Method for recognizing image of plant leaf

Abstract

The invention discloses a method for recognizing an image of a plant leaf. The method comprises a training stage and a recognition stage. The training stage comprises the following steps of: inputting an image training set of the plant leaf; and storing a training result after performing batch preprocessing, batch feature extraction and neural network classifier training by using a system. The recognition stage comprises the following steps of: allowing a user to input a single image of the plant leaf of which the variety is unknown to the system and mark the leaf base point coordinate and leaf apex point coordinate of the leaf; performing preprocessing and feature extraction on the single image by using the system; and classifying by using the neural network classifier, outputting a plant variety list and attaching detailed graphics and text information to each item of the list. The method has the advantages of outputting a plurality of high-accuracy candidate results, greatly enhancing recognition credibility, supporting a scalar quantity of leaf features as well as leaf features in complex forms (such as a matrix form) and increasing the recognition rate of the plant leaf.

Description

technical field [0001] The invention relates to the technical field of automatic plant classification, in particular to a method for identifying plant leaf images. Background technique [0002] Plants have been closely related to humans for thousands of years. With the progress of human civilization, plants have been damaged more and more seriously. Therefore, it is of great significance to identify and classify plants and establish a plant digital resource library to help protect plants. The plant leaf digital image machine recognition algorithm will undoubtedly greatly speed up the classification of plants. [0003] Due to the complex three-dimensional geometric features of flowers, fruits, stems and branches, the identification of leaves is relatively simple and effective for machines. Stephen Gang Wu et al. used a probabilistic neural network (PNN, full name Probabilistic Neural Network) to classify and identify plant leaves. Experiments show that the recognition rat...

AI Technical Summary

Problems solved by technology

Therefore, the quality and quantity of the features taken by this method need to be improved

[0007] Second, there is no mention of the selection or calculation of standard samples for each plant leaf in the database

However, there is still a certain degree of variation between the leaves of plants of the same species

Lack of representative standard samples, the matching effect will be greatly affected

[0008] Third, the classification method lacks a weight determination strategy

[0009] Fourth, the recognition rate of the system fails to meet the requirements of blade recognition applications

Images