An Adaptive CNNs Technology for Robust Iris Segmentation

Abstract

Iris segmentation algorithms are of great significance in complete iris recognition systems, and directly affect the iris verification and recognition results. However, the conventional iris segmentation algorithms have poor adaptability and are not sufficiently robust when applied to noisy iris databases captured under unconstrained conditions. In addition, there are currently no large iris databases; thus, the iris segmentation algorithms cannot maximize the benefits of convolutional neural networks (CNNs). The main work of this paper is as follows: first, we propose an architecture based on CNNs combined with dense blocks for iris segmentation, referred to as a dense-fully convolutional network (DFCN), and adopt some popular optimizer methods, such as batch normalization (BN) and dropout. Second, because the public ground-truth masks of the CASIA-Interval-v4 and IITD iris databases do not include the labeled eyelash regions, we label these regions that occlude the iris regions using the Labelme software package. Finally, the promising results of experiments based on the CASIA-Interval-v4, IITD, and UBIRIS.V2 iris databases captured under different conditions reveal that the iris segmentation network proposed in this paper outperforms all of the conventional and most of the CNN-based iris segmentation algorithms with which we compared our algorithm's results in terms of various metrics, including the accuracy, precision, recall, f1 score, and nice1 and nice2 error scores, reflecting the robustness of our proposed network. INDEX TERMS CNNs, dense block, dense-fully convolutional network, iris segmentation.

Novel Optimization Based Hybrid Self-Organizing Map Classifiers for Iris Image Recognition

“…To bridge the gap of power consumption of Graphical Processing Unit (GPUs) and to support energy efficient biometric system, authors in the article [15] have adapted parallelism in executing the recognition operation. A few other machine learning aspects of iris recognition are detailed in articles [16][17][18][19][20][21][22][23].…”

Hybrid Iris Segmentation Method Based on CNN and Principal Curvatures

“…4). Binary cross-entropy is used as a loss function, the Jacquard measure is used as a metric [16], the Adam optimizer [17] for optimization.…”

Robust Iris Segmentation Algorithm in Non-Cooperative Environments Using Interleaved Residual U-Net

“…Iris recognition has been determined as the most accurate and reliable biometric identification approach and thus it has been deployed in several applications such as identification and authentication systems, intelligent key systems, digital forensics, and border control [ 1 , 2 , 3 , 4 ]. An iris comprises a large amount of distinctive, constant, and forgery-proof features such as complex textures and explicit structural information for biometric identification [ 5 , 6 ]. In addition to this, iris traits are stable and remain unchanged throughout a person’s lifetime [ 7 ].…”

“…A common iris recognition system often consists of the following procedures: Iris image acquisition, iris image pre-processing, iris segmentation, iris feature extraction, and feature matching for identification or authentication [ 1 , 3 , 4 , 6 , 10 ]. In the iris recognition system, iris segmentation is a critical and challenging task because of the unpredictable and irregular shape of the iris [ 4 , 7 ].…”

“…In most cases, the occluded iris area (e.g., eyelids or eyelashes, eyeglasses, poor illuminations, and motion blurs) would greatly influence the overall accuracy of iris segmentation algorithms. Previous studies have shown that the error produced in the iris segmentation step is transmitted into all following phases of the iris recognition, so iris boundary estimation is still a very important pre-processing stage for achieving the high accuracy of the system [ 1 , 2 , 4 , 6 ].…”