Title :
An Algorithm and Its Performance Analysis for Ridges Extraction of Time-frequency Distribution Image Using PSO Algorithm
Author :
Yu, Ming ; Zhao, Jian ; Zeng, Jianchao
Author_Institution :
Tianjin Inst. of Urban Constr., Tianjin
Abstract :
In order to obtain the feature parameters of a signal, the image ridge of time-frequency domain must usually be detected. In the paper, the PSO algorithm is applied to the detection of the transform-domain image ridge. A new ridge detection algorithm is proposed, together with its specific realization process. Furthermore, this method is simulated to evaluate precision of this and the robustness of noise. Comparing its simulation results with the common method prove that this algorithms have the advantage to be fast and simple, with high accuracy, less iterations and small noise. It appears that the so defined ridges deserve as some features of the signal.
Keywords :
feature extraction; image recognition; particle swarm optimisation; PSO algorithm; noise robustness; ridge detection algorithm; ridges extraction; time-frequency distribution image; transform-domain image ridge; Detection algorithms; Distributed computing; Karhunen-Loeve transforms; Linear systems; Mobile communication; Mobile computing; Noise robustness; Performance analysis; Signal processing; Time frequency analysis; Time-frequency image ridge; particle swarm optimization (PSO) algorithm; ridge Extraction;
Conference_Titel :
Communications and Mobile Computing, 2009. CMC '09. WRI International Conference on
Conference_Location :
Yunnan
Print_ISBN :
978-0-7695-3501-2
DOI :
10.1109/CMC.2009.240