Modified Conditional Generative Adversarial Network-Based Optical Blur Restoration for Finger-Vein Recognition

Abstract

Among the existing biometrics methods, finger-vein recognition is beneficial because finger-veins patterns are locate under the skin and thus difficult to forge. Moreover, user convenience is high because non-invasive image capturing devices are used for recognition. In real environments, however, optical blur can occur while capturing finger-vein images du to both skin scattering blur caused by light scattering in the skin layer and lens focus mismatch caused by finger movement. The blurred images generated in this manner can cause severe performance degradation for finger-vein recognition. The majority of the previous studies addressed the restoration method o skin scattering blurred images; however, only limited studies have addressed the restoration of optically blurred images. Even the previous studies on the restoration of optical blur restoration have performed restoration based on the estimation of the accurate point spread function (PSF) for a specific image-capturing device. Thus, it is difficult to apply these methods to finger-vein images acquired by different devices. To address this problem, this paperproposes a new method for restoring optically blurred finger-vei images using a modified conditional generative adversarial network (conditional GAN) and recognizing the restored finger-vein images using a deep convolutional neural network (CNN). The results of the experiment performed using two open databases, the Shandong University homologous multimodal traits (SDUMLA-HMT) finger-vein database and Hong Kong Polytechnic University finger-image database (version 1) confirmed that the proposed method outperforms the existing methods. INDEX TERMS Finger-vein recognition, optical blur image restoration, modified conditional GAN, CNN.

Restoration of Motion Blurred Image by Modified DeblurGAN for Enhancing the Accuracies of Finger-Vein Recognition

“…However, this method requires that parameters should be accurately predicted when measuring two PSFs to improve performance, causing extensive processing time. Choi et al [ 11 ] proposed a finger-vein recognition method by restoring the optical blur included in the original finger-vein image based on modified conditional GAN. This method has the advantage that it can be applied to images acquired from various environments but has the disadvantage that it does not consider more complex motion blur that can occur during image acquisition.…”

“…Therefore, image restoration through a deblurring method is necessary. Extensive research has been conducted for restoring skin scattering blur that occurs frequently [ 2 , 3 , 4 , 5 , 6 , 7 , 8 , 9 ], and several studies have been conducted on optical blur caused by the difference in the distance from a camera lens to the finger vein and finger thickness [ 10 , 11 ]. Motion blur can occur frequently, due to finger movement.…”

A Novel Finger Vein Recognition Method Based on Aggregation of Radon-Like Features

“…Recently, some more powerful but complex network models, such as Siamese Network [ 46 ], GaborPCA Network [ 47 , 48 ], Convolutional Autoencoder [ 49 ], Capsule Network [ 50 ], DenseNet [ 51 , 52 ], Fully Convolutional Network (FCN) [ 53 , 54 ], Generative Adversarial Network (GAN) [ 55 , 56 , 57 ], and Long Short-term Memory (LSTM) Network [ 58 ], etc., also emerged in the field of FV image recognition. Especially for the GAN, which can not only achieve more robust vein patterns from low-quality FV images, but also generate a variety of synthetic FV samples.…”

Finger-Vein Pattern Restoration With Generative Adversarial Network

“…In these approaches, the vein network is segmented and stored in a binary image and then the minutiae features are extracted from resulting binary image. Unfortunately, finger-vein image quality is inherently affected by a number of factors: environmental illumination [17], [18], [19], ambient temperature [4], [19], [20], light scattering in imaging finger tissues [21], [22], [23], [24]. These factors are impossible to be controlled and/or avoided in practical applications, so the vein verification system generates some low quality images where the separability between the vein and non-vein patterns is poor or some vein patterns are corrupted.…”

“…For example, the work designs a depth-dependent point spread function (PSF), based on which a scattering suppression method was proposed using transcutaneous fluorescent imaging to restore vein patterns. Similarly, some optical model [22], [23], [24] are employed to remove light scattering occurrence in biological tissue during imaging.…”