IrisDenseNet: Robust Iris Segmentation Using Densely Connected Fully Convolutional Networks in the Images by Visible Light and Near-Infrared Light Camera Sensors

Abstract

The recent advancements in computer vision have opened new horizons for deploying biometric recognition algorithms in mobile and handheld devices. Similarly, iris recognition is now much needed in unconstraint scenarios with accuracy. These environments make the acquired iris image exhibit occlusion, low resolution, blur, unusual glint, ghost effect, and off-angles. The prevailing segmentation algorithms cannot cope with these constraints. In addition, owing to the unavailability of near-infrared (NIR) light, iris recognition in visible light environment makes the iris segmentation challenging with the noise of visible light. Deep learning with convolutional neural networks (CNN) has brought a considerable breakthrough in various applications. To address the iris segmentation issues in challenging situations by visible light and near-infrared light camera sensors, this paper proposes a densely connected fully convolutional network (IrisDenseNet), which can determine the true iris boundary even with inferior-quality images by using better information gradient flow between the dense blocks. In the experiments conducted, five datasets of visible light and NIR environments were used. For visible light environment, noisy iris challenge evaluation part-II (NICE-II selected from UBIRIS.v2 database) and mobile iris challenge evaluation (MICHE-I) datasets were used. For NIR environment, the institute of automation, Chinese academy of sciences (CASIA) v4.0 interval, CASIA v4.0 distance, and IIT Delhi v1.0 iris datasets were used. Experimental results showed the optimal segmentation of the proposed IrisDenseNet and its excellent performance over existing algorithms for all five datasets.

Unconstrained Iris Segmentation Using Convolutional Neural Networks

“…All inferences run on a laptop with an i7-7700HQ, 32GB DDR4 RAM, an NVidia GTX 1070. The IrisDenseNet [5] does not report its inference time but their work is based on the SegNet [6] which reports an forward pass time of 422ms with an image of dimension 360x480.…”

Special Issue on Visual Sensors

“…In [26], a video-based person re-identification method with hybrid deep appearance-temporal features is proposed. Another application using deep learning methods was presented by Arsalan et al [27]. The authors proposed a densely connected fully convolutional network, which can determine the true iris boundary even with inferior-quality images by using better information gradient flow between the dense blocks.…”

Entropy Based CNN for Segmentation of Noisy Color Eye Images using Color, Texture and Brightness Contour Features

“…al. [14] defined densely connected fully CNN for selecting accurate iris boundaries without preprocessing noisy eye images acquired invisible spectrum for non ideal environment. In paper [15], Liu et.…”

“…Performances of accuracy and average segmentation time for proposed entropy based CNN segmentation algorithm is compared with some other existing method [11][12][13][14][15][16][17][18]…”