Proceedings ArticleDOI
CHIF: Convoluted Histogram Image Features for Detecting Silicone Mask based Face Presentation Attack
Akshay Agarwal,Mayank Vatsa,Richa Singh +2 more
- pp 1-5
Reads0
Chats0
TLDR
This research proposes a computationally efficient solution by utilizing the power of CNN filters, and texture encoding for silicone mask based presentation attacks by binarizing the image region after convolving the region with the filters learned via CNN operations.Abstract:
Face recognition algorithms are generally vulnerable towards presentation attacks ranging from cost-effective ways such as print and replay to sophisticated mediums such as silicone masks. Carefully designed silicone masks have real-life face texture once wore and can exhibit facial motions; thereby making them challenging to detect. In the literature, while several algorithms have been developed for detecting print and replay based attacks, limited work has been done for detecting silicone mask-based attack. In this research, we propose a computationally efficient solution by utilizing the power of CNN filters, and texture encoding for silicone mask based presentation attacks. The proposed framework operates on the principle of binarizing the image region after convolving the region with the filters learned via CNN operations. On the challenging silicon mask face presentation attack database (SMAD), the proposed feature descriptor shows 3.8% lower error rate than the state-of-the-art algorithms.read more
Citations
More filters
Journal ArticleDOI
Deep Learning for Face Anti-Spoofing: A Survey
TL;DR: In this paper , a comprehensive review of recent advances in deep learning based face anti-spoofing (FAS) is presented, which covers several novel and insightful components: 1) besides supervision with binary label (e.g., ‘0’ for bonafide vs. ‘1' for PAs), also investigate recent methods with pixel-wise supervision, and 2) in addition to traditional intra-dataset evaluation, collect and analyze the latest methods specially designed for domain generalization and open-set FAS; and 3) besides commercial RGB camera, summarize the deep learning applications under multi-modal (i.e. light field and flash) sensors.
Posted Content
MixNet for Generalized Face Presentation Attack Detection
TL;DR: This research has proposed a deep learning-based network termed as MixNet to detect presentation attacks in cross-database and unseen attack settings and shows the effectiveness of the proposed algorithm.
Proceedings ArticleDOI
MixNet for Generalized Face Presentation Attack Detection
TL;DR: In this article, the authors proposed a deep learning-based network termed as MixNet to detect presentation attacks in cross-database and unseen attack settings, which utilizes state-of-the-art convolutional neural network architectures and learns the feature mapping for each attack category.
Posted Content
Deep Learning for Face Anti-Spoofing: A Survey
TL;DR: A comprehensive review of recent advances in deep learning-based face anti-spoofing can be found in this article, which covers several novel and insightful components: 1) besides the traditional binary label (e.g., '0' for bonafide vs. '1' for PAs), they also investigate recent methods with pixel-wise supervision, and 2) in addition to traditional intra-dataset evaluation, they collect and analyze the latest methods specially designed for domain generalization and open-set FAS; and 3) besides commercial RGB camera, they summarize
Journal ArticleDOI
Boosting Face Presentation Attack Detection in Multi-Spectral Videos Through Score Fusion of Wavelet Partition Images
TL;DR: This article presents a unified PAD algorithm for different kinds of attacks such as printed photos, a replay of video, 3D masks, silicone masks, and wax faces, which utilizes a combination of wavelet decomposed raw input images from sensor and face region data to detect whether the input image is bonafide or attacked.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Proceedings ArticleDOI
Going deeper with convolutions
Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich +8 more
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Journal Article
Visualizing Data using t-SNE
TL;DR: A new technique called t-SNE that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map, a variation of Stochastic Neighbor Embedding that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map.