The master’s student Nasreen Muzihr Mujahid presented her thesis under the supervision of Assistant Professor Dr. Ali Mohsen Mohammed.
The study aimed to design a precise biometric system that effectively identifies individuals through captured iris images. This system finds applications in various fields, including security and national identity programs, ensuring person identification. The iris was chosen due to its unique, unchanging, and protected features from external factors. Differences exist between the irises of the right and left eyes, even for twins.

The study proposed two models to enhance iris recognition performance across different spectra. Pre-processing of iris images captured in various fields, whether near-infrared (NIR) or visible light (VIS), was done using DCT-Normalization to reduce lighting variations. Relevant features were extracted using the Histogram of Oriented Gradients (HOG) approach for both NIR and VIS images.
The first model utilized Linear Discriminant Analysis (LDA) to reduce high-dimensional data. The second model employed Firefly Algorithm (FA) for feature selection, achieving high accuracy with fewer features. The selected features were then used for classification.

Experimental results were conducted on the PolyU bi-spectral images database from Hong Kong Polytechnic University, containing 209 individuals with different optical spectra for both eyes. The proposed approach exhibited exceptional matching performance and excellent accuracy across various fields. The proposed models achieved the highest results (99.25%, 97.35%) on the 12,540 images in the database, surpassing global research efforts. Additionally, the proposed approach incurred significantly lower computational costs compared to deep learning techniques, reducing the overall complexity of the recognition system and making it suitable for practical applications.

The thesis was accepted with an excellent.