No abstract

In order to effectively detect the distribution of Cd in lettuce leaves, this article proposes a wavelet support vector machine regression (WSVR) modeling method and uses it in the prediction of cadmium (Cd) content in lettuce leaves. In addition, this article also observed the internal and external tissue structure of lettuce leaves under different concentrations of Cd stress by scanning electron microscopy and transmission electron microscopy. Moreover, the lettuce leaf samples under different Cd concentration stresses were acquired by the hyperspectral imaging system, different preprocessing algorithms combined with dimensionality reduction algorithms were used to select the spectral characteristic wavelengths, and SVR and WSVR models were established based on the spectral characteristic data. The results showed that with the increase of Cd concentration, the internal and external tissue structure of lettuce leaves changed significantly. The WSVR model parameters for the best prediction of Cd concentration in lettuce were Rp2 of 0.8843, RMSEP of 0.1292 mg/kg. Finally, the Cd contents in lettuce leaves were visualized on the prediction maps by predicted spectral features on each hyperspectral image pixel. Practical Applications It is of great significance to realize the visual expression of the distribution of heavy metals in crop leaves through nondestructive testing. In order to demonstrate the feasibility of Vis‐NIR hyperspectral imaging technology for the detection of cadmium (Cd) content in lettuce leaves, scanning electron microscopy and transmission electron microscopy were used to observe the internal and external tissue structure of lettuce leaves under different concentrations of Cd. Wavelet support vector machine regression modeling method was proposed and used to predict the Cd content in lettuce leaves. It is proved that the Vis‐NIR hyperspectral imaging technology is a feasible and effective method to realize the visualization of Cd content distribution in crop leaves.

We built a new system for object recognition by combining the joint transform structure with the wavelet transform. The system can perform preprocessing and correlation in a single step. It has many good features including high antinoise capability and sharp correlation peaks without sidelobes. To test the effectiveness of this system, experimental results on a plane model are also given.