拉曼谱峰识别是拉曼定性分析中的关键技术之一, 针对现有拉曼谱峰识别方法中存在的缺陷和不足提出了一种双尺度相关拉曼光谱谱峰识别方法, 即采用两个尺度下的相关系数与局部信噪比相结合来实现拉曼谱峰识别。 利用MATLAB对所提算法与传统的连续小波变换法进行了对比分析, 并通过实测拉曼光谱进行验证。 分析结果: 双尺度相关法识别一幅拉曼谱的平均时间为0.51 s, 连续小波变换法为0.71 s； 当谱峰信噪比≥6时（现代拉曼光谱仪器均可达到较高的信噪比）, 双尺度相关法的谱峰识别准确率高于99%, 连续小波变换法的谱峰识别准确率小于84%, 且双尺度相关法谱峰位置识别误差的均值与标准差均要小于连续小波变换法。 通过仿真对比分析和实验验证表明: 双尺度相关法具有无需人工干预, 无需做去噪及去背景等预处理操作, 识别速度快, 识别准确率高等特点, 是一种切实可行的拉曼谱峰识别方法。

The authors proposed a new Raman peak recognition method named bi-scale correlation algorithm. The algorithm uses the combination of the correlation coefficient and the local signal-to-noise ratio under two scales to achieve Raman peak identification. We compared the performance of the proposed algorithm with that of the traditional continuous wavelet transform method through MATLAB, and then tested the algorithm with real Raman spectra. The results show that the average time for identifying a Raman spectrum is 0.51 s with the algorithm, while it is 0.71 s with the continuous wavelet transform. When the signal-to-noise ratio of Raman peak is greater than or equal to 6(modern Raman spectrometers feature an excellent signal-to-noise ratio), the recognition accuracy with the algorithm is higher than 99%, while it is less than 84% with the continuous wavelet transform method. The mean and the standard deviations of the peak position identification error of the algorithm are both less than that of the continuous wavelet transform method. Simulation analysis and experimental verification prove that the new algorithm possesses the following advantages: no needs of human intervention, no needs of de-noising and background removal operation, higher recognition speed and higher recognition accuracy. The proposed algorithm is operable in Raman peak identification.