Time filter

Source Type

Fès, Morocco

Ennaji A.,Fez University | Aarab A.,Fez University | Khaissidi G.,University of Pau and Pays de lAdour
International Review on Computers and Software

This paper proposes a new approach for automatic and effective segmentation of dermoscopic images. The method of segmentation is based on a pre-processing using the color structure-texture image decomposition based on Partial Differential Equations, and a step of segmentation by fuzzy clustering based algorithm. The proposed approach has been implemented and compared with other recent algorithms for dermoscopic image segmentation in order to demonstrate sufficiently good results, the proposed technique was be evaluated as performance for lesion detection in dermoscopic images, and the results are 78% of specificity, 99% of sensitivity and 0.99 of the AUC metric. © 2014 Praise Worthy Prize S.r.l. - All rights reserved. Source

El Moubtahij H.,University Sidi Mohammed Ben Abdellah | Halli A.,Fez University | Satori K.,Fez University
International Review on Computers and Software

This Recognition of Arabic text handwritten awaits precise recognition solutions. There are a lot of difficulties facing a good handwritten Arabic recognition system such as unlimited variant in human handwriting, similarities of different character shapes, and their location in the word. This paper presents a handwriting Arabic text recognition system. It decomposes the text image into text line images and extracts a set of simple statistical features from a narrow window which is sliding a long that text line, then it injects the resulting feature vectors to the Hidden Markov Model Toolkit (HTK). HTK is a portable toolkit for speech recognition system. In recognized state, the concatenation of characters to form words is modelled by simple lexical models, each word is modelled by a stochastic finite-state automaton (SFSA), and the concatenation of words into sentences is modelled by an n-gram language model. The proposed system is applied to a data corpus constructed by Text lines examples from the “Arabic- Numbers”, which contains 1905 sentences and 47 words. This phrase is written by 5 different peoples. © 2014 Praise Worthy Prize S.r.l. - All rights reserved. Source

Serhier Z.,Hassan II University | Harzy T.,Hassan II University | ELfakir S.,Fez University | Diouny S.,Chouaib Doukkali University | And 4 more authors.
Rheumatology International

The aim of this study was to adapt the knee and hip osteoarthritis quality of life questionnaire (OAKHQoL)into Moroccan Arabic and to determine its psychometricproperties. After translation, back-translation and pretesting, the translated version was submitted to an expert committee. The psychometric properties were tested on patients with hip or knee osteoarthritis. Internal consistency was tested using Cronbach's alpha coefficient (α), and the test-retest reliability using intraclass correlation coefficients (ICC). Construct validity was assessed by examining item-convergent and divergent validity and by comparing the average scores between age groups and walk perimeter groups. The study was conducted on 131 patients (115 with osteoarthritis of the knee and 16 with osteoarthritis of the hip). The "physical activities" (α = 0.93), "mental health" (α = 0.84) and "pain" (α = 0.88) dimensions of the Arabic version were internally reliable. The ICC were adequate to good; 0.83 for "physical activities", 0.65 for "mental health" and 0.70 for "pain" dimensions. The instrument demonstrated good construct validity; all items exceeded the 0.4 criterion for convergent validity, except items 13 and 41 and most of the correlations between items and their own scale were significantly higher than their correlations with other scales. A semantically equivalent translation has been developed with cultural adaptation of OAKHQoL. It is quite reliable and a valid measure of the effect of osteoarthritis on the quality of life on Moroccan patients. © Springer-Verlag 2011. Source

El Fakir S.,Fez University | Serhier Z.,Fez University | Berraho M.,Fez University | Elrhazi K.,Fez University | And 3 more authors.
American Journal of Health Promotion

Purpose. To determine the association between income level and variations in knowledge and perceptions about tobacco smoking in Morocco. Design. Cross-sectional study. Setting. Random sample of 9195 subjects representative of the Moroccan population. Subjects. Subjects aged >15 years from households. Measures. Data were collected from selected households using a standardized questionnaire about smoking, educational level, household monthly income, and knowledge of health effects of smoking. Analysis. Stepwise logistic regression was used for multivariate analysis. Adjusted odds ratios with 95% confidence intervals for each variable were calculated as an estimate of the likelihood of having knowledge that smoking causes selected diseases. Results. Among 9195 subjects, 27.8% reported low income (<2000 Moroccan dirhams [MAD]), and 9.9% reported the highest income level (≥6000 MAD). Higher income was significantly associated with higher knowledge of health effects of smoking (p < .0001); 55% of low-income respondents compared to 71.5% of respondents with higher income knew about the relationship between cigarette smoking and cancer. Conclusions. Lower income level was associated with lower awareness of the harms of smoking. There is a need to improve knowledge of the dangers of smoking among the disadvantaged segments of the population. Copyright © 2011 by American Journal of Health Promotion, Inc. Source

Maqqor A.,Fez University | Maqqor A.,University Sidi Mohammed Ben Abdellah | Halli A.,Fez University | Halli A.,Moulay Ismai University | And 3 more authors.
International Review on Computers and Software

In this paper, we present a multi-classifier approach for off-line handwritten Arabic word recognition system. The main objective of this paper is to develop a handwriting recognition system that can be learned and applied to different Arabic writing styles. We propose an approach that combines multiple classifiers based on semi-continuous Hidden Markov Model using different feature extraction methods. The following process consists of several phases: pre-processing, extraction of pertinent characteristics and modeling. The role of the pre-processing phase is to prepare the input image text, i.e, binarization, normalization, segmentation and skeletonization. The obtained images are then used to extract features using a mixture of geometrical and statistical characteristics, namely, the intensities of gray level of the pixel, the densities and the concavities of the pixels, the VH2D projections and the invariants Hu moments. The modeling phase is based on the Hidden Markov Model using the HTK tools for the training and the recognition phase. Each character is modeled by a semi-continuous HMMs, and each set of feature has its own HMM. To improve the performance of our Arabic handwriting recognition system, we propose to combine parallel methods of HMMs having the same architecture, but training phase using four different types of primitive vectors. Our system was evaluated using the ENIT/IFN the base Arabic data. Results Obtained show that the combination of four semicontinuous HMM classifiers gives a significant improvement of our off-line handwriting recognition system compared to results obtained when using individual classifiers. © 2015 Praise Worthy Prize S.r.l. - All rights reserved. Source

Discover hidden collaborations