Grain moisture content detecting method based on hyperspectral image technology

Abstract

The invention discloses a grain moisture content detecting method based on a hyperspectral image technology, which comprises the following steps: respectively acquiring an all black calibrated image B, an all white calibrated image W and a hyperspectral original data image I of grains the moisture content of which is given; carrying out reflection spectral correction on the hyperspectral original data image I of grains by the all black calibrated image B and the all white calibrated image W to obtain a corrected image R of grains; extracting the grain image from the corrected image R; carrying out spectral correction by a moving average method and multiplicative scatter correction; calculating the correlation coefficients of spectral reflection values and the moisture content; selecting a correlation coefficient as the maximum spectral reflection value to be input into an artificial neural network; and establishing a grain moisture prediction model. In the invention, the grain moisture content is detected by the artificial neural network according to the spectral signature of the grains caused by the moisture content, a quick stable method is provided, and the detecting efficiency is improved.

Description

technical field [0001] The invention relates to a method for detecting moisture content of grain grains based on hyperspectral image technology. Background technique [0002] The moisture content of grain grains is one of the important factors to determine its storage conditions. In actual production, a suitable production process is generally adopted. The grain grains are threshed and then sent to the drying tower. After preheating, drying, slowing down, and cooling to room temperature, After reaching a safe moisture content of about 14%, it is discharged from the drying tower. In this process, the online detection and control of grain moisture is the core technology that restricts the grain drying system; [0003] The traditional grain moisture detection mostly removes the moisture in the grain directly by drying or chemical methods, and detects the absolute moisture content of the sample. Among them, drying methods mainly include electric oven method, decompression meth...

AI Technical Summary

Problems solved by technology

These methods have high detection accuracy and are suitable for laboratory detection, but they are time-consuming and laborious, and have certain destructive effects on grain particles, so rapid online detection cannot be realized

Some other detection methods, such as capacitance method, acoustic method, nuclear magnetic resonance method, neutron moisture meter, etc., either have insufficient stability or are expensive and difficult to promote.

Images