@admissions.kfupm.edu.sa
Information and Computer Science Department
King Fahd University of Petroleum and Minerals
Computer Science, Artificial Intelligence, Education, Computer Science Applications
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Mohammed Yahia and Husni Al-Muhtaseb
Zarqa University
Datasets of text images are important for optical text recognition systems. Such datasets can be used to enhance performance and recognition rates. In this research work, we present a bilingual dataset consists of Arabic/English text images to address the lack of availability of bilingual text databases. The presented dataset consists of 97812 text images, which are categorized into two groups; Scanned page and digitized line images. Images of the two forms are written with 10 fonts and four sizes, and prepared/scanned with four dpi resolutions. The dataset preparation process includes text collection, text editing, image construction, and image processing. The dataset can be used in optical text recognition, optical font recognition, language identification, and segmentation. Different text recognition and language identification experiments have been conducted using images of the dataset and Hidden Markov Model (HMM) classifier. For the digitized images recognition experiments, the best-achieved recognition correctness is 99.01% and the best accuracy is 99.01%. The font that has the highest recognition rates was Tahoma. For the scanned images recognition experiments, Tahoma has also shown the highest performance with 97.86% for correctness and 97.73% for accuracy. For the language identification experiments, Tahoma has shown the performance with 99.98% for word-language identification rate.
Mohammed Alqmase and Husni Al-Muhtaseb
Springer Science and Business Media LLC
Mohammed Alqmase, Husni Al-Muhtaseb, and Habib Rabaan
Springer Science and Business Media LLC
Khalid M. O. Nahar, Mohammed Abu Shquier, Wasfi G. Al-Khatib, Husni Al-Muhtaseb, and Moustafa Elshafei
Springer Science and Business Media LLC
Khalid M.O. Nahar, Wasfi G. Al-Khatib, Moustafa Elshafei, Husni Al-Muhtaseb, and Mansour M. Alghamdi
IEEE
In this paper, we investigated the use of Learning Vector Quantization (LVQ) for phoneme transcription in Arabic speech recognition systems. We used Arabic speech corpus of TV news clips. Then, we employed feature vectors, which embed the frame neighboring correlation information between adjacent phonemes to replace the traditional trip hones models. Next, we generated the phonemes codebooks using the K-means splitting algorithm. After that, we trained the generated codebooks using the LVQ algorithm. When using the trained LVQ codebooks in utterance phoneme transcription of an open vocabulary test corpus, the phoneme recognition rate was 72% without the use of any added phoneme big rams or HMM models. The results of this research if improved could be used to serve the holy Quran text transcription without any phonemes big rams (phonemes language model). This would increase the speed of the Quranic speech to text transcription and creates the infrastructure of suitable high speed automatic identification system of Quranic sounds recognition and translation.
K. M. O. Nahar, W. G. Al-Khatib, M. Elshafei, H. Al-Muhtaseb, and M. M. Alghamdi
IEEE
Continuous Arabic Speech Recognition, appears in many real life applications. Its speed, accuracy and improvement are highly dependent on the accuracy of the language phonemes set. The main goal of this research is to recognize and transcribe the Arabic phonemes based on a data-driven approach. We built a phoneme recognizer based on a data driven approach using HTK tool. Different numbers of Gaussian mixtures with different numbers of HMM states were used in modeling the Arabic phonemes in order to reach the best configuration. The corpus used consists of about 4000 files, representing 5 recorded hours of modern standard Arabic of TV-News. The maximum phoneme recognition accuracy reached was 56.79%. This result is very encouraging and shows the viability of our approach as compared to using a fixed number of HMM states.
Khalid M. O Nahar, Mustafa Elshafei, Wasfi G. Al-Khatib, Husni Al-Muhtaseb, and Mansour M. Alghamdi
Springer Berlin Heidelberg
Dia AbuZeina, Wasfi Al-Khatib, Moustafa Elshafei, and Husni Al-Muhtaseb
Springer Science and Business Media LLC
Husni Al-Muhtaseb and Rami Qahwaji
IGI Global
Arabic text recognition is receiving more attentions from both Arabic and non-Arabic-speaking researchers. This chapter provides a general overview of the state-of-the-art in Arabic Optical Character Recognition (OCR) and the associated text recognition technology. It also investigates the characteristics of the Arabic language with respect to OCR and discusses related research on the different phases of text recognition including: pre-processing and text segmentation, common feature extraction techniques, classification methods and post-processing techniques. Moreover, the chapter discusses the available databases for Arabic OCR research and lists the available commercial Software. Finally, it explores the challenges related to Arabic OCR and discusses possible future trends.
Dia AbuZeina, Wasfi Al-Khatib, Moustafa Elshafei, and Husni Al-Muhtaseb
Springer Science and Business Media LLC
Dia AbuZeina, Wasfi Al-Khatib, Moustafa Elshafei, and Husni Al-Muhtaseb
Springer Science and Business Media LLC
Jawad H AlKhateeb, Jinchang Ren, Jianmin Jiang, and Husni Al-Muhtaseb
Elsevier BV
Mohamed Ali, Moustafa Elshafei, Mansour Al-Ghamdi, Husni Al-Muhtaseb, and Atef Al-Najjar
IEEE
Phonetic dictionaries are essential components of large-vocabulary natural language speaker-independent speech recognition systems. This paper presents a rule-based technique to generate Arabic phonetic dictionaries for a large vocabulary speech recognition system. The system used classic Arabic pronunciation rules, common pronunciation rules of Modern Standard Arabic, as well as morphologically driven rules. The paper gives in detail an explanation of these rules as well as their formal mathematical presentation. The rules were used to generate a dictionary for a 5.4 hours corpus of broadcast news. The phonetic dictionary contains 23,841 definitions corresponding to about 14232 words. The generated dictionary was evaluated on an actual Arabic speech recognition system. The pronunciation rules and the phone set were validated by test cases. The Arabic speech recognition system achieves word error rate of %11.71 for fully diacritized transcription of about 1.1 hours of Arabic broadcast news.
Husni A. Al-Muhtaseb, Sabri A. Mahmoud, and Rami S. Qahwaji
Elsevier BV
Mansour Alghamdi, Moustafa Elshafei, and Husni Al-Muhtaseb
Springer Science and Business Media LLC
M Elshafei
Elsevier BV
A.A. Amin, M.Y. Osman, R.E. Abdel-Aal, and H. Al-Muhtaseb
Institute of Electrical and Electronics Engineers (IEEE)
The testability problem of dual-port memories is investigated. A functional model is defined, and architectural modifications to enhance the testability of such chips are described. These modifications allow multiple access of memory cells for increased test speed with minimal overhead on both silicon area and device performance. New fault models are proposed, and efficient O(/spl radic/n) test algorithms are described for both the memory array and the address decoders. The new fault models account for the simultaneous dual-access property of the device. In addition to the classical static neighborhood pattern-sensitive faults, the array test algorithm covers a new class of pattern sensitive faults, duplex dynamic neighborhood pattern-sensitive faults (DDNPSF).