Share Email Print
cover

Proceedings Paper • new

A fast blink-control system based on FPGA
Author(s): Siwen Cai; Peng Wang; Qiang Zhang; Yuanyuan Chen
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

People have been pursuing fast and convenient methods to control machines. However, the existing human-computer interaction methods still have many shortcomings. We present here a fast blink-control system based on FPGA. The video image processing technologies were utilized to realize the blink-control algorithm and the Verilog hardware description language (Verilog HDL) was taken to develop functional modules on the FPGA. Positioning human eye and recognizing blink were implemented with integral projection method based on gradient operator according to features of eyes. Then, subsequent operations were performed based on judgement results. The designed fast blink-control system was verified on ALTER FPGA development platform. The results showed that the accuracy to detect eye blink (front face, no inclination) was 98% and the average response time of the system was about 413ms, which reached the real-time detection level. Therefore, it has achieved the goal to provide a new control mode which is fast and effective.

Paper Details

Date Published: 27 November 2019
PDF: 6 pages
Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 1132116 (27 November 2019); doi: 10.1117/12.2547449
Show Author Affiliations
Siwen Cai, Harbin Univ. of Science and Technology (China)
Peng Wang, Harbin Univ. of Science and Technology (China)
Qiang Zhang, Harbin Univ. of Science and Technology (China)
Yuanyuan Chen, Harbin Univ. of Science and Technology (China)


Published in SPIE Proceedings Vol. 11321:
2019 International Conference on Image and Video Processing, and Artificial Intelligence
Ruidan Su, Editor(s)

© SPIE. Terms of Use
Back to Top