriptors

Author 1: H. Moudni Author 2: M. Er-rouidi Author 3: M. Oujaoura Author 4: O. Bencharef

In this article, we describe the recognition system of Amazigh handwritten letters. The SURF descriptor, specifically the SURF-36, and the GIST descriptor are used for extracting feature vectors of each letter from our database which consists of 25740 manuscripts isolated Amazigh characters. All the feature vectors of each letter form a training set which is used to train the neural network so that it can calculate a single output on the information it receives. Finally, we made a comparative study between the SURF-36 descriptor and GIST descriptor.

SURF GIST Principal Component Analysis Neural Network Amazigh Characters.

Abstract doi.org/10.14569/SpecialIssue.2013.030208 PDF

9

Printed Arabic Character Classification Using Cadre of Level Feature Extraction Technique

Author 1: S. Nouri Author 2: M.Fakir

Feature extraction techniques is important in character recognition, because they can enhance the efficacy of recognition in comparison to other approaches. This study aims to investigate the novel feature extraction technique called the Cadre of Level technique in order to represent printed characters and digits. This technique gives statistic and morphologic information, i.e. the calculation is based on a statistical approach but in the positions which can give some information about the morphologic of character. The image of a character is divided into 100 zones, then for each zone we average 5 extracted values (one value for each level) to 1 value for each zone, which gives 100 features for each character. This technique was applied to 105 different characters and 10 different digits of Arabic printed script. K-Nearest Neighbor algorithm was used to classify the printed characters and digits.

Arabic Character Cadre of Level Recognition K-Nearest Neighbor Digits.

Abstract doi.org/10.14569/SpecialIssue.2013.030209 PDF

Contact Info

Follow Us