Jump to main content
Jump to site search


Spectral features extraction based on continuous wavelet transform and image segmentation for peak detection

Abstract

Peak detection is a crucial step in spectral signal pre-processing. The accurate locations of the characteristic peaks are the prerequisite for chemical identification. However, the measured spectra inevitably contain both noise and baseline signals. These interference signals will generate a series of false peaks, which is a challenge for spectral analyses. For this purpose, a spectral peak detection algorithm (CWT-IS) based on continuous wavelet transform (CWT) and image segmentation (IS) is proposed. First, the wavelet coefficient matrix is obtained by CWT, then the matrix is converted to a gray image and the image is segmented by a machine vision method, an improved version of Otsu method based on fuzzy mathematical theory. The desired threshold can be determined based on the membership grades of segmentation performance and the features of the false peaks are eliminated. The fuzzy Otsu method solves the problem that the traditional Otsu method cannot effectively handle the image with a unimodal histogram, thus, this method can accurately separate the peak regions from the CWT coefficient matrix and the ridges representing the peaks are complete. The method has been successfully applied to the peak detection of simulated spectra and MALDI–TOF spectra. The experimental results show that CWT-IS can effectively eliminate the adverse effect of noise and baseline and make the features of spectral peaks become more obvious, which is conducive to determine the characteristic peak positions.

Back to tab navigation

Supplementary files

Publication details

The article was received on 21 Sep 2019, accepted on 22 Nov 2019 and first published on 22 Nov 2019


Article type: Paper
DOI: 10.1039/C9AY02052G
Anal. Methods, 2019, Accepted Manuscript

  •   Request permissions

    Spectral features extraction based on continuous wavelet transform and image segmentation for peak detection

    G. Yang, J. Dai, X. Liu, M. Chen and X. Wu, Anal. Methods, 2019, Accepted Manuscript , DOI: 10.1039/C9AY02052G

Search articles by author

Spotlight

Advertisements