Showing papers by "Aly A. Fahmy published in 2008"

Enhancing English/Arabic CLIR Using Word Collocations and Statistical Translation and Transliteration Resources

Abstract: In Cross Language Information Retrieval (CLIR), queries in one language retrieve documents in other language(s). This can be done through Query Translation that comes up against Translation/Transliteration challenges like ambiguity as the main problems. In this paper, a comprehensive solution has been introduced for these challenges. 1 st , 4 powerful English/Arabic Machine Readable Dictionaries (MRD) from English to Arabic, including a dictionary for collocations and 3 dictionaries for single English words that have been introduced from different perspectives, aiming to examine the effect of each perspective on the final query result. 2 nd , A modern Arabic Corpus has been built. 3 rd , a comprehensive model for Query Translation from English to Arabic that detects and translates collocations, single words translation and transliteration, and solves the replacement ambiguity, has been introduced. The experiments' results proved that the proposed models are very effective overcoming the Query Translation and CLIR challenges.

A multi-agent model for face recognition using multi-featurs and multi-classifiers

Abstract: :This paper presents a new model based on multi-agent technology for face recognitionusing multi-features and multi-classifiers. The human faces are verified by projectingface images onto a feature space that spans the significant variations among knownfaces by computing the discrete cosine transform (DCT) and discrete wavelettransform (DWT) features. The classifiers used in this research namely, K-nearestneighbor (K-NN), neural network (NN), support vector machine (SVM), BayesNet,classification and regression tree (CART), and decision tree algorithm (C4.5). Theexperimental results using these classifiers individually show that the recognition rateis up to 95% on the Olivetti Research Laboratory (ORL) database of facial images[14]. To improve the performance of the model, the classifier with the highestrecognition rate is correlated with other classifiers to select the most suitablecomplementary group of classifiers that give a high recognition rate. Each classifier inthe group is represented by agent in a multi-agent system. An average of 97%recognition rate is reached using K-NN, NN, and CART. Again, to improve theperformance of the model, each classifier in the agents group is applied on the DCTfeature vector and if the recognized face is not matched with the personal informationdatabase then it is applied on the DWT feature vector. The experimental resultsshowed that the recognition rate using this model is up to 99.5%.