Partitioned iterated function systems by regression models for head pose estimation

• Published in: Machine vision and applications Vol. 32; no. 5
• Main Authors: Abate, Andrea F., Barra, Paola, Pero, Chiara, Tucci, Maurizio
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.09.2021; Springer Nature B.V
• Subjects: Communications Engineering; Computer Science; Computer vision; Datasets; Estimates; Face recognition; Facial recognition technology; Fractals; Head movement; Image acquisition; Image compression; Image Processing and Computer Vision; Methods; Networks; Neural networks; Object recognition; Pattern Recognition; Pitch (inclination); Pose estimation; Regression analysis; Regression models; Robotics and Intelligent Systems; Rolling motion; Self-similarity; Special Issue on 25th ICPR - Computer Vision; Special Issue Paper; Vision systems; Yaw; Regression models; PIFS; Face detection; Head pose estimation
• ISSN: 0932-8092; 1432-1769; 1432-1769
• DOI: 10.1007/s00138-021-01234-1

Head pose estimation represents an important computer vision technique in different contexts where image acquisition cannot be controlled by an operator, making face recognition of unknown subjects more accurate and efficient. In this work, starting from partitioned iterated function systems to identify the pose, different regression models are adopted to predict the angular value errors (yaw, pitch and roll axes, respectively). This method combines the fractal image compression characteristics, such as self-similar structures in order to identify similar head rotation, with regression analysis prediction. The experimental evaluation is performed on widely used benchmark datasets, i.e., Biwi and AFLW2000, and the results are compared with many existing state-of-the-art methods, demonstrating the robustness of the proposed fusion approach and excellent performance.