Spoofing and disguise variations in face recognition

Abstract : Human recognition has become an important topic as the need and investments for security applications grow continuously. Numerous biometric systems exist which utilize various human characteristics. Among all biometrics traits, face recognition is advantageous in terms of accessibility and reliability. In the thesis, two challenges in face recognition are analyzed. The first one is face spoofing. Spoofing in face recognition is explained together with the countermeasure techniques that are proposed for the protection of face recognition systems against spoofing attacks. For this purpose, both 2D photograph and 3D mask attacks are analyzed. The second challenge explored in the thesis is disguise variations, which are due to facial alterations, facial makeup and facial accessories (occlusions). The impact of these disguise variations on face recognition is explored, separately. Then, techniques which are robust against disguise variations are proposed.
Complete list of metadatas

Cited literature [122 references]  Display  Hide  Download

https://pastel.archives-ouvertes.fr/tel-01413382
Contributor : Abes Star <>
Submitted on : Friday, December 9, 2016 - 4:49:06 PM
Last modification on : Thursday, October 17, 2019 - 12:36:09 PM
Long-term archiving on : Monday, March 27, 2017 - 2:52:17 PM

File

TheseKoseV2.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01413382, version 1

Citation

Neslihan Kose. Spoofing and disguise variations in face recognition. Image Processing [eess.IV]. Télécom ParisTech, 2014. English. ⟨NNT : 2014ENST0020⟩. ⟨tel-01413382⟩

Share

Metrics

Record views

797

Files downloads

1135