International Journal of Computer Science & Network Security

International Journal of Computer Science & Network Security (국제컴퓨터통신보호논문지학회)
권호 표지
DOI QR코드

DOI QR Code

Heterogeneous Parallel Architecture for Face Detection Enhancement

  • Received : 2022.02.05
  • Published : 2022.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Face Detection is one of the most important aspects of image processing, it considers a time-consuming problem in real-time applications such as surveillance systems, face recognition systems, attendance system and many. At present, commodity hardware is getting more and more heterogeneity in terms of architectures such as GPU and MIC co-processors. Utilizing those co-processors along with the existing traditional CPUs gives the algorithm a better chance to make use of both architectures to achieve faster implementations. This paper presents a hybrid implementation of the face detection based on the local binary pattern (LBP) algorithm that is deployed on both traditional CPU and MIC co-processor to enhance the speed of the LBP algorithm. The experimental results show that the proposed implementation achieved improvement in speed by 3X when compared to a single architecture individually.

Keywords

Acknowledgement

This work is supported by the King Abdulaziz University, High-Performance Computing Center (Aziz Supercomputer) (http://hpc.kau.edu.sa).

References

  1. N. NIKE and G. N. RATHNA, "Real time face detection on gpu using opencl," Computer Science, 2014.
  2. M. Chouchene, F. E. Sayadi and H. Bahr, "Optimized parallel implementation of face detection based on GPU component," Microprocessors and Microsystems, vol. 39, pp. 393--404, 2015. https://doi.org/10.1016/j.micpro.2015.04.009
  3. M. B. Lopez , A. Nieto and J. Boute, "Evaluation of real-time LBP computing in multiple architectures," Journal of RealTime Image Processing, vol. 13, no. 6, 2017.
  4. M. Fayez , Faheem, I. Katib and N. R. Aljohani, "Real-time image scanning framework using gpgpu face detection case study," Proceedings of the International Conference on Image Processing, Computer Vision, and Pattern Recognition (IPCV), 2016.
  5. Y. M. Abdelaal , M. Fayez and H. Faheem, "Performance evaluation of image scanning:face detection case study," p. pp. 1-15, 2019.
  6. M. . R. Ikbal, F. Mahmoud, M. Fouad and I. Katib, "Fast implementation of face detection using lpb classifier on gpgpus," Intelligent Computing- Proceedings of the Computing Conference, p. pp. 1036-1047, 2019.
  7. T. Ojala , M. Pietikainen and D. Harwood, "A comparative study of texture measures with classification based on featured distributions," Pattern recognition, vol. 29, no. 1, p. 51-59, 1996.. https://doi.org/10.1016/0031-3203(95)00067-4
  8. B. Konig-Ries and H. Faheem, "A new scheduling strategy for solving the motif finding problem on heterogeneous architectures," International Journal of Computer Applications, vol. 101, p. 27-31, sep 2014. https://doi.org/10.5120/17685-8543
  9. "pre-trained LBP classifier," [Online].Available: https://github.com/opencv/opencv/blob/master/data/lbpcascades/lbpcascade_frontalface.xml.