Computer Vision and Bi-directional Neural Network for Extraction of Communications Signal from Noisy Spectrogram

Seksan Phonsri, Sankha Subhra Mukherjee, Mathini Sellathurai

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Extraction of communication signals from noisy spectrograms is a challenging problem which has not been explored extensively from an intelligent signal processing and computer vision based perspective. In this paper we propose a novel technique of extracting the communications signal from a noisy spectrogram using a combination of fuzzy neighborhood thresholding based self organizing neural network and morphological operations. We show that about 98% detection is achieved at 5% false alarm of a particular scenario outperforming traditional energy detection.

Original languageEnglish
Title of host publication2015 IEEE Conference on Antenna Measurements & Applications (CAMA)
PublisherIEEE
Number of pages4
ISBN (Electronic)9781467391498
DOIs
Publication statusPublished - 10 Mar 2015
EventIEEE Conference on Antenna Measurements 2015 - Chiang Mai, Thailand
Duration: 30 Nov 20152 Dec 2015

Conference

ConferenceIEEE Conference on Antenna Measurements 2015
CountryThailand
CityChiang Mai
Period30/11/152/12/15

Keywords

  • Computer Vision
  • Spectrogram
  • Bi-directional Self-organizing Neural Networks
  • Fuzzy Hostility Index
  • Morphological Filtering
  • Blob Detection

Cite this

Phonsri, S., Mukherjee, S. S., & Sellathurai, M. (2015). Computer Vision and Bi-directional Neural Network for Extraction of Communications Signal from Noisy Spectrogram. In 2015 IEEE Conference on Antenna Measurements & Applications (CAMA) [7428185] IEEE. https://doi.org/10.1109/CAMA.2015.7428185