IET Biometrics最新文献

The recent COVID-19 pandemic has increased the focus on hygienic and contactless identity verification methods. However, the pandemic led to the wide use of face masks, essential to keep the pandemic under control. The effect of wearing a mask on face recognition (FR) in a collaborative environment is a currently sensitive yet understudied issue. Recent reports have tackled this by evaluating the masked probe effect on the performance of automatic FR solutions. However, such solutions can fail in certain processes, leading to the verification task being performed by a human expert. This work provides a joint evaluation and in-depth analyses of the face verification performance of human experts in comparison to state-of-the-art automatic FR solutions. This involves an extensive evaluation by human experts and 4 automatic recognition solutions. The study concludes with a set of take-home messages on different aspects of the correlation between the verification behaviour of humans and machines.

The concept of biometric identification is centred around the theory that every individual is unique and has distinct characteristics. Various metrics such as fingerprint, face, iris, or retina are adopted for this purpose. Nonetheless, new alternatives are needed to establish the identity of individuals on occasions where the above techniques are unavailable. One emerging method of human recognition is lip-based identification. It can be treated as a new kind of biometric measure. The patterns found on the human lip are permanent unless subjected to alternations or trauma. Therefore, lip prints can serve the purpose of confirming an individual's identity. The main objective of this work is to design experiments using computer vision methods that can recognise an individual solely based on their lip prints. This article compares traditional and deep learning computer vision methods and how they perform on a common dataset for lip-based identification. The first pipeline is a traditional method with Speeded Up Robust Features with either an SVM or K-NN machine learning classifier, which achieved an accuracy of 95.45% and 94.31%, respectively. A second pipeline compares the performance of the VGG16 and VGG19 deep learning architectures. This approach obtained an accuracy of 91.53% and 93.22%, respectively.

Photoplethysmography (PPG) signal is a novel biometric trait related to the identity of people; many time- and frequency-domain methods for PPG biometric recognition have been proposed. However, the existing domain methods for PPG biometric recognition only consider a single domain or the feature-level fusion of time and frequency domains, without considering the exploration of the fusion correlations of the time and frequency domains. The authors propose a time–frequency fusion for a PPG biometric recognition method with collective matrix factorisation (TFCMF) that leverages collective matrix factorisation to learn a shared latent semantic space by exploring the fusion correlations of the time and frequency domains. In addition, the authors utilise the ℓ_2,1 norm to constrain the reconstruction error and shared matrix, which can alleviate the influence of noise and intra-class variation, and ensure the robustness of learnt semantic space. Experiments demonstrate that TFCMF has better recognition performance than current state-of-the-art methods for PPG biometric recognition.

Text tattoos contain rich information about an individual for forensic investigation. To extract this information, text tattoo localisation is the first and essential step. Previous tattoo studies applied existing object detectors to detect general tattoos, but none of them considered text tattoo localisation and they neglect the prior knowledge that text tattoos are usually inside or nearby larger tattoos and appear only on human skin. To use this prior knowledge, a prior knowledge-based attention mechanism (PKAM) and a network named Text Tattoo Localisation Network based on Double Attention (TTLN-DA) are proposed. In addition to TTLN-DA, two variants of TTLN-DA are designed to study the effectiveness of different prior knowledge. For this study, NTU Tattoo V2, the largest tattoo dataset and NTU Text Tattoo V1, the largest text tattoo dataset are established. To examine the importance of the prior knowledge and the effectiveness of the proposed attention mechanism and the networks, TTLN-DA and its variants are compared with state-of-the-art object detectors and text detectors. The experimental results indicate that the prior knowledge is vital for text tattoo localisation; The PKAM contributes significantly to the performance and TTLN-DA outperforms the state-of-the-art object detectors and scene text detectors.

Doppelgängers (or lookalikes) usually yield an increased probability of false matches in a facial recognition system, as opposed to random face image pairs selected for non-mated comparison trials. In this work, the impact of doppelgängers on the HDA Doppelgänger and Disguised Faces in The Wild databases is assessed using a state-of-the-art face recognition system. It is found that doppelgänger image pairs yield very high similarity scores resulting in a significant increase of false match rates. Further, a doppelgänger detection method is proposed, which distinguishes doppelgängers from mated comparison trials by analysing differences in deep representations obtained from face image pairs. The proposed detection system employs a machine learning-based classifier, which is trained with generated doppelgänger image pairs utilising face morphing techniques. Experimental evaluations conducted on the HDA Doppelgänger and Look-Alike Face databases reveal a detection equal error rate of approximately 2.7% for the task of separating mated authentication attempts from doppelgängers.

In recent years, with the advent of deep-learning, face recognition (FR) has achieved exceptional success. However, many of these deep FR models perform much better in handling frontal faces compared to profile faces. The major reason for poor performance in handling of profile faces is that it is inherently difficult to learn pose-invariant deep representations that are useful for profile FR. In this paper, the authors hypothesise that the profile face domain possesses a latent connection with the frontal face domain in a latent feature subspace. The authors look to exploit this latent connection by projecting the profile faces and frontal faces into a common latent subspace and perform verification or retrieval in the latent domain. A coupled conditional generative adversarial network (cpGAN) structure is leveraged to find the hidden relationship between the profile and frontal images in a latent common embedding subspace. Specifically, the cpGAN framework consists of two conditional GAN-based sub-networks, one dedicated to the frontal domain and the other dedicated to the profile domain. Each sub-network tends to find a projection that maximises the pair-wise correlation between the two feature domains in a common embedding feature subspace. The efficacy of the authors’ approach compared with the state of the art is demonstrated using the CFP, CMU Multi-PIE, IARPA Janus Benchmark A, and IARPA Janus Benchmark C datasets. Additionally, the authors have also implemented a coupled convolutional neural network (cpCNN) and an adversarial discriminative domain adaptation network (ADDA) for profile to frontal FR. The authors have evaluated the performance of cpCNN and ADDA and compared it with the proposed cpGAN. Finally, the authors have also evaluated the authors’ cpGAN for reconstruction of frontal faces from input profile faces contained in the VGGFace2 dataset.

There has recently been intensive development of methods for identification and personal verification using the human finger vascular system (FVS). The primary focus of these efforts has been the increasingly sophisticated methods of image processing, and frequently employing machine learning. In this article, we present a new concept of imaging in which the finger vasculature is illuminated using different wavelengths of light, generating multiple FVS images. We hypothesised that the analysis of these image sets, instead of individual images, could increase the effectiveness of identification. Analyses of data from over 100 volunteers, using five different deterministic methods for feature extraction, consistently demonstrated improved identification efficiency with the addition of data obtained from another wavelength. The best results were seen for combinations of diodes between 800 and 900 nm. Finger vascular system observations outside this range were of marginal utility. The knowledge gained from this experiment can be utilised by designers of biometric recognition devices leveraging FVS technology. Our results confirm that developments in this field are not restricted to image processing algorithms, and that hardware innovations remain relevant.