The development of spectroscopic survey telescopes like Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST), Apache Point Observatory Galactic Evolution Experiment and Sloan Digital Sky Survey has opened up unprecedented opportunities for stellar classification. Specific types of stars, such as early-type emission-line stars and those with stellar winds, can be distinguished by the profiles of their spectral lines. In this paper, we introduce a method based on derivative spectroscopy (DS) designed to detect signals within complex backgrounds and provide a preliminary estimation of curve profiles. This method exhibits a unique advantage in identifying weak signals and unusual spectral line profiles when compared to other popular line detection methods. We validated our approach using synthesis spectra, demonstrating that DS can detect emission signals three times fainter than Gaussian fitting. Furthermore, we applied our method to 579,680 co-added spectra from LAMOST Medium-Resolution Spectroscopic Survey, identifying 16,629 spectra with emission peaks around the Hα line from 10,963 stars. These spectra were classified into three distinct morphological groups, resulting in nine subclasses as follows. (1) Emission peak above the pseudo-continuum line (single peak, double peaks, emission peak situated within an absorption line, P Cygni profile, Inverse P Cygni profile); (2) Emission peak below the pseudo-continuum line (sharp emission peak, double absorption peaks, emission peak shifted to one side of the absorption line); (3) Emission peak between the pseudo-continuum line.

There are currently no refbacks.