NAS-QDCNN: NEURON ATTENTION STAGE-BY-STAGE QUANTUM DILATED CONVOLUTIONAL NEURAL NETWORK FOR IRIS RECOGNITION AT A DISTANCE

Biometric identification has become a vital approach for ensuring information security. Identifying persons on the basis of their biometric features is a major aspect of identification technology. Iris recognition (IR) is useful for recognizing persons and several iris recognition at-a-distance (IAAD) systems have been introduced for extracting iris features and improving iris image quality in biometric systems. Moreover, despite higher quality images, accuracy is the major challenging problem. To bridge this gap, neuron attention stage-by-stage quantum dilated convolutional neural network (NAS-QDCNN) is developed here for IAAD using iris images. Then, iris images are preprocessed employing the Kalman filtering and region of interest (ROI) extraction technique. After preprocessing, the segmentation process is conducted utilizing the Daugman rubber sheet model. Then, the feature extraction process is conducted on segmented iris images by extracting features, such as fast retina keypoint (FREAK) and gray-level co-occurrence matrix (GLCM). Based on the extracted features, IR is performed at a distance using the NAS-QDCNN method, which is the combination of neuron attention stage-by-stage net (NASNet) and quantum dilated convolutional neural network (QDCNN). It is noticed that NAS-QDCNN has gained a high accuracy of 96.838%, and minimum false rejection rate (FRR) of 0.311% and a false acceptance range (FAR) of 0.453%. The NAS-QDCNN method effectively enhances IR making it a promising solution for biometric identification systems.