Robust Face Recognition Under Partial Occlusion Based on Local Generic Features

Yadav, Amit; Gupta, Neeraj; Khan, Aamir; Jalal, Anand Singh

doi:10.4018/ijcini.20210701.oa4

Cited by 7 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2020, Qin et al proposed a morphing attack based on partial face manipulation to compromise the uniqueness of face templates using the most effective facial components (eyes and nose) [14]. In 2021, Yadav et al proposed an approach that utilizes local general features to recognize partially occluded faces and combines feature scale-invariant feature transform and multiblock local binary patterns [15].…”

Section: Related Workmentioning

confidence: 99%

Effect of Smaller Fingerprint Sensors on the Security of Fingerprint Authentication

Jeong,

Jeong

2023

IEEE Access

View full text Add to dashboard Cite

Small fingerprint sensors are necessary to be used in the small devices like smartphones, USBs, and cards. Different small devices have different sizes of fingerprint sensors. The scanned fingerprint image through a small fingerprint sensor is a partial fingerprint image instead of a whole fingerprint image, if we use a small fingerprint sensor. If the size of the partial fingerprints stored in the database decreases, the number of minutiae that are compared when matching decreases. Unfortunately, for the small number of minutiae, it is possible to construct "Masterprints". Masterprints can be used to impersonate multiple users stored in the database. If the size of a partial image is 15% of a whole image, a Masterprint can be produced. We investigate the vulnerability of various sizes of partial images due to the Masterprint. Because sensors have different sizes, we use partial images of 9% to 48% of a whole image. Our results show that the security of partial fingerprint authentication is severely affected by the sizes of partial images and sensors. The smaller the partial image size, the larger the impostor matching rate; and the smaller the false matching rates, the steeper the impostor matching rate increases.

show abstract

Section: Related Workmentioning

confidence: 99%

Effect of Smaller Fingerprint Sensors on the Security of Fingerprint Authentication

Jeong,

Jeong

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The onboarding process will face a holistic approach in its biometric system, more precisely, in the digital onboarding process, the state-of-the-art of EADS technology is based on the facial recognition system. Although there are several types of biometric captures that can be performed, some of them already known like the fingerprint 5 and some other more atypical ones like wrist vein images 6 – 8 or Finger-Knuckle-Print (FKP) 5 , 9 recognition, the facial biometrics has drawn significant attention due to its potential use in biometric authentication 10 as non-intrusive and simple way to capture the facial image of the customer.…”

Section: Soter Projectmentioning

confidence: 99%

Digital onboarding in finance: a novel model and related cybersecurity risks

García¹,

Venegas²,

Aguilera³

et al. 2022

Open Res Europe

View full text Add to dashboard Cite

Over the last few years, the financial sector has undergone a digital revolution that has had a severe impact on different related areas such as, the entities, the cybersecurity of systems, regulations and, of course, customers. SOTER project takes the challenge providing a complete set of tools to enhance the cybersecurity levels by implementing, in addition to non-technological tools, an innovative onboarding process has been implemented with the goals of increasing security, improving the user experience and integrity in the sector, and facilitating the customer entry into the digital marketplace by combining a set of breakthrough technologies. The cybersecurity research plays a crucial role in the conception and implementation of the onboarding process and for this kind of processes it has to be studied as an individual area by itself, as it is necessary to analyze the possible threats that can affect them, their origin and the solution(s) that can be taken to address them. Therefore, the SOTER project presents a fully digital onboarding process, innovative, adaptable to both current and future market needs and to possible changes in regulation, based on the most advanced technologies available today, and above all guaranteeing the cybersecurity of both entities and end users.

show abstract

“…As a branch of computer vision, face recognition technology has been widely used in people's work, life and study because of its high recognition accuracy. However, faces under partial occlusion bring new challenges to traditional recognition techniques [1][2][3] . Since the outbreak of COVID-19 in 2019, wearing masks in public places is still a rule that people must follow.…”

Section: Introductionmentioning

confidence: 99%

An improved method for partial occlusion face inpainting

Liu,

Roben

2023

Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023)

View full text Add to dashboard Cite

Face with mask would lead to a reduction in the number of features that can be extracted from the face, thus severely reducing the accuracy of face recognition. Image inpainting methods can be used to recover the obscured regions. A face image inpainting model based on pix2pix generative adversarial network is proposed for the current blurring problem after face image inpainting. The generator network and discriminator network in the model are trained adversarially to achieve the restoration of obscured faces. Multi-branch residual modules and dilated convolutional layers are added to the generator network as a way to guarantee the boundary consistency of the restored images. In addition, a face dataset wearing masks is constructed on the CelebA dataset. According to the experimental findings, the inpainting result is effective, and both PSNR and SSIM are much better than those of the original pix2pix and other methods.

show abstract

Robust Face Recognition Under Partial Occlusion Based on Local Generic Features

Cited by 7 publications

References 15 publications

Effect of Smaller Fingerprint Sensors on the Security of Fingerprint Authentication

Effect of Smaller Fingerprint Sensors on the Security of Fingerprint Authentication

Digital onboarding in finance: a novel model and related cybersecurity risks

An improved method for partial occlusion face inpainting

Contact Info

Product

Resources

About