Audio-Visual Biometric Recognition and Presentation Attack Detection: A Comprehensive Survey

Abstract

Biometric recognition is a trending technology that uses unique characteristics data to identify or verify/authenticate security applications. Amidst the classically used biometrics, voice and face attributes are the most propitious for prevalent applications in day-to-day life because they are easy to obtain through restrained and user-friendly procedures. The pervasiveness of low-cost audio and face capture sensors in smartphones, laptops, and tablets has made the advantage of voice and face biometrics more exceptional when compared to other biometrics. For many years, acoustic information alone has been a great success in automatic speaker verification applications. Meantime, the last decade or two has also witnessed a remarkable ascent in face recognition technologies. Nonetheless, in adverse unconstrained environments, neither of these techniques achieves optimal performance. Since audio-visual information carries correlated and complementary information, integrating them into one recognition system can increase the system's performance. The vulnerability of biometrics towards presentation attacks and audio-visual data usage for the detection of such attacks is also a hot topic of research. This paper made a comprehensive survey on existing state-of-the-art audio-visual recognition techniques, publicly available databases for benchmarking, and Presentation Attack Detection (PAD) algorithms. Further, a detailed discussion on challenges and open problems is presented in this field of biometrics.INDEX TERMS Biometrics, audio-visual person recognition, presentation attack detection.

Efficient and Secure Cancelable Biometric Authentication Framework Based on Genetic Encryption Algorithm

“…These transformations are one-way functions used for the extracted features that enhance the diversity and unlinkability properties. The same biometric template can be suffered from different transformations for various services to forbidden cross-matching between stored biometrics in various cloud datasets [22][23][24][25][26][27]. Another type of cancelable biometric system is called a hybrid approach.…”

BIOMEX-DB: A Cognitive Audiovisual Dataset for Unimodal and Multimodal Biometric Systems

“…Three modalities were considered due to their particular characteristics: voice, video feed and electroencephalography (EEG) signals. In a similar fashion as discussed in [14] for audiovisual biometric systems, the selection of the aforementioned modalities aims to take advantage "...of complimentary biometric information present between voice and face cues", and goes a step beyond by cross-relating to EEG biometric information present in the process of generating visually-evoked potentials, imagining speech and uttering-articulation. A total of 51 users volunteered, all Spanish-speaking Latinos, 26 males and 25 females, with ages between 16 and 61 years old (x = 29.75 , σ = 10.97); 43 claimed to be righthanded, 5 left-handed and 3 declared being ambidextrous.…”

“…A relevant characteristic of DL models is their ability to extract and process features directly from raw biometric data [32], although more complex information can be extracted using deeper models, as it is the case with deeply learned residual features [33]. In general, DL techniques achieve very high performance in both identification and verification cases [14], but with the associated complexity cost. In the first part of this section, we present two unimodal recognition experiments based on Convolutional Neural Networks (CNN), using the dataset BIOMEX-DB with voice and face information.…”

Multilingual Audio-Visual Smartphone Dataset And Evaluation

“…For example, some smartphones come with fingerprint and some include face recognition. The captured uni-modal bio-metrics like face or iris comes with several problems like low quality, variations in pose, problem with illuminations, background noise, low spatial and temporal resolutions of video [18]. Therefore, this problem is addressed in multimodal biometrics by taking advantages of default sensors like camera and microphone.…”

“…The second challenge is from the presentation attacks or also called as spoofing attacks and indirect attacks which are comprehensively explained in [29] for face and in [18] for audio-visual. Presentation attacks are defined as the presentation to a biometric capture subsystem with the goal of interfering with the operation of the biometric system [12].…”