Günay Yılmaz, Asuman; Turhal, Uğur; Nabiyev, Vasif

Currently, biometric recognition systems, especially facial recognition systems, are frequently used for person authentication. Increasing facial image and video sharing on social media makes these systems vulnerable to attacks. For this reason, there is an increasing need for sensitive face presentation attack (FPA) detection systems. In this paper, a lightweight multi-input hybrid deep convolutional neural network model was proposed for FPA detection. For this purpose, a simplified version of the widely used Xception network was developed. This model was extended via squeeze and excitation blocks to weight the data in the feature encoding channels. In addition, a simple residual network architecture with attention blocks was designed. The FPA detection performances of these models were subsequently examined in cases where the input data consisted of the raw images or cropped facial images. According to the results, a deep learning architecture with three parallel connections was proposed. The raw images, cropped facial images, and face-weighted multi-color multi-level local binary pattern features were given as inputs to the proposed model. Therefore, a multi-input hybrid FPA detection model was created using both hand-crafted features and deep features. The proposed architecture has approximately 82% fewer parameters than the original Xception network does. The experimental results on the benchmark CASIA and REPLAY-ATTACK datasets demonstrate the model's effectiveness, achieving a 1.53% equal error rate (EER) on the CASIA dataset and 0.00% EER with a 0.07% half total error rate (HTER) on the REPLAY-ATTACK dataset. These results outperform many state-of-the-art methods while requiring significantly fewer computational resources, making the approach suitable for deployment in resource-constrained environments.

AtıfScopus5·WoS4·OpenAlex2

İncele

Turhal, Uğur; Günay Yılmaz, Asuman; Nabiyev, Vasif

Biometric data (facial, voice, fingerprint, and retinal scans, for example) are widely used in identification due to their unique and irreversible nature. Facial recognition technologies are employed in a wide range of applications due to their contactless nature and convenience. However, technological advancements and the availability of access to personal information have rendered these biometric systems susceptible to attacks utilizing fake faces. As a result, the issue of anti-spoofing has emerged as a critical one in the field of facial recognition. This study proposes a joint face presentation attack (FPA) detection method based on face-weighted multi-color multi-level LBP features extracted from the combination of device-dependent HSV and device-independent L*a*b* color spaces. The facial images were converted to HSV and L*a*b* color spaces. Three levels of regional LBP features were extracted from each color channel and then concatenated. Finally, a Multi-Color Multi-Level LBP (MCML_LBP) feature vector was obtained. In addition, the Face Weighted MCML_LBP feature vector was produced (FW_MCML_LBP) by adding the LBP histogram extracted from the central region of the normalized image. The feature vectors are used to train an SVM classifier after reducing their size using PCA. Twenty-five different test scenarios were subjected to experimentation on the CASIA and Replay-Attack databases. 2.11% EER and 0.19% HTER were achieved on CASIA (Overall) and Replay-Attack (Grandtest) databases, respectively, using the L*a*b color space and the proposed feature extraction method. The results of the study showed that the proposed method was successful in FPA detection compared to the state-of-the-art methods.

AtıfScopus11·WoS10·OpenAlex10

İncele

Günay Yılmaz, Asuman; Turhal, Uğur; Nabiyev, Vasif

Biometric recognition systems are frequently used in daily life although they are vulnerable to attacks. Today, especially the increasing use of face authentication systems has made these systems the target of face presentation attacks (FPA). This has increased the need for sensitive systems detecting the FPAs. Recently surgical masks, frequently used due to the pandemic, directly affect the performance of face recognition systems. Researchers design face recognition systems only from the eye region. This motivated us to evaluate the FPA detection performance of the eye region. Based on this, in cases where the whole face is not visible, the FPA detection performance of other parts of the face has also been examined. Therefore, in this study, FPA detection performances of facial regions of wide face, cropped face, eyes, nose, and mouth was investigated. For this purpose, the facial regions were determined and normalized, and texture features were extracted using powerful texture descriptor local binary patterns (LBP) due to its easy computability and low processing complexity. Multi-block LBP features are used to obtain more detailed texture information. Generally uniform LBP patterns are used for feature extraction in the literature. In this study, the FPA detection performances of both uniform LBP patterns and all LBP patterns were investigated. The size of feature vector is reduced by principal component analysis, and real/fake classification is performed with support vector machines. Experimental results on NUAA, CASIA, REPLAY-ATTACK and OULU-NPU datasets show that the use of all patterns increased the performance of FPA detection.

AtıfScopus18·WoS11·OpenAlex19

İncele