Apply Physical System Model and Computer Algorithm to Identify Osmanthus Fragrans Seed Vigor Based on Hyperspectral Imaging and Convolutional Neural Network

Rapid identification of seed vitality plays key roles in the cultivation of the agricultural and forestry crops. This study discusses the use of compose a specular like technology, the computer algorithm and the feasibility of the physical system identification under different osmanthus seed vigor, in order to improve the ability to recognize. Two varieties of Osmanthus seeds (JinQiGui and RiXiangGui) were artificially aged and then hyperspectral data were collected. Multivariate scattering correction (MSC) and competitive adaptive reweighted sampling algorithm (CARS) were used for spectral preprocessing and feature wavelength selection, respectively. The extreme learning machine (ELM) and k-nearest neighbor (KNN) were used to establish the spectral discriminant model, and convolutional neural network was used in the computer image discriminant model. When MSC+CARS is combined with the above Discriminative model, nearly 100% recognition can be achieved with fewer bands. Compared with machine learning model, image-depth learning model can get higher model accuracy for different vigor JQG and RXG without complex preprocessing. These results indicate that hyperspectral imaging technology can effectively distinguish different vigor of Osmanthus fragrans seeds based on computer technology and physical system. Combining deep neural networks with image information is of great importance for research and development of portable high precision seed vitality spectral imagers.