Large Crowdcollected Facial Anti-Spoofing Dataset

Timoshenko, Denis; Simonchik, Konstantin; Shutov, Vitaly; Zhelezneva, Polina; Grishkin, Valery

doi:10.1109/csitechnol.2019.8895208

Cited by 12 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Qualitative Results: We evaluated our proposed method on two datasets, CelebA Spoof [7] and LCC FASD [8], and achieved competitive results comparable to State of the Art models. On the CelebA Spoof dataset, our method achieved an AUC score of 0.9882, an EER score of 0.17, and an APCER score of 6, which were similar to MN3 large and better than MN3 small, but lower than AE Net.…”

Section: Resultsmentioning

confidence: 99%

Graph for Transformer Feature: A New Approach for Face Anti-Spoofing

Trinh,

Nguyen,

Nguyen

et al. 2023

ESANN 2023 Proceesdings

View full text Add to dashboard Cite

Face recognition is popular nowadays, however, Face antispoofing (FAS) poses a significant challenge for recognition systems due to the threat of external attacks. While many deep learning methods have been proposed to address this issue, they often face challenges in industry settings. Experiments found that patch extraction modules, such as the Vision Transformer and Swin Transformer, are effective for FAS in single images and perform well in industrial environments. From this point, we propose a model that leverages Transformer features and Graph Neural Networks to learn global information and identify correlations between patch features, which are critical for FAS.

show abstract

Section: Resultsmentioning

confidence: 99%

Graph for Transformer Feature: A New Approach for Face Anti-Spoofing

Trinh,

Nguyen,

Nguyen

et al. 2023

ESANN 2023 Proceesdings

View full text Add to dashboard Cite

show abstract

“…Neural networks, inspired from the way human neurons interact with each other [18], are regarded as the main constituents of artificial intelligence frameworks, and are being predominantly used for classification problems, right since their inception in the forms of Perceptron and ADALINE [19][20][21]. CNNs, a variant of artificial neural networks, have recently been used for many pattern detection tasks and thus were considered the framework of choice for several applications such as face detection [22], facial expression recognition [23], and image classification [24]. These networks have one or more of the following layers: convolutional layer, pooling layer, activation layer and fully connected layer and are known to have high performance in machine learning problems [25].…”

Section: Convolutional Neural Network (Cnn)mentioning

confidence: 99%

What Does A Typical CNN “See” In An Emotional Facial Image?

Sannasi,

Kyritsis,

Gray

2023

World Congress on Electrical Engineering and Computer Systems and Science

View full text Add to dashboard Cite

The objective of this research is to understand the current capabilities of artificial neural network algorithms and contrast them to the human visual system, in order to identify the most effective features to support affective automation. This can, in turn, aid in optimisation of resources used for storage and transmission by understanding which level of information can be used to augment and potentially accelerate accurate identification of emotional facial expressions. For the first part of our experiment, which we present in this paper, we focused on evaluating feature selection of facial expression images using machine learning. 70 (10 examples of each basic emotion) randomly selected from the NIMSTIM dataset images were used, which were split into train (56) and test ( 14) sets. The testing images were then processed using Singular Vector Decomposition to vary the levels of information shown in the image. Next, the training dataset was used to train a Convolutional Neural Network algorithm with 18 layers (with convolutional, max pooling, dropout, flattening and activation layers) and 66,884,615 trainable parameters. The validation accuracy was 45% and the confusion matrix showed that the emotion disgust was predicted at almost 100% accuracy, surprise at 55%, and sorrow/happiness/neutral at 46-47%. As expected, the granularity level of the test images had an effect on the successful predictions. A feature map visualisation was performed to demonstrate what the CNN "sees" (i.e., the feature selection) in the image in order to accurately predict the emotional expression type. For the next phase of our experiment, we plan on contrasting the features and performance to that of the human visual system using an experimental design with eye tracking.

show abstract

“…Ditahun 2018 hingga 2021 muncul set data Rose-Youtu [29], SiW [30], WFFD [31], SiW-M [32], CASIA-SURF [18], Swax [17], CelebA-Spoof [33], RECOD-MPAD [34], CASIA-SURF 3D Mask [35], CASIA-SURF HiFiMask [19], GREAT-FASD-S [36] dan LCC FASD [37]. Set data seperti CASIA-SURF, CelebA-Spoof, dan CASIA-SURF HiFiMask memiliki kompleksitas yang tinggi karena memiliki jumlah data yang besar dan menggunakan subjek yang sangat banyak.…”

Section: Gambaran Umum Dan Ketersediaan Set Data Publikunclassified

Studi Literatur Presentation Attack dan Set Data Anti-Spoof Wajah

Senapartha

Tamtama²

2022

Jurnal Teknik Elektro

View full text Add to dashboard Cite

Face anti-spoof systems are needed in facial recognition systems to ward off attacks that present fake faces in front of the camera or image capture sensor (presentation attack). To build the system, a data set is needed to build a classification model that distinguishes the authenticity of the face of the input image received by the system. In the past decade anti-face spoof research has produced many data sets that are public, but often researchers need time to build or use the right public data sets that are used to build facial anti-spoof models. This article conducts a literature study of public data sets using a systematic literature review method to find out the types of attacks that appear on the facial anti-spoof system, the development process, evolution, and availability of facial anti-spoof data sets. From the search and selection results based on the specified criteria, there were 42 primary research manuscripts in the period 2010 to 2021. The results of the literature study found that there were three trends in the development of anti-spoof facial data sets, namely, 1) data sets with a very large number, 2) datasets with different types of facial samples, and 3) datasets constructed with various devices and sensors. These various public data sets can be accessed freely but with special rules such as agreeing to an end user license agreement document from the researcher or the institution that owns the data set. However, there are also datasets that cannot be accessed due to invalid URLs or due to special rules from the cloud storage service provider where the datasets are stored.

show abstract

Large Crowdcollected Facial Anti-Spoofing Dataset

Cited by 12 publications

References 9 publications

Graph for Transformer Feature: A New Approach for Face Anti-Spoofing

Graph for Transformer Feature: A New Approach for Face Anti-Spoofing

What Does A Typical CNN “See” In An Emotional Facial Image?

Studi Literatur Presentation Attack dan Set Data Anti-Spoof Wajah

Contact Info

Product

Resources

About