A method and device for nondestructive testing of passion fruit maturity based on multi-source information

Abstract

The present invention provides a method and device for nondestructive testing of passion fruit maturity based on multi-source information. The method includes: acquiring a carbon dioxide concentration value exhaled from a test sample, and determining the respiration rate of the sample to be tested according to the carbon dioxide concentration value; The two-dimensional grayscale image of each band of hyperspectral imaging, the two-dimensional grayscale images of all bands are synthesized into a three-dimensional hyperspectral image, and the image features of the region of interest of the detection sample are extracted from the hyperspectral image; the detection sample is extracted from the hyperspectral image. The original spectral curve of the region of interest, and extract the spectral features according to the original spectral curve, the spectral features are the reflectance of different wavelengths; input the respiration rate, image features and spectral features into the detection model obtained by pre-training to obtain the maturity of the sample to be tested Spend. The method does not need to destroy the passion fruit itself, has high detection efficiency and low detection cost, and can avoid the limitations and low accuracy of conventional machine learning methods.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a nondestructive testing technology for agricultural products, in particular to a nondestructive testing method and device for ripeness of passion fruit based on multi-source information. Background technique [0002] In recent years, with the development of the economy and the improvement of consumption levels, consumers' requirements for the quality of passion fruit have gradually increased. The internal and external quality of passion fruit has a greater relationship with the maturity of passion fruit. The maturity of passion fruit can be determined according to the sweetness and sourness, but passion fruit needs to be cut. At the same time, the maturity of passion fruit is also directly related to its most suitable edible state and taste. [0003] The current evaluation and judgment of passion fruit maturity mainly rely on visual observation, and there are problems of...

AI Technical Summary

Problems solved by technology

[0003] At present, the evaluation and judgment of the maturity of passion fruit mainly depends on the naked eye observation. There are problems of uneven classification quality, slow classification efficiency, and inaccurate classification, which cannot meet the needs of the large-scale fruit market.

Images