Single-Shot Face Anti-Spoofing for Dual Pixel Camera

Wu, Xiaojun; Jing-hui, Zhou; Li, Jun; Ni, Fangyi; Fan, Haoqiang

doi:10.1109/tifs.2020.3035879

Cited by 18 publications

(9 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, the real and fake images are successfully classified when the detector takes the depth maps from our network. We also refer to a recent study [52] for face anti-spoofing using DP. We expect that our dataset will be useful for this research field.…”

Section: Applicationsmentioning

confidence: 99%

“…Exploiting the advantages of DP images, previous studies [15,35,36,48,60] have demonstrated that DP images can be utilized to estimate scene depths within the certain ranges of scenes. Despite strengths of DP images, there has been limited study [52] to recover a facial geometry from a Dual-Pixel camera. This is due to the lack of facial DP dataset with precise 3D geometry and an appropriate architectural design.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Facial Depth and Normal Estimation using Single Dual-Pixel Camera

Kang¹,

Choe²,

Ha³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

Section: Applicationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Facial Depth and Normal Estimation using Single Dual-Pixel Camera

Kang¹,

Choe²,

Ha³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…A comparative analysis was performed for analyzing the established method with respect to accuracy and execution time. A NN (neural network)-based face anti-spoofing algorithm was projected by Xiaojun Wu, et.al (2021) in which DP (dual pixel) sensor images [22]. Initially, a DP image pair was utilized for input in network and a depth map was created with a baseline.…”

Section: Literature Reviewmentioning

confidence: 99%

Hybrid Classification for Face Spoof Detection

Mittal¹

2021

IJRASET

View full text Add to dashboard Cite

ML (machine learning) is consisted of a method of recognizing face. This technique is useful for the attendance system. Two sets are generated for testing and training phases in order to segment the image, to extract the features and develop a dataset. An image is considered as a testing set; the training set is contrasted when it is essential to identify an image. An ensemble classifier is implemented to classify the test images as recognized or non-recognized. The ensemble algorithm fails to acquire higher accuracy as it classifies the data in two classes. Thus, GLCM (Grey Level Co-occurrence Matrix) is projected for analyzing the texture features in order to detect the face. The attendance of the query image is marked after detecting the face. The simulation outcomes revealed the superiority of the projected technique over the traditional methods concerning accuracy. Keywords: DWT, GLCM, KNN, Decision Tree

show abstract

“…F ACE recognition [1]- [4] has been widely utilized in identity authentication products. However, face recognition is vulnerable to realistic presentation attacks (PAs), including faces printed on paper (print attack), faces replayed on digital devices (replay attack), etc.. Aiming to secure face recognition systems from PAs, face anti-spoofing (FAS) [5]- [9] technology has attracted increasing attention from both academia and industry.…”

Section: Introductionmentioning

confidence: 99%

“…In the past two decades, both traditional handcrafted feature-based [5], [6], [10], [11] and deep learning-based [7]- [9], [12], [13] methods have been shown to be effective for FAS. On the one hand, classical handcrafted descriptors [5], [6], [10], [11] extract discrimination between live and spoof faces based on human prior knowledge.…”

Section: Introductionmentioning

confidence: 99%

Meta-Teacher For Face Anti-Spoofing

Qin

Yan

et al. 2022

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Face anti-spoofing (FAS) secures face recognition from presentation attacks (PAs). Existing FAS methods usually supervise PA detectors with handcrafted binary or pixel-wise labels. However, handcrafted labels may are not the most adequate way to supervise PA detectors learning sufficient and intrinsic spoofing cues. Instead of using the handcrafted labels, we propose a novel Meta-Teacher FAS (MT-FAS) method to train a meta-teacher for supervising PA detectors more effectively. The meta-teacher is trained in a bi-level optimization manner to learn the ability to supervise the PA detectors learning rich spoofing cues. The bi-level optimization contains two key components: 1) a lower-level training in which the meta-teacher supervises the detector's learning process on the training set; and 2) a higher-level training in which the meta-teacher's teaching performance is optimized by minimizing the detector's validation loss. Our meta-teacher differs significantly from existing teacher-student models because the meta-teacher is explicitly trained for better teaching the detector (student), whereas existing teachers are trained for outstanding accuracy neglecting teaching ability. Extensive experiments on five FAS benchmarks show that with the proposed MT-FAS, the trained meta-teacher 1) provides better-suited supervision than both handcrafted labels and existing teacher-student models; and 2) significantly improves the performances of PA detectors.

show abstract

Single-Shot Face Anti-Spoofing for Dual Pixel Camera

Cited by 18 publications

References 40 publications

Facial Depth and Normal Estimation using Single Dual-Pixel Camera

Facial Depth and Normal Estimation using Single Dual-Pixel Camera

Hybrid Classification for Face Spoof Detection

Meta-Teacher For Face Anti-Spoofing

Contact Info

Product

Resources

About