A Novel Deep Transfer Learning-Based Approach for Face Pose Estimation

• Published in: Cybernetics and information technologies : CIT Vol. 24; no. 2; pp. 105 - 121
• Main Authors: Rusia, Mayank Kumar, Singh, Dushyant Kumar, Aquib Ansari, Mohd
• Format: Journal Article
• Language: English
• Published: Sciendo 01-06-2024
• Subjects: Biometrics; Deep convolutional neural network; Face alignment; Face recognition; Image processing; Landmark detection
• ISSN: 1314-4081; 1314-4081
• DOI: 10.2478/cait-2024-0018

An efficient face recognition system is essential for security and authentication-based applications. However, real-time face recognition systems have a few significant concerns, including face pose orientations. In the last decade, numerous solutions have been introduced to estimate distinct face pose orientations. Nevertheless, these solutions must be adequately addressed for the three main face pose orientations: Yaw, Pitch, and Roll. This paper proposed a novel deep transfer learning-based multitasking approach for solving three integrated tasks, i.e., face detection, landmarks detection, and face pose estimation. The face pose variation vulnerability has been intensely investigated here underlying three modules: image preprocessing, feature extraction module through deep transfer learning, and regression module for estimating the face poses. The experiments are performed on the well-known benchmark dataset Annotated Faces in the Wild (AFW). We evaluate the outcomes of the experiments to reveal that our proposed approach is superior to other recently available solutions.