FASS: Face Anti-Spoofing System Using Image Quality Features and Deep Learning

Solomon, Enoch; Cios, Krzysztof J.

doi:10.3390/electronics12102199

Cited by 15 publications

(4 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, in dense crowd conditions, our method does not perform human pose estimation as well as VGG, which stems from the weakness of the transformer in analyzing small targets. This may also be due to the fact that we did not use the full block stack [2,2,18,2] format, such as in the original swin transformer, in order to reduce the computational effort and control downsampling.…”

Section: Discussionmentioning

confidence: 99%

“…Human pose estimation has diverse applications, including systems designed to provide assistance in the daily lives of elderly individuals living alone. Such systems can assist caregivers in promptly detecting whether a senior citizen living alone has experienced an emergency or any other situation that requires attention [1][2][3]. In water parks, a drowning detection system utilizing human pose estimation can aid lifeguards in timely identification of individuals in distress [4][5][6][7].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

AiPE: A Novel Transformer-Based Pose Estimation Method

Lu,

Min

2024

Electronics

View full text Add to dashboard Cite

Human pose estimation is an important problem in computer vision because it is the foundation for many advanced semantic tasks and downstream applications. Although some convolutional neural network-based pose estimation methods have achieved good results, these networks are still limited for restricted receptive fields and weak robustness, leading to poor detection performance in scenarios with blur or low resolution. Additionally, their highly parallelized strategy is likely to cause significant computational demands, requiring high computing power. In comparison to the convolutional neural networks, the transformer-based methods offer advantages such as flexible stacking, global perspective, and parallel computation. Based on the great benefits, a novel transformer-based human pose estimation method is developed, which employees multi-head self-attention mechanisms and offset windows to effectively suppress the quick growth of the computational complexity near human keypoints. Experimental results under detailed visual comparison and quantitative analysis demonstrate that the proposed method can efficiently deal with the pose estimation problem in challenging scenarios, such as blurry or occluded scenes. Furthermore, the errors in human skeleton mapping caused by keypoint occlusion or omission can be effectively corrected, so the accuracy of pose estimation results is greatly improved.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

AiPE: A Novel Transformer-Based Pose Estimation Method

Lu,

Min

2024

Electronics

View full text Add to dashboard Cite

show abstract

“…This comprehensive study aims to provide an overview of the existing works and approaches in the field of face spoofing detection. A lot of work has been done in this field, including: Enoch Solomon and Krzysztof J. Cios 2023, [10] propose a face anti-spoofing system that integrates image quality features and deep learning methods. The system aims to distinguish between genuine and spoofed faces by analyzing both the inherent quality of the image and using deep learning models to learn discriminative representations.…”

Section: Literature Reviewmentioning

confidence: 99%

Face Anti-Spoofing Methods: A Comparative Analysis through the Lens of a Comprehensive Review

Kamat

2024

IJRASET

View full text Add to dashboard Cite

In computer vision, face anti-spoofing is an important aspect that aims to differentiate genuine facial features from spoofing attempts. This review paper comprehensively explores existing methodologies, emphasising advancements in computer vision and deep learning. Diverse techniques, ranging from traditional methods like multi-scale LBPs and CNNs to recent innovations such as FeatherNet and ViT-S-Adapter-TSR, are meticulously analysed. A comparative table provides insights into different methods, highlighting their performance on various datasets like MSU-MFD, CASIA-FASD, and OULU-NPU. However, challenges like diverse datasets, varying evaluation metrics, and real-world applicability are acknowledged. The paper discusses limitations related to real-world conditions, computational efficiency, and the ever-evolving nature of spoofing techniques. It emphasises the need for ongoing collaboration and innovation in research to address challenges like dataset consistency and adaptability to emerging threats. In conclusion, while progress has been made, the paper emphasises the dynamic nature of face anti-spoofing research. The pursuit of more effective, adaptable, and computationally efficient methods continues, promising real-world impact against evolving threats.

show abstract

“…2 This is concerning, especially at this moment in time when AI is being used as a tool to disrupt public harmony through disinformation campaigns. 3 At a time when surveillance is increasingly using images and videos, [4][5][6][7] ensuring the authenticity of visual content has become ever important. While deep faked videos have been proven to be detectable through techniques like Electrical Network Frequency, 8,9 AI-generated imagery has not been detectable using the same techniques.…”

Section: Introductionmentioning

confidence: 99%

Generative adversarial networks-based AI-generated imagery authentication using frequency domain analysis

Poredi,

Sudarsan,

Solomon

et al. 2024

Disruptive Technologies in Information Sciences VIII

View full text Add to dashboard Cite

In an era characterized by the prolific generation of digital imagery through advanced artificial intelligence, the need for reliable methods to authenticate actual photographs from AI-generated ones has become paramount. The ever-increasing ubiquity of AI-generated imagery, which seamlessly blends with authentic photographs, raises concerns about misinformation and trustworthiness. Authenticating these images has taken on critical significance in various domains, including journalism, forensic science, and social media. Traditional methods of image authentication often struggle to adapt to the increasingly sophisticated nature of AI-generated content. In this context, frequency domain analysis emerges as a promising avenue due to its effectiveness in uncovering subtle discrepancies and patterns that are less apparent in the spatial domain. Delving into the imperative task of imagery authentication, this paper introduces a novel Generative Adversarial Networks (GANs) based AI-generated Imagery Authentication (GANIA) method using frequency domain analysis. By exploiting the inherent differences in frequency spectra, GANIA uncovers unique signatures that are difficult to replicate, ensuring the integrity and authenticity of visual content. By training GANs on vast datasets of real images, we create AI-generated counterparts that closely mimic the characteristics of authentic photographs. This approach enables us to construct a challenging and realistic dataset, ideal for evaluating the efficacy of frequency domain analysis techniques in image authentication. Our work not only highlights the potential of frequency domain analysis for image authentication but also underscores the importance of adopting generative AI approaches in studying this critical topic. Through this innovative fusion of AI and frequency domain analysis, we contribute to advancing image forensics and preserving trust in visual information in an AI-driven world.

show abstract

FASS: Face Anti-Spoofing System Using Image Quality Features and Deep Learning

Cited by 15 publications

References 66 publications

AiPE: A Novel Transformer-Based Pose Estimation Method

AiPE: A Novel Transformer-Based Pose Estimation Method

Face Anti-Spoofing Methods: A Comparative Analysis through the Lens of a Comprehensive Review

Generative adversarial networks-based AI-generated imagery authentication using frequency domain analysis

Contact Info

Product

Resources

About