Loading…
Anomaly Detection-Based Unknown Face Presentation Attack Detection
Anomaly detection-based spoof attack detection is a recent development in face Presentation Attack Detection (fPAD), where a spoof detector is learned using only non-attacked images of users. These detectors are of practical importance as they are shown to generalize well to new attack types. In thi...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Conference Proceeding |
Language: | English |
Subjects: | |
Online Access: | Request full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | |
---|---|
cites | |
container_end_page | 9 |
container_issue | |
container_start_page | 1 |
container_title | |
container_volume | |
creator | Baweja, Yashasvi Oza, Poojan Perera, Pramuditha Patel, Vishal M. |
description | Anomaly detection-based spoof attack detection is a recent development in face Presentation Attack Detection (fPAD), where a spoof detector is learned using only non-attacked images of users. These detectors are of practical importance as they are shown to generalize well to new attack types. In this paper, we present a deep-learning solution for anomaly detection-based spoof attack detection where both classifier and feature representations are learned together end-to-end. First, we introduce a pseudo-negative class during training in the absence of attacked images. The pseudo-negative class is modeled using a Gaussian distribution whose mean is calculated by a weighted running mean. Secondly, we use pairwise confusion loss to further regularize the training process. The proposed approach benefits from the representation learning power of the CNNs and learns better features for fPAD task as shown in our ablation study. We perform extensive experiments on four publicly available datasets: Replay-Attack, Rose-Youtu, OULU-NPU and Spoof in Wild to show the effectiveness of the proposed approach over the previous methods. Code is available at: https://github.com/yashasvi97/IJCB2020_anomaly |
doi_str_mv | 10.1109/IJCB48548.2020.9304935 |
format | conference_proceeding |
fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_9304935</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9304935</ieee_id><sourcerecordid>9304935</sourcerecordid><originalsourceid>FETCH-LOGICAL-i203t-3a9cc747273587dbf5c533da65fd660cd58654afefbe0d7b922909083959ee513</originalsourceid><addsrcrecordid>eNpFj81Kw0AURkdBsNY-gSB5gcQ7_3OXSbVaKejCrstk5gZi24kkA9K3F7Hg6lsczoGPsXsOFeeAD-vXZaOcVq4SIKBCCQqlvmA33ArHkTtjLtlMKKtKNIjXbDFNnwDAjRCcyxlr6jQc_eFUPFKmkPshlY2fKBbbtE_DdypWPlDxPtJEKftfXtQ5-7D_F27ZVecPEy3OO2fb1dPH8qXcvD2vl_Wm7AXIXEqPIVhlhZXa2dh2Omgpoze6i8ZAiNoZrXxHXUsQbYtCICA4iRqJNJdzdvfX7Ylo9zX2Rz-edufL8gd0qErr</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Anomaly Detection-Based Unknown Face Presentation Attack Detection</title><source>IEEE Xplore All Conference Series</source><creator>Baweja, Yashasvi ; Oza, Poojan ; Perera, Pramuditha ; Patel, Vishal M.</creator><creatorcontrib>Baweja, Yashasvi ; Oza, Poojan ; Perera, Pramuditha ; Patel, Vishal M.</creatorcontrib><description>Anomaly detection-based spoof attack detection is a recent development in face Presentation Attack Detection (fPAD), where a spoof detector is learned using only non-attacked images of users. These detectors are of practical importance as they are shown to generalize well to new attack types. In this paper, we present a deep-learning solution for anomaly detection-based spoof attack detection where both classifier and feature representations are learned together end-to-end. First, we introduce a pseudo-negative class during training in the absence of attacked images. The pseudo-negative class is modeled using a Gaussian distribution whose mean is calculated by a weighted running mean. Secondly, we use pairwise confusion loss to further regularize the training process. The proposed approach benefits from the representation learning power of the CNNs and learns better features for fPAD task as shown in our ablation study. We perform extensive experiments on four publicly available datasets: Replay-Attack, Rose-Youtu, OULU-NPU and Spoof in Wild to show the effectiveness of the proposed approach over the previous methods. Code is available at: https://github.com/yashasvi97/IJCB2020_anomaly</description><identifier>EISSN: 2474-9699</identifier><identifier>EISBN: 1728191866</identifier><identifier>EISBN: 9781728191867</identifier><identifier>DOI: 10.1109/IJCB48548.2020.9304935</identifier><language>eng</language><publisher>IEEE</publisher><subject>Authentication ; Biological system modeling ; Face recognition ; Faces ; Feature extraction ; Support vector machines ; Training</subject><ispartof>2020 IEEE International Joint Conference on Biometrics (IJCB), 2020, p.1-9</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9304935$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,23930,23931,25140,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9304935$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Baweja, Yashasvi</creatorcontrib><creatorcontrib>Oza, Poojan</creatorcontrib><creatorcontrib>Perera, Pramuditha</creatorcontrib><creatorcontrib>Patel, Vishal M.</creatorcontrib><title>Anomaly Detection-Based Unknown Face Presentation Attack Detection</title><title>2020 IEEE International Joint Conference on Biometrics (IJCB)</title><addtitle>IJCB</addtitle><description>Anomaly detection-based spoof attack detection is a recent development in face Presentation Attack Detection (fPAD), where a spoof detector is learned using only non-attacked images of users. These detectors are of practical importance as they are shown to generalize well to new attack types. In this paper, we present a deep-learning solution for anomaly detection-based spoof attack detection where both classifier and feature representations are learned together end-to-end. First, we introduce a pseudo-negative class during training in the absence of attacked images. The pseudo-negative class is modeled using a Gaussian distribution whose mean is calculated by a weighted running mean. Secondly, we use pairwise confusion loss to further regularize the training process. The proposed approach benefits from the representation learning power of the CNNs and learns better features for fPAD task as shown in our ablation study. We perform extensive experiments on four publicly available datasets: Replay-Attack, Rose-Youtu, OULU-NPU and Spoof in Wild to show the effectiveness of the proposed approach over the previous methods. Code is available at: https://github.com/yashasvi97/IJCB2020_anomaly</description><subject>Authentication</subject><subject>Biological system modeling</subject><subject>Face recognition</subject><subject>Faces</subject><subject>Feature extraction</subject><subject>Support vector machines</subject><subject>Training</subject><issn>2474-9699</issn><isbn>1728191866</isbn><isbn>9781728191867</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2020</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNpFj81Kw0AURkdBsNY-gSB5gcQ7_3OXSbVaKejCrstk5gZi24kkA9K3F7Hg6lsczoGPsXsOFeeAD-vXZaOcVq4SIKBCCQqlvmA33ArHkTtjLtlMKKtKNIjXbDFNnwDAjRCcyxlr6jQc_eFUPFKmkPshlY2fKBbbtE_DdypWPlDxPtJEKftfXtQ5-7D_F27ZVecPEy3OO2fb1dPH8qXcvD2vl_Wm7AXIXEqPIVhlhZXa2dh2Omgpoze6i8ZAiNoZrXxHXUsQbYtCICA4iRqJNJdzdvfX7Ylo9zX2Rz-edufL8gd0qErr</recordid><startdate>20200928</startdate><enddate>20200928</enddate><creator>Baweja, Yashasvi</creator><creator>Oza, Poojan</creator><creator>Perera, Pramuditha</creator><creator>Patel, Vishal M.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>20200928</creationdate><title>Anomaly Detection-Based Unknown Face Presentation Attack Detection</title><author>Baweja, Yashasvi ; Oza, Poojan ; Perera, Pramuditha ; Patel, Vishal M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i203t-3a9cc747273587dbf5c533da65fd660cd58654afefbe0d7b922909083959ee513</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Authentication</topic><topic>Biological system modeling</topic><topic>Face recognition</topic><topic>Faces</topic><topic>Feature extraction</topic><topic>Support vector machines</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Baweja, Yashasvi</creatorcontrib><creatorcontrib>Oza, Poojan</creatorcontrib><creatorcontrib>Perera, Pramuditha</creatorcontrib><creatorcontrib>Patel, Vishal M.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Xplore (Online service)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Baweja, Yashasvi</au><au>Oza, Poojan</au><au>Perera, Pramuditha</au><au>Patel, Vishal M.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Anomaly Detection-Based Unknown Face Presentation Attack Detection</atitle><btitle>2020 IEEE International Joint Conference on Biometrics (IJCB)</btitle><stitle>IJCB</stitle><date>2020-09-28</date><risdate>2020</risdate><spage>1</spage><epage>9</epage><pages>1-9</pages><eissn>2474-9699</eissn><eisbn>1728191866</eisbn><eisbn>9781728191867</eisbn><abstract>Anomaly detection-based spoof attack detection is a recent development in face Presentation Attack Detection (fPAD), where a spoof detector is learned using only non-attacked images of users. These detectors are of practical importance as they are shown to generalize well to new attack types. In this paper, we present a deep-learning solution for anomaly detection-based spoof attack detection where both classifier and feature representations are learned together end-to-end. First, we introduce a pseudo-negative class during training in the absence of attacked images. The pseudo-negative class is modeled using a Gaussian distribution whose mean is calculated by a weighted running mean. Secondly, we use pairwise confusion loss to further regularize the training process. The proposed approach benefits from the representation learning power of the CNNs and learns better features for fPAD task as shown in our ablation study. We perform extensive experiments on four publicly available datasets: Replay-Attack, Rose-Youtu, OULU-NPU and Spoof in Wild to show the effectiveness of the proposed approach over the previous methods. Code is available at: https://github.com/yashasvi97/IJCB2020_anomaly</abstract><pub>IEEE</pub><doi>10.1109/IJCB48548.2020.9304935</doi><tpages>9</tpages></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | EISSN: 2474-9699 |
ispartof | 2020 IEEE International Joint Conference on Biometrics (IJCB), 2020, p.1-9 |
issn | 2474-9699 |
language | eng |
recordid | cdi_ieee_primary_9304935 |
source | IEEE Xplore All Conference Series |
subjects | Authentication Biological system modeling Face recognition Faces Feature extraction Support vector machines Training |
title | Anomaly Detection-Based Unknown Face Presentation Attack Detection |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-27T11%3A17%3A09IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Anomaly%20Detection-Based%20Unknown%20Face%20Presentation%20Attack%20Detection&rft.btitle=2020%20IEEE%20International%20Joint%20Conference%20on%20Biometrics%20(IJCB)&rft.au=Baweja,%20Yashasvi&rft.date=2020-09-28&rft.spage=1&rft.epage=9&rft.pages=1-9&rft.eissn=2474-9699&rft_id=info:doi/10.1109/IJCB48548.2020.9304935&rft.eisbn=1728191866&rft.eisbn_list=9781728191867&rft_dat=%3Cieee_CHZPO%3E9304935%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i203t-3a9cc747273587dbf5c533da65fd660cd58654afefbe0d7b922909083959ee513%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=9304935&rfr_iscdi=true |