Classification of heavy metal Cd stress in lettuce leaves based on WPCA algorithm and fluorescence hyperspectral technology

Abstract

The feasibility of fluorescence hyperspectral technology to classify lettuce leaves under different heavy metal pollutant cadmium stress was discussed and demonstrated, and the wavelet principal component analysis (WPCA) algorithm was proposed to effectively reduce the dimensionality of the data in this paper. The fluorescence hyperspectral images of 1250 lettuce leaves with 5 cadmium (Cd) stress categories (contrast check, low pollution, light pollution, medium pollution and severe pollution) were obtained by fluorescence hyperspectral imaging instrument. In addition, the results of atomic absorption spectrometry showed that the Cd content in lettuce leaves increased with the increase of Cd stress concentration. Taking the entire lettuce leaf as the region of interest, the ROI fluorescence hyperspectra of the lettuce leaf was obtained through mask processing. Then, WPCA was used to reduce the dimensionality of the fluorescence hyperspectral data with different wavelet basis function including db4, db5, db6, sym5 and sym7. Support vector machine (SVM) and cuckoo search optimization support vector machine (CS-SVM) models were set up based on WPCA dimensionality reduction data. Besides, the classification accuracy rate of WPCA-CS-SVM model for Cd stress lettuce leaves was higher than that of WPCA-SVM model. Among them, the WPCA-CS-SVM model based on the third layer decomposition of the sym7 wavelet basis function had the best performance, the accuracy of the calibration set and the prediction set were 99.79% and 94.19%, and the modeling time was only 465.32 s. WPCA algorithm combined with fluorescence hyperspectral technology could effectively realize the classification of lettuce leaves under different Cd concentration stress.