College of Computer Science and Mathematics

Discussion of a master’s thesis in the College of Computer Science and Mathematics – Department of Software

Titled (Develop an API Third-party software to enhance photo documents for integration with The University of Mosul platforms (

In continuation of the scientific research movement and with the follow-up and attendance of the Dean of the College of Computer Science and Mathematics, Professor Dr. Dhuha Bashir Abdullah, the respected

The discussion hall at the College of Computer Science and Mathematics at the University of Mosul on

17/9/2024

The master’s thesis (Develop an API Third-party software to enhance photo documents for integration with The University of Mosul platforms) was discussed by the student Nisreen Nizar Raouf and supervised by Assist. Prof. Dr. Mohammad Abdulghani Taha.

• The thesis submitted by the student Nisreen Nizar Raouf presents a detailed approach to accelerating document image processing for the data center at the University of Mosul and evaluating image quality using a cloud platform. The methodology consists of two main phases: First, the integration phase is completed by connecting the university’s data center to the cloud platform using FastAPI, ensuring smooth data exchange with full security and the simultaneous optimization of all technologies involved. Second, in the cloud platform phase, the user uploads the document to system (X), which then sends the document and its type to the image enhancement server. The images are first normalized according to the document type, and image comparison is carried out using the correlation coefficient and the Histogram of Oriented Gradients (HOG) method. Additionally, distorted images are enhanced using the Fast Library for Approximate Nearest Neighbors (FLANN) algorithm, and image sharpness is improved using the Laplacian sharpening filter based on the nature of the image with appropriate tools and formulas. The image enhancement server then sends the improved document image and a similarity score back to system X, with the option to reject images that do not meet the required specifications.
• The study evaluated various algorithms and methods, including feature extraction techniques, document enhancement algorithms, and image similarity measurement algorithms, selecting the best ones to integrate into the proposed platform. The thesis highlights the benefits of applying these methods in cloud environments. The proposed platform demonstrates high efficiency in information exchange and accurate document image analysis within the university’s data center.
• Currently, the platform is operational within the University of Mosul’s Computer Center systems.

The discussion committee consisted of:

Prof. Dr. Shahba Ibrahim Khalil/ University of Mosul / College of Computer Science and Mathematics – Chairman

Assistant Professor Dr. Nada Nehme Selim/ University of Mosul / College of Computer Science and Mathematics – Member

Assistant Professor Dr. Sondos Khalil Ibrahim/ University of Mosul / College of Computer Science and Mathematics – Member

Assistant Professor Dr. Muhammad Abdel Ghani Taha/ University of Mosul / College of Computer Science and Mathematics – Member and Supervisor