Abstract
AbstractHead 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.
Funder
Università degli Studi di Salerno
Publisher
Springer Science and Business Media LLC
Subject
Computer Science Applications,Computer Vision and Pattern Recognition,Hardware and Architecture,Software
Reference34 articles.
1. Abate, A.F., Barra, P., Bisogni, C., Nappi, M., Ricciardi, S.: Near real-time three axis head pose estimation without training. IEEE Access 7, 64256–64265 (2019)
2. Abate, A.F., Barra, P., Pero, C., Tucci, M.: Head pose estimation by regression algorithm. Pattern Recognit. Lett. 140, 179–185 (2020)
3. Barra, P., Barra, S., Bisogni, C., De Marsico, M., Nappi, M.: Web-shaped model for head pose estimation: an approach for best exemplar selection. IEEE Trans. Image Process. 29, 5457–5468 (2020). https://doi.org/10.1109/TIP.2020.2984373
4. Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, Berlin (2006)
5. Bisogni, C., Nappi, M., Pero, C., Ricciardi, S.: Hp2ifs: head pose estimation exploiting partitioned iterated function systems. In: 25th International Conference on Pattern Recognition (ICPR2020)
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献