Bibliographic Details
| Title: |
A Multi-Modal Convolutional Neural Network for Face Anti-Spoofing Detection. |
| Authors: |
S. Mahmood, Hala1 hala.shaker@uobasrah.edu.iq, Al-Darraji, Salah2 |
| Source: |
Iraqi Journal for Electrical & Electronic Engineering. Jun2026, Vol. 22 Issue 1, p46-55. 10p. |
| Subjects: |
Convolutional neural networks, Multisensor data fusion, Deep learning, Detectors, Machine learning, Biometric identification |
| Abstract (English): |
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. [ABSTRACT FROM AUTHOR] |
| Abstract (Arabic): |
تركز المقالة على نهج شبكة عصبية تلافيفية متعددة الوسائط (CNN) للكشف عن هجمات تقديم الوجه (PAD) بهدف تعزيز الأمان في أنظمة التعرف على الوجه. باستخدام مجموعة بيانات هجوم التقديم متعددة القنوات الواسعة (WMCA)، التي تتضمن بيانات من نماذج متعددة مثل الصور الملونة (RGB)، والعمق، والأشعة تحت الحمراء (IR)، والحرارية، تقوم الدراسة بتقييم استراتيجيتين للدمج—الدمج المسبق (pre-fusion) الذي يجمع البيانات الخام، والدمج اللاحق (post-fusion) الذي يجمع مخرجات كل نمط على حدة—لتحسين دقة مكافحة التزييف. تظهر النتائج أن طريقة الدمج اللاحق، وخاصة باستخدام مصنف التكديس (stacking classifier)، تحقق معدل خطأ تصنيف متوسط (ACER) منخفض يصل إلى 0.03%، متفوقة بذلك على التقنيات الحديثة المتقدمة. تؤكد الدراسة على أهمية دمج البيانات متعددة الوسائط وتقنيات الدمج المتنوعة في التمييز الفعال بين الوجوه الحقيقية وهجمات التزييف في أنظمة التوثيق البيومترية. [Extracted from the article] |
|
Copyright of Iraqi Journal for Electrical & Electronic Engineering is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Engineering Source |
