Tobacco leaf grade identification method and system based on MHHO algorithm and SVM model

Abstract

The invention discloses a tobacco leaf grade identification method and system based on an MHHO algorithm and an SVM model, and the method comprises the steps: obtaining a tobacco leaf grade chemical component data set, carrying out the training of an initial SVM model through the combination of the MHHO algorithm, and obtaining an optimized SVM model; obtaining a to-be-classified tobacco leaf grade chemical component data set; inputting the data set into the optimized SVM model; according to an SVM model output result, tobacco leaf grades are determined and classified; sVM model optimization specifically comprises the steps of optimizing SVM model selection parameters through an MHHO algorithm, and achieving SVM model optimization; according to the MHHO algorithm, a nonlinear time-varying strategy of chaos disturbance convergence is used for updating a calculation strategy of escape energy in the development stage explored and converted by the Harris eagle algorithm; a nonlinear time-varying strategy of chaos disturbance convergence is used for updating a position updating strategy in a development stage in the Harris eagle algorithm. According to the method, data errors are reduced, and the tobacco leaf grade identification efficiency and precision are effectively improved.

Description

technical field [0001] The invention relates to the technical field of tobacco identification, in particular to a tobacco grade identification method and system based on an MHHO algorithm and an SVM model. Background technique [0002] In the tobacco industry, the grade of tobacco leaves directly affects the quality and taste of cigarettes, so the classification of tobacco leaves is of great significance. The traditional classification of tobacco leaves mainly relies on professionals to identify the quality of tobacco leaves through vision, touch, smell and other senses, and then comprehensively evaluate the tobacco leaf grades. This method is mixed with more subjective factors and has a greater correlation with the experience of professionals, resulting in low efficiency and difficulty in ensuring accuracy. [0003] Existing extraction and analysis of features such as color, size, shape, and surface texture of tobacco leaf images, and inputting these feature data into a ne...

AI Technical Summary

Problems solved by technology

[0005] The parameters of the support vector machine affect its classification accuracy, and there are certain difficulties in the selection of parameters. Therefore, the existing Harris eagle optimization algorithm is used to select the optimal parameters of the support vector machine. At different stages, Harris eagle individuals adopt different strategies Hunting, this multi-strategy search method makes the Harris Eagle optimization algorithm have good optimization accuracy and convergence performance. However, when the algorithm iterates to the later stage, the population position update converges and the population diversity is single, making it difficult for the algorithm to jump out of the local optimum. Excellent, which affects the accuracy and speed of algorithm convergence

Images