Performance Tuning Techniques for Face Detection Algorithms on GPGPU
Yara M. Abdelaal1, M. Fayez2, Samy Ghoniemy3, Ehab Abozinadah4, H.M. Faheem5

1Yara M. Abdelaal, Computer Systems, Ain Shams University, Cairo, Egypt.
2M. Fayez*, Computer Systems, Ain Shams University, Cairo, Egypt.
3Samy Ghoniemy, Computer Systems, British University in Cairo, Cairo, Egypt.
4Ehab Abozinadah, Information Systems, King Abdelaziz University, Jeddah, KSA.
5H. M. Faheem, Computer Systems, Ain Shams University, Cairo, Egypt.

Manuscript received on November 11, 2020. | Revised Manuscript received on December 05, 2020. | Manuscript published on December 10, 2021. | PP: 103-108 | Volume-10 Issue-2, December 2020 | Retrieval Number: 100.1/ijitee.B82341210220| DOI: 10.35940/ijitee.B8234.1210220
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Face detection algorithms varies in speed and performance on GPUs. Different algorithms can report different speeds on different GPUs that are not governed by linear or near-linear approximations. This is due to many factors such as register file size, occupancy rate of the GPU, speed of the memory, and speed of double precision processors. This paper studies the most common face detection algorithms LBP and Haar-like and study the bottlenecks associated with deploying both algorithms on different GPU architectures. The study focuses on the bottlenecks and the associated techniques to resolve them based on the different GPUs specifications. 
Keywords: Face Detection, GPU Performance, LBP, Haar Like.