Face anti-spoofing (FAS) plays a vital role in securing face recognition systems from the presentation attacks (PAs). As more and more realistic PAs with novel types spring up, it is necessary to develop robust algorithms for detecting unknown attacks even in unseen scenarios. However, deep models supervised by traditional binary loss (e.g., ‘0’ for bonafide vs. ‘1’ for PAs) are weak in describing intrinsic and discriminative spoofing patterns. Recently, pixel-wise supervision has been proposed for the FAS task, intending to provide more fine-grained pixel/patch-level cues. In this paper, we firstly give a comprehensive review and analysis about the existing pixel-wise supervision methods for FAS. Then we propose a novel pyramid supervision, which guides deep models to learn both local details and global semantics from multi-scale spatial context. Extensive experiments are performed on five FAS benchmark datasets to show that, without bells and whistles, the proposed pyramid supervision could not only improve the performance beyond existing pixel-wise supervision frameworks, but also enhance the model’s interpretability (i.e., locating the patch-level positions of PAs more reasonably). Furthermore, elaborate studies are conducted for exploring the efficacy of different architecture configurations with two kinds of pixel-wise supervisions (binary mask and depth map supervisions), which provides inspirable insights for future architecture/supervision design.

Revisiting Pixel-Wise Supervision for Face Anti-Spoofing

Face anti-spoofing (FAS) plays a vital role in securing face recognition systems from the presentation attacks (PAs). As more and more realistic PAs with novel types spring up, it is necessary to develop robust algorithms for detecting unknown attacks even in unseen scenarios. However, deep models supervised by traditional binary loss (e.g., `0' for bonafide vs. `1' for PAs) are weak in describing intrinsic and discriminative spoofing patterns. Recently, pixel-wise supervision has been proposed for the FAS task, intending to provide more fine-grained pixel/patch-level cues. In this paper, we firstly give a comprehensive review and analysis about the existing pixel-wise supervision methods for FAS. Then we propose a novel pyramid supervision, which guides deep models to learn both local details and global semantics from multi-scale spatial context. Extensive experiments are performed on five FAS benchmark datasets to show that, without bells and whistles, the proposed pyramid supervision could not only improve the performance beyond existing pixel-wise supervision frameworks, but also enhance the model's interpretability (i.e., locating the patch-level positions of PAs more reasonably). Furthermore, elaborate studies are conducted for exploring the efficacy of different architecture configurations with two kinds of pixel-wise supervisions (binary mask and depth map supervisions), which provides inspirable insights for future architecture/supervision design.

Self-supervised 2D face presentation attack detection via temporal sequence sampling

Face anti-spoofing (FAS) has lately attracted increasing attention due to its vital role in securing face recognition systems from presentation attacks (PAs). As more and more realistic PAs with novel types spring up, early-stage FAS methods based on handcrafted features become unreliable due to their limited representation capacity. With the emergence of large-scale academic datasets in the recent decade, deep learning based FAS achieves remarkable performance and dominates this area. However, existing reviews in this field mainly focus on the handcrafted features, which are outdated and uninspiring for the progress of FAS community. In this paper, to stimulate future research, we present the first comprehensive review of recent advances in deep learning based FAS. It covers several novel and insightful components: 1) besides supervision with binary label (e.g., ‘0’ for bonafide vs. ‘1’ for PAs), we also investigate recent methods with pixel-wise supervision (e.g., pseudo depth map); 2) in addition to traditional intra-dataset evaluation, we collect and analyze the latest methods specially designed for domain generalization and open-set FAS; and 3) besides commercial RGB camera, we summarize the deep learning applications under multi-modal (e.g., depth and infrared) or specialized (e.g., light field and flash) sensors. We conclude this survey by emphasizing current open issues and highlighting potential prospects. 

Deep Learning for Face Anti-Spoofing: A Survey

Face anti-spoofing detection based on multi-scale image quality assessment

Face Anti Spoofing (FAS) systems are used to identify malicious spoofing attempts targeting face recognition systems using mediums such as video replay or printed papers. With increasing adoption of face recognition technology as a biometric authentication method, FAS techniques are gaining in importance. From a learning perspective, such systems pose a binary classification task. When implemented with Neural Network based solutions, it is common to use the binary cross entropy (BCE) function as the loss to optimize. In this study, we propose a variant of BCE that enforces a margin in angular space and incorporate it in training the DeepPixBis model [1]. In addition, we also present a method to incorporate such a loss for attentive pixel wise supervision applicable in a fully convolutional setting. Our proposed approach achieves competitive scores in both intra and inter-dataset testing on multiple benchmark datasets, consistently outperforming vanilla DeepPixBis. Interestingly, in the case of Protocol 4 of OULU-NPU, considered to be the hardest protocol, our proposed method achieves 5.22% ACER, which is only 0.22% higher than the current State of the Art without requiring any expensive Neural Architecture Search.

A-DeepPixBis: Attentional Angular Margin for Face Anti-Spoofing

The emergence of biometric-based authentication using modern sensors on electronic devices has led to an escalated use of face recognition technologies. While these technologies may seem intriguing, they are accompanied by numerous implicit drawbacks. In this paper, we look into the problem of face anti-spoofing (FAS) on a frame level in an attempt to ameliorate the risks of face-spoofed attacks in biometric authentication processes. We employed a bi-directional feature pyramid network (BiFPN) that is used for convolutional multi-scaled feature extraction on the EfficientDet detection architecture, which is novel to the task of FAS. We further use these convolutional multi-scaled features in order to perform deep pixel-wise supervision. For all of our experiments, we performed evaluations across all major datasets and attained competitive results for the majority of the cases. Additionally, we showed that introducing an auxiliary self-supervision branch tasked with reconstructing the inputs in the frequency domain demonstrates an average classification error rate (ACER) of 2.92% on Protocol IV of the OULU-NPU dataset, which is significantly better than the currently available published works on pixel-wise face anti-spoofing. Moreover, following the procedures of prior works, we performed inter-dataset testing, which further consolidated the generalizability of the proposed models, as they showed optimum results across various sensors without any fine-tuning procedures.

https://www.mdpi.com/1424-8220/21/8/2799/pdf

Bi-FPNFAS: Bi-Directional Feature Pyramid Network for Pixel-Wise Face Anti-Spoofing by Leveraging Fourier Spectra

/pdf/blpnet-a-new-dnn-model-and-bengali-ocr-engine-for-automatic-3ujjefmy.pdf

BLPnet: A new DNN model and Bengali OCR engine for Automatic License Plate Recognition

Precise eye gaze detection has a multitude of real-life use cases such as the input mechanism for physically disabled persons, driver’s attention detection in vehicles, cheating detection in online exam, augmented reality, medical research and so on. Most of the applications need to support real-time functionality, thus the need for a fast and reliable method for eye gaze detection can be justified. In this research work, we propose a non-wearable and webcam-based eye-gaze detection method that offers multiple benefits in terms of accuracy, robustness, and reliability over existing solutions. We approached gaze detection as a multiclass classification problem, this reduced the complexity of the method and allows the solution to be implemented in a way that allows free head movement of the user. We leveraged the latest innovation and breakthroughs in deep learning to construct a novel eye-gaze detection method that works using the live video feed from any modern webcam with acceptable frame rates for proper real-time applications. We achieved 99% validation accuracy in gaze prediction and 20 FPS on average in real-time applications such as mouse pointer control and scrolling.

A Robust Webcam-based Eye Gaze Estimation System for Human-Computer Interaction

Although there has been a huge body of work on Bangla license plate detection and recognition, the successes of these works have largely been limited to correct detection and recognition of undistorted license plates whose images are taken chiefly from the front or the back of vehicles with slight angular variations. As a result, most Bangla automatic license plate recognition (ALPR) systems in practice struggle when the license plates are skewed on the viewing or the image planes of the license plates. In this paper, we address this issue by proposing an analytical approach that can enhance the ALPR of both normal and skewed license plates and can be incorporated into existing Bangla ALPR systems without modifying their internal structures. Specifically, we demonstrate how existing ALPR systems can be treated as black boxes and analyzed to understand what sort of license plate images they work best on and introduce a novel pipeline that combines deep learning and an algorithmic procedure for transforming images of both normal and skewed license plates into formats that are best suited for the ALPR systems. We note that our proposed method can be easily generalized and applied to non-Bangla license plates as well.

Koushik Roy

Papers

A-DeepPixBis: Attentional Angular Margin for Face Anti-Spoofing

Bi-FPNFAS: Bi-Directional Feature Pyramid Network for Pixel-Wise Face Anti-Spoofing by Leveraging Fourier Spectra

BLPnet: A new DNN model and Bengali OCR engine for Automatic License Plate Recognition

A Robust Webcam-based Eye Gaze Estimation System for Human-Computer Interaction

An Analytical Approach for Enhancing the Automatic Detection and Recognition of Skewed Bangla License Plates