College of Engineering

A master thesis was discussed in Department of Computer Engineering / College of Engineering at University of Mosul entitled “Enhancement of Iris Recognition system using Deep learning in Image Segmentation” submitted by (Ruaa Waleed Jalal), Supervised ByAsst. Prof. Dr. Mayada Faris Ghanimon Sunday, June 06, 2022.The thesis presented a deep learning technique for improving iris segmentation performance called SegNet, which performs joint semantic segmentation of ocular qualities (iris and pupil) with greater accuracy in unconstrained scenarios. Specular reflections, eye contact, off-angle shots, low resolution, and various occlusions, particularly due to eyelids and eyelashes, are visible in the images captured in these scenarios. These difficult circumstances limit the performance and dependability of ocular segmentation structures.Segmentation begins by denoising the original image with a deep convolutional neural network to address these issues (DCNN). The semantic segmentation of the iris and pupil is then accomplished with the help of a densely connected fully convolutional encoder-decoder network.Finally, for feature extraction and classification, the proposed system is implemented using a pre-trained convolutional neural network (Alex Net).The results show that the used system has good performance in terms of accuracy and execution speed (comparing with state of art as shown in chapter four), so it can be depended and the user would not be inconvenienced while using it.