LieToMe: An Ensemble Approach for Deception Detection from Facial Cues

被引:21
作者
Avola, Danilo [1 ]
Cascio, Marco [1 ]
Cinque, Luigi [1 ]
Fagioli, Alessio [1 ]
Foresti, Gian Luca [2 ]
机构
[1] Sapienza Univ, Dept Comp Sci, Via Salaria 113, I-00198 Rome, Italy
[2] Univ Udine, Dept Comp Sci Math & Phys, Via Sci, I-33100 Udine, Italy
关键词
Deception detection; facial expressions; stacked generalization; LOCAL BINARY PATTERNS; FISHER VECTOR; RECOGNITION; ALGORITHM; FEATURES;
D O I
10.1142/S0129065720500689
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Deception detection is a relevant ability in high stakes situations such as police interrogatories or court trials, where the outcome is highly influenced by the interviewed person behavior. With the use of specific devices, e.g. polygraph or magnetic resonance, the subject is aware of being monitored and can change his behavior, thus compromising the interrogation result. For this reason, video analysis-based methods for automatic deception detection are receiving ever increasing interest. In this paper, a deception detection approach based on RGB videos, leveraging both facial features and stacked generalization ensemble, is proposed. First, a face, which is well-known to present several meaningful cues for deception detection, is identified, aligned, and masked to build video signatures. These signatures are constructed starting from five different descriptors, which allow the system to capture both static and dynamic facial characteristics. Then, video signatures are given as input to four base-level algorithms, which are subsequently fused applying the stacked generalization technique, resulting in a more robust meta-level classifier used to predict deception. By exploiting relevant cues via specific features, the proposed system achieves improved performances on a public dataset of famous court trials, with respect to other state-of-the-art methods based on facial features, highlighting the effectiveness of the proposed method.
引用
收藏
页数:20
相关论文
共 92 条
[1]   Detecting Deceptive Behavior via Integration of Discriminative Features From Multiple Modalities [J].
Abouelenien, Mohamed ;
Perez-Rosas, Veronica ;
Mihalcea, Rada ;
Burzo, Mihai .
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2017, 12 (05) :1042-1055
[2]   Facial expression recognition in the wild using improved dense trajectories and Fisher vector encoding [J].
Afshar, Sadaf ;
Salah, Albert Ali .
PROCEEDINGS OF 29TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, (CVPRW 2016), 2016, :1517-1525
[3]   Face description with local binary patterns:: Application to face recognition [J].
Ahonen, Timo ;
Hadid, Abdenour ;
Pietikainen, Matti .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2006, 28 (12) :2037-2041
[4]   A dynamic ensemble learning algorithm for neural networks [J].
Alam, Kazi Md Rokibul ;
Siddique, Nazmul ;
Adeli, Hojjat .
NEURAL COMPUTING & APPLICATIONS, 2020, 32 (12) :8675-8690
[5]  
Alazrai R., 2018, P IEEE INT C HLTH NE, P1
[6]  
[Anonymous], 2019, P IEEE GLOB COMM C G
[7]  
[Anonymous], 2015, FRONTIERS PSYCHOL
[8]  
[Anonymous], 1995, PROC INT WORKSHOP AU
[9]  
Avola D., 2019, IEEE T MULTIMEDIA, V22, P10
[10]  
Avola D., 2019, IEEE T MULTIMEDIA, P1