Paper
21 December 2023 Morse code detection and recognition algorithm based on YOLO-SVTR
Zijun Li, Zhenhua Wei, Siming Han
Author Affiliations +
Proceedings Volume 12970, Fourth International Conference on Signal Processing and Computer Science (SPCS 2023); 1297046 (2023) https://doi.org/10.1117/12.3012226
Event: Fourth International Conference on Signal Processing and Computer Science (SPCS 2023), 2023, Guilin, China
Abstract
Aiming at the problem of continuous detection and recognition of Morse codes in shortwave frequency band under time-frequency domain analysis, this paper proposes a YOLO-SVTR algorithm based on deep learning. Firstly, the short-time Fourier transform is used to transform the signal to be detected into a time-frequency image. Then, the lightweight improved YOLOv5 s model is used to detect Morse codes in the time-frequency image and automatically crop the target area. Finally, the cropped image is input into the SVTR-LCNet model to decode the corresponding text information. The simulation results show that the YOLO-SVTR algorithm effectively completes the integrated detection and recognition of Morse codes in the simulated short-wave band, and has good processing speed and high decoding accuracy.
(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Zijun Li, Zhenhua Wei, and Siming Han "Morse code detection and recognition algorithm based on YOLO-SVTR", Proc. SPIE 12970, Fourth International Conference on Signal Processing and Computer Science (SPCS 2023), 1297046 (21 December 2023); https://doi.org/10.1117/12.3012226
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Detection and tracking algorithms

Time-frequency analysis

Performance modeling

Signal detection

Image processing

Shortwaves

Signal processing

Back to Top