Real time Arabic translation system for signboard images based on printed character recognition

العناوين الأخرى

نظام الترجمة العربي الآني لصور اللوحات الإعلانية بالاعتماد على تمييز الحروف المطبوعة

مقدم أطروحة جامعية

al-Sharari, Shuruq al-Mamun Fayiz

مشرف أطروحة جامعية

al-Hashimi, Rafiq Abd al-Rahman A.

أعضاء اللجنة

al-Zubaydi, Rashid
Uwayyid, Husayn

الجامعة

جامعة الشرق الأوسط

الكلية

كلية تكنولوجيا المعلومات

القسم الأكاديمي

قسم علم الحاسوب

دولة الجامعة

الأردن

الدرجة العلمية

ماجستير

تاريخ الدرجة العلمية

2013

الملخص الإنجليزي

In spite of the diversity in products of translation text embedded in images for many languages but for Arabic texts there are problems seem to be not yet well solved to address this problem.

In this thesis we developed a new system that will automatically translate Arabic text embedded in images into English.

This system consists of four subsystems: preprocessing, segmentation (text detection), character recognition and translation.

Dealing with Arabic language was the most important problem faced by the proposed system because it has a set of characteristics makes the identification very difficult, such as words interrelated.

In additional there are more than one form character and although the system achieve satisfactory results in dealing with the Arabic language and get an excellent translation through improving the quality of the entered image to the system.

The system automatically detect the text in the image and we applied Template matching algorithm to recognize the Arabic character.

Our proposal system works good with different backgrounds, rotated images, skewed, font sizes and blurred images.

The proposed system has been tested on samples of 25 images selected from signboard in street and showed promising experimental results within the limits of the system, which is the font size 40, font type (ALNSKH).

The system was assessed using recall measurement to evaluate the performance of the developed system and the experimental results of character recognition show a rate of 81.82%, the word recognition subsystem gave a rate of (94.44%) and the word translation was about (83.33%).

التخصصات الرئيسية

تكنولوجيا المعلومات وعلم الحاسوب

عدد الصفحات

63

قائمة المحتويات

• APA
• MLA
• AMA

لغة النص

الإنجليزية

نوع البيانات

رسائل جامعية

رقم السجل

BIM-699680