Specific emitter identification based on ITD and texture analysis

Abstract

To solve the defects of time-frequency analysis and poor separability of extracted features in specific emitter identification (SEI) based on Hilbert-Huang transform (HHT)，a novel SEI method based on intrinsic time-scale decomposition(ITD)was proposed.ITD was utilized to decompose the emitter signals and get the time-frequency energy distribution(TFED)firstly，later the TFED spectrum was transformed into gray image and several image texture features through histogram statistic and gray-level co-occurrence matrix was extracted for identification.Measured ship communication signals and simulated emitter signals were used to test the performance of proposed method.Compared with another two SEI methods based on HHT，the proposed method is proved more effective in identification accuracy.

Keywords

• SEI
• ITD
• TFED spectrum
• texture analysis