Visible light image-based walnut maturity detection and prediction method

Abstract

The invention relates to a visible light image-based walnut maturity detection and prediction method, and belongs to the field of deep learning and image processing. The method comprises the following steps: firstly, collecting walnut samples and color images of the walnut samples in different periods, measuring fat contents of the samples, and dividing walnut maturity grades according to the fat contents and external characteristics of walnut kernels in different periods; and establishing a walnut maturity detection and prediction data set; then performing low-illumination walnut image screening and preprocessing, then inputting the images into an improved Faster RCNN network, outputting the maturity of walnuts in the images by the network, marking the maturity with a suggestion box, and evaluating the fat content of walnut kernels under the maturity at the same time. and finally, intercepting a walnut region from the original image according to the walnut suggestion box, inputting the walnut region into a walnut maturity prediction algorithm based on LSTM, and performing walnut maturity and fat content prediction after three days. The method can accurately detect the current maturity of the walnuts in the image and the maturity of the walnuts after three days and evaluate the fat content of the walnuts.

Description

technical field [0001] The invention belongs to the field of deep learning and image processing, in particular to a walnut maturity detection and prediction method based on visible light images. Background technique [0002] The oil yield of walnut kernels is closely related to its maturity. Walnuts picked earlier are not fully mature, their oil yield is low, and the transformation of various nutrients has not yet been completed; walnuts picked later are prone to mold and deterioration. And then affect the quality of walnut oil. Therefore, how to judge the maturity of walnuts in the current period and predict the maturity of walnuts is conducive to guiding harvesting, improving the quality and quality of walnut kernel oil, and improving the economic benefits of walnut planting industry and oil extraction enterprises . [0003] According to the current knowledge, no method for detecting and predicting the maturity of walnuts has been found, and the methods for detecting or ...

AI Technical Summary

Problems solved by technology

[0003] According to the current knowledge, no method for detecting and predicting the maturity of walnuts has been found, and the methods for detecting or predicting the maturity of other crops or fruits are still insufficient in the task of detecting and predicting the maturity of walnuts:

However, this method has several shortcomings: first, this method needs to repeatedly measure the data of multiple meteorological factors, which is cumbersome and time-consuming; second, this method needs to use different instruments to measure ground temperature, air temperature, humidity, sunshine duration and precipitation The accuracy of each data is susceptible to interference from factors such as instrument accuracy, environmental complexity, and measurement standardization, so the measurement results are not conducive to the accuracy of the final prediction results

In the blueberry maturity non-destructive detection process [0030], [0033], [0034], this invention divides the chlorophyll content prediction data set BCPD according to the chlorophyll content in the blueberry, and carries out the training of the blueberry chlorophyll prediction content network BCPN, and the volume obtained by training The product neural network can be used to predict the maturity of blueberries. However, this method has the following disadvantages for the reference of walnut maturity detection: First, measure the chlorophyll value of each period and use the Label-Image script to label the images of the corresponding period. Construct the chlorophyll content prediction data set BCPD, and use the data set for the training and testing of the blueberry chlorophyll content prediction network BCPN. The color change of the inner appearance is extremely weak, and the method proposed by this invention is not suitable for the detection of walnut maturity; second, the method is mainly used to judge the maturity of the blueberry in the image, but it does not determine the degree of maturity of the main nutrients. However, walnut maturity detection not only needs to detect the maturity of each walnut in the image, but also needs to analyze the content of main nutrients in the walnut kernel under this maturity; third, this method is mainly to input the color image of the prediction model Maturity prediction of the blueberry in the blueberry, if the blueberry is not yet ripe, the future maturity of the blueberry cannot be predicted

Images