2022
DOI: 10.1007/s11042-022-13248-6
|View full text |Cite
|
Sign up to set email alerts
|

A comprehensive survey on techniques to handle face identity threats: challenges and opportunities

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
11
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
2

Relationship

2
6

Authors

Journals

citations
Cited by 36 publications
(11 citation statements)
references
References 176 publications
0
11
0
Order By: Relevance
“…Image enhancement includes various preprocessing operations such as serialization and annotation, resizing, and class-wise labeling of the dataset. Applying these operations reduces the inconsistency and complexity of our use case NUAA dataset [12,13].…”
Section: Image Enhancementmentioning
confidence: 99%
“…Image enhancement includes various preprocessing operations such as serialization and annotation, resizing, and class-wise labeling of the dataset. Applying these operations reduces the inconsistency and complexity of our use case NUAA dataset [12,13].…”
Section: Image Enhancementmentioning
confidence: 99%
“…Face recognition is now common in daily life, enabling smartphone unlocking [1], auto-tagging on social media [2], identity verification at airports [3], and others application. Despite its extensive uses, face recognition faces challenges such as recognizing faces in low resolution [4], varied poses [5], and different lighting conditions [6]. These issues can reduce performance [7], requiring enhancements for better effectiveness and accuracy.…”
Section: Introductionmentioning
confidence: 99%
“…For face image generation, a GAN is trained on a dataset of real face images. 11 The generator starts by creating low-resolution, blurry images, but as training progresses, it learns to create more detailed, realistic images on the basis of style images. The face image generation process is done in two ways.…”
Section: Introductionmentioning
confidence: 99%
“…Based on all these facts, we can say that the GAN models with proper optimization are suitable deep learning models to generate realistic random faces for automated Multimedia content creation. For face image generation, a GAN is trained on a dataset of real face images 11 . The generator starts by creating low‐resolution, blurry images, but as training progresses, it learns to create more detailed, realistic images on the basis of style images.…”
Section: Introductionmentioning
confidence: 99%