Continuum problem is a phenomenon that the continuum of spectra get off their actual continuum even break off due to interstellar extinction and flux calibration, and it will have negative impact on the subsequent process such as spectral line extraction and so on. Due to this problem and considering of the continuum features of the stellar spectra, a method of automatic detection and recognition of the continuum problem in the stellar spectra is proposed, which will improve work efficiency greatly compared with the traditional human eyes examination under the condition of maintaining high accuracy. Firstly in this method, the subclass of the test stellar spectra is confirm by calculating the spectra’s lick indices, and the test stellar spectra are normalized . Secondly, the continuum of the test stellar spectra and the template spectra are fit with the same method. The last step goes to continuum template matching. The flux differences of the test stellar spectra and template spectra at every point of wavelength in the continuum spectra will be calculated to analyze the features of its distribution. The features counted are average (called β) value and standard deviation (called δ). The percentage of points distributed in range β±ɑ*δ will be detected to confirm that if there is continuum problem. In the end, this method has been proven to have a good effect on detecting and recognizing the continuum problem spectra by a great deal of experiments.