The student Zainab Hashim Fattouhi received her master's degree from the Department of Computer Sciences / University of Technology for her thesis titled (System for identifying the retina based on the machine learning descriptor). The proposed system benefited from two of the characteristics of the local characteristics effective for detecting and extracting the characteristics of the retina in order to use These characteristics indicate the identity of the person. The proposed identification system consists of three stages: extraction of the vascular pattern in the retina, extraction of local characteristics and matching of these characteristics. The stage of the extraction of blood vessels was done using many techniques of filtering and cutting images to produce a binary image consisting of blood vessels only so that the algorithm can be implemented to extract the characteristics proposed later. For the extraction phase, an algorithm was proposed to extract the properties of the retina, which is the combination of two local descriptors, SURF and BRISK. The features of these two descriptors were used to produce a faster and more accurate extraction algorithm than the classical descriptors, These features are important for real-time applications, which usually require rapid processing of an increasing amount of data. For the matching phase, FANN was used to match the properties extracted with the properties in the database. This was on Tuesday, 18/12/2018, and on the discussion room in the building of the department. The discussion committee was composed of Prof. Dr. Aliaa Karim Abdel Hassan and Prof. Nada Falih Hassan from the University of Technology / Computer Sciences Department And Prof. Dr. Raghd Abdel Aziz from the University of Baghdad / Ibn Rushd College of Education / Department of Computer Science / Department of Computer Science in the presence of the supervisor of the student (Dr Matheel Emad Eddin Abdel Moneim).

Download Abstract