×
The submission system is temporarily under maintenance. Please send your manuscripts to
Go to Editorial ManagerFace recognition is the technology that verifies or recognizes faces from images, videos, or real-time streams. It can be used in security or employee attendance systems. Face recognition systems may encounter some attacks that reduce their ability to recognize faces properly. So, many noisy images mixed with original ones lead to confusion in the results. Various attacks that exploit this weakness affect the face recognition systems such as Fast Gradient Sign Method (FGSM), Deep Fool, and Projected Gradient Descent (PGD). This paper proposes a method to protect the face recognition system against these attacks by distorting images through different attacks, then training the recognition deep network model, specifically Convolutional Neural Network (CNN), using the original and distorted images. Diverse experiments have been conducted using combinations of original and distorted images to test the effectiveness of the system. The system showed an accuracy of 93% using FGSM attack, 97% using deep fool, and 95% using PGD.
Face recognition technique is an automatic approach for recognizing a person from digital images using mathematical interpolation as matrices for these images. It can be adopted to realize facial appearance in the situations of different poses, facial expressions, ageing and other changes. This paper presents efficient face recognition model based on the integration of image preprocessing, Co-occurrence Matrix of Local Average Binary Pattern (CMLABP) and Principle Component Analysis (PCA) methods respectively. The proposed model can be used to compare the input image with existing database images in order to display or record the citizen information such as name, surname, birth date, etc. The recognition rate of the model is better than 99%. Accordingly, the proposed face recognition system is functional for criminal investigations. Furthermore, it has been compared with other reported works in the literature using diverse databases and training images. .
The smart classroom is a fully automated classroom where repetitive tasks, including attendance registration, are automatically performed. Due to recent advances in artificial intelligence, traditional attendance registration methods have become challenging. These methods require significant time and effort to complete the process. Therefore, researchers have sought alternative ways to accomplish attendance registration. These methods include identification cards, radio frequency, or biometric systems. However, all of these methods have faced challenges in safety, accuracy, effort, time, and cost. The development of digital image processing techniques, specifically face recognition technology, has enabled automated attendance registration. Face recognition technology is considered the most suitable for this process due to its ability to recognize multiple faces simultaneously. This study developed an integrated attendance registration system based on the YOLOv7 algorithm, which extracts features and recognizes students’ faces using a specially collected database of 31 students from Mustansiriyah University. A comparative study was conducted by applying the YOLOv7 algorithm, a machine learning algorithm, and a combined machine learning and deep learning algorithm. The proposed method achieved an accuracy of up to 100%. A comparison with previous studies demonstrated that the proposed method is promising and reliable for automating attendance registration.
Recently, face recognition technology has become more prevalent in various applications, including mobile devices, access control, and financial transactions. Therefore, it is crucial to address potential vulnerabilities that attackers might exploit. In this study, a method for face presentation attack detection (PAD) is introduced. The method utilizes the diversity of modalities provided by some cameras and sensors to detect face spoofing using convolutional neural networks (CNN) within the context of deep learning. To assess the effectiveness of the proposed approach in real-world scenarios, the wide multi-channel presentation attack (WMCA) dataset is used. The presented method exploits the multi-modal data, including RGB, depth, IR, and thermal channels, to enhance system performance and explore different techniques for combining the results from each modality. Furthermore, this study explores diverse techniques for fusing results from each channel in two fusion scenarios, pre-fusion and post-fusion. In the pre-fusion scenario, data from the four channels is combined, resulting in an ACER value of 0.19%. In the post-fusion scenario, the results of each modality are fused using different fusion techniques, such as majority voting, weighted voting, average pooling, and a stacking classifier. The stacking classifier yields the most favorable outcome with an ACER ratio of 0.03%. This performance is notably superior when compared to state-of-the-art methodologies.