Pinellia ternate quality grading method based on neural network

Abstract

The invention discloses a pinellia ternate quality grading method based on a neural network. The method comprises the following steps that: a terminal obtains the size, defect area, shape, color, surface texture and color distribution of pinellia ternate from an acquired pinellia ternate image through machine vision; the size, defect area, shape, color, surface texture and color distribution of pinellia ternate are further combined with the temperature and humidity of the operation area to form eight-dimensional characteristic data as the input quantity of the BP neural network, and the manually marked pinellia ternate quality grade is used as the output quantity; bP neural network training and testing are carried out; inputting the acquired pinellia ternate images into the neural networkmodels processed in the step 1 and trained in the step 2 to obtain pinellia ternate quality grades, acquiring operation positions of a pinellia ternate harvester and manually recorded receiving batchnumbers by combining with a GPS sensor, and generating exclusive traceable information two-dimensional codes by adopting a QR Code encoding technology. The pinellia ternate quality can be accurately determined, and pinellia ternate product information traceability is achieved.

Description

technical field [0001] The invention belongs to the field of agricultural technology, in particular to a neural network-based method for grading the quality of Pinellia pinellia. Background technique [0002] In the context of the rapid development of information technology, "smart agriculture" is a new generation of new agricultural production methods that integrate the Internet, cloud computing, Internet of Things and artificial intelligence, enabling the comprehensive and comprehensive application of various information technologies in agriculture . The traceability of agricultural product information is an important guarantee for its quality and safety. As an important Chinese medicinal material with anti-cancer effects, the traceability of its production information is especially important. At present, a large amount of data in the process of pinellia planting and production, such as origin, production environment, fertilization, etc., have not been effectively recorde...

AI Technical Summary

Problems solved by technology

The information recorded in this method is limited, most of which are product processing information rather than production information, and some data are input manually, which inevitably has data reliability problems, so it is not suitable for agricultural products such as pinellia.

Images