Master’s Thesis Defense at the College of Computer Science and Mathematics – Department of Computer Science for the student

(Tahir Ali Mahmoud)

A Master’s thesis was discussed in the Discussion Hall at the College of Computer Science and Mathematics, University of Mosul, on Thursday, 3/9/2026.

Master’s Thesis entitled:

“An Intelligent System for Extracting Text from Multilingual Images Using Deep Learning”

By the student: “Tahir Ali Mahmoud”
Supervised by: Asst. Prof. Dr. Yusra Faisal Mohammed

The thesis addressed: Developing an intelligent system for detecting and recognizing Arabic and English text in natural scene images using deep learning techniques.

The study discussed: Integrating Swin Transformer, FPN, and DBNet++ techniques for text detection, and Vision Transformer with PARSeq for bilingual text recognition and arranging the recognized text according to its reading direction.

The thesis aimed to: Develop, implement, and evaluate an integrated system for detecting and recognizing Arabic and English text in natural images. It also aimed to address the difference in reading direction between the two languages and achieve efficient performance using limited computational resources.

This thesis contributes to the following Sustainable Development Goals:

1. Quality Education.
2. Industry, Innovation and Infrastructure.
3. Reduced Inequalities, through supporting multilingual text processing and information accessibility technologies.

The discussion committee consists of

 

Prof. Dr. Baidaa Ibrahim Khalil                (Chairman)                 

Asst. Prof.  Hanan Hamed Ali                      (Member)

Dr. Tarfa Yassin Hamed                              (Member)

Asst. Prof. Dr. Yusra Faisal Mohammed    (Member and Supervisor)