Tobacco Leaf Image Feature Extraction And Evaluation Of Threshing Effect

The purpose of threshing is to produce tobacco leaves suitable for silk processing in cigarette factories.In the process of shredded tobacco leaves,the stalks in the tobacco leaves will increase the amount of stalks and stalks in the tobacco,reduce the purity of the tobacco,and affect the operating efficiency of the cigarette maker and the quality of cigarette products.The large,medium and round-shaped tobacco leaves have the best silk-making effect.Therefore,improving the separation quality of the stem and leaves of the threshing process and the shape and structure of the tobacco leaves have become a topic of great importance to cigarette factories and threshing and redrying enterprises.This article takes the tobacco leaf structure after threshing as the research object,and aims to improve the threshing effect.The following three aspects are mainly carried out:1.Test the image collection of tobacco leaves after threshing.By adjusting the three parameters of the feed rate of the threshing machine,the rotating speed of the threshing roller,and the opening of the frame,the images of tobacco leaves under different combinations of parameters are obtained,and image processing technology is used to extract The shape characteristic parameters of tobacco leaves are obtained from the data studied in this paper.2.With >12.7mm leaf rate(large and medium leaf rate),leaf stalk rate,stalk rate,round-shaped leaf rate,and broken leaf rate,design an evaluation index based on the analytic hierarchy process-entropy weight method The threshing effect matrix weighting method not only considers the amount of information provided by various indicators,but also takes into account the subjective opinions of experts,which improves the accuracy and scientificity of the indicator weights.Combined with the TOPSIS method and the grey relational analysis method,the selection of the threshing effect plan was realized from the two aspects of position and shape,and the quality of threshing effect was evaluated.3.Use BP neural network to predict and analyze the threshing effect,construct regression equations,factor graphs,and 3D surface graphs to explore the influence of threshing process parameters on the threshing effect.The results show that the order of the influence of each process parameter on the threshing rate is as follows: feed volume,frame opening,and threshing speed.There is an obvious interaction between the feed rate and the speed of the beater,and the feed rate and the opening of the frame.The interaction between the speed of the beater and the opening of the frame is not obvious.Under certain conditions,lower the feed rate,the opening of the frame,and the speed of the beater can obtain a higher threshing effect.