Application of Blind Deblurring Algorithm for Iris Biometric

Alaoui, F. Taia; Assid, K.; Dembele, V.; Nassim, Abdelkrim

doi:10.5120/13720-1509

Cited by 5 publications

(5 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Blurred samples along with their clean samples are shown in Figure 1. Table 1 shows 1 Dataset available on request to authors. the results of the verification experiment performed on the blurred data and the same experiment performed on the deblurred data.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

FDeblur-GAN: Fingerprint Deblurring using Generative Adversarial Network

Joshi¹,

Dabouei²,

Dawson³

et al. 2021

Preprint

View full text Add to dashboard Cite

While working with fingerprint images acquired from crime scenes, mobile cameras, or low-quality sensors, it becomes difficult for automated identification systems to verify the identity due to image blur and distortion. We propose a fingerprint deblurring model FDeblur-GAN, based on the conditional Generative Adversarial Networks (cGANs) and multi-stage framework of the stack GAN. Additionally, we integrate two auxiliary sub-networks into the model for the deblurring task. The first sub-network is a ridge extractor model. It is added to generate ridge maps to ensure that fingerprint information and minutiae are preserved in the deblurring process and prevent the model from generating erroneous minutiae. The second sub-network is a verifier that helps the generator to preserve the ID information during the generation process. Using a database of blurred fingerprints and corresponding ridge maps, the deep network learns to deblur from the input blurry samples. We evaluate the proposed method in combination with two different fingerprint matching algorithms. We achieved an accuracy of 95.18% on our fingerprint database for the task of matching deblurred and ground truth fingerprints.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Be that as it may, existing methods for deblurring of biometric images are mostly focused on other biometric traits such as iris [12], face [1], and hand-based biometric traits such as palm prints [23] or finger wrinkles [5]. Cho et al [5] proposed a GAN-based model for deblurring finger wrinkles for authentication.…”

Section: Related Workmentioning

confidence: 99%

FDeblur-GAN: Fingerprint Deblurring using Generative Adversarial Network

Joshi¹,

Dabouei²,

Dawson³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In [56], authors proposed iris deblurring algorithm for iris capture based on the domain knowledge inherent in iris images and iris capture settings to improve the performance. Alaoui et al proposed the method of motion deblurring of iris image to achieve a quality edge preserving image restoration using Total Variation (TV)-L1 regularization technique [57]. In [58], authors proposed iris image deblurring method to enhance the quality of blurred iris images based on refinement of point spread function.…”

Section: Deblurring Of Iris Imagesmentioning

confidence: 99%

Enhanced Iris Recognition Method by Generative Adversarial Network-Based Image Reconstruction

et al. 2021

View full text Add to dashboard Cite

“…Thus, researchers improved the images using a deblur method and then proceeded with the evaluation of the recognition performance. Alaoui et al [ 11 ] performed image blurring by applying point spread function (PSF) with the face recognition technology (FERET) database. The images were deblurred with fast total variation (TV)-l1 deconvolution, image features were obtained using PCA, and feature matching was performed with Euclidean distance.…”

Section: Related Workmentioning

confidence: 99%

Face and Body-Based Human Recognition by GAN-Based Blur Restoration

Koo

Cho

Baek

et al. 2020

Sensors

View full text Add to dashboard Cite

The long-distance recognition methods in indoor environments are commonly divided into two categories, namely face recognition and face and body recognition. Cameras are typically installed on ceilings for face recognition. Hence, it is difficult to obtain a front image of an individual. Therefore, in many studies, the face and body information of an individual are combined. However, the distance between the camera and an individual is closer in indoor environments than that in outdoor environments. Therefore, face information is distorted due to motion blur. Several studies have examined deblurring of face images. However, there is a paucity of studies on deblurring of body images. To tackle the blur problem, a recognition method is proposed wherein the blur of body and face images is restored using a generative adversarial network (GAN), and the features of face and body obtained using a deep convolutional neural network (CNN) are used to fuse the matching score. The database developed by us, Dongguk face and body dataset version 2 (DFB-DB2) and ChokePoint dataset, which is an open dataset, were used in this study. The equal error rate (EER) of human recognition in DFB-DB2 and ChokePoint dataset was 7.694% and 5.069%, respectively. The proposed method exhibited better results than the state-of-art methods.

show abstract

Application of Blind Deblurring Algorithm for Iris Biometric

Cited by 5 publications

References 53 publications

FDeblur-GAN: Fingerprint Deblurring using Generative Adversarial Network

FDeblur-GAN: Fingerprint Deblurring using Generative Adversarial Network

Enhanced Iris Recognition Method by Generative Adversarial Network-Based Image Reconstruction

Face and Body-Based Human Recognition by GAN-Based Blur Restoration

Contact Info

Product

Resources

About