Online plant species identification method based on geometric invariant shape features

Abstract

The invention relates to an online plant species identification method based on geometric invariant shape features. The method includes 1, allowing a browser to acquire leaf image and transmit to a server after pre-processing; 2, allowing the server to calculate the leaf shape features according to pre-processed leaf images, establishing feature vectors, storing a trained moving center hypersphere classifier in the server, allowing the moving center hypersphere classifier to perform species identification according to the feature vectors, outputting the plant species code, querying a leaf information database according to the plant species code, and feeding the final identification result back to the browser; 3, allowing the browser to display the final identification result including the leaf, flower, fruit and seed images of the identified species and the scientific instruction information of the species. Compared with the prior art, the method has the advantages of fine real-time performance, convenience and high accuracy.

Description

Technical field [0001] The invention relates to a method for plant identification, in particular to an online plant species identification method based on geometrically invariant shape features. Background technique [0002] In the biological sense, plant taxonomy is a discipline that divides plant species, studies the origin of plants of the same group, explores the genetic relationship between plants and the evolution and development of species. Through the comparison between various species, various plants can be identified, grouped and named, and arranged to facilitate people's knowledge and understanding of plants. The original plant classification is mainly based on the differences in the morphology, habits, and uses of plants, without considering the genetic and evolutionary relationship between plants. For example, in my country's "Compendium of Materia Medica", plants are divided into five parts: grass part, fruit part, wood part, grain store part, and vegetable part ac...

AI Technical Summary

Problems solved by technology

[0005] After investigation, it is found that (1) the above identification methods are mostly applied to a single leaf, and cannot be used for leaves under complex backgrounds

(2) Traditional recognition is based on embedded or C / S architecture mode recognition system, which requires handheld devices or installation programs

(3) The objects of the above research work are mostly limited to several or a small number of species of plants in a specific field, and have not been widely used

And because of its own defects, it is not very convenient and quick, and the cost is relatively large

(4) Leaf shape, as a very important feature of leaf images, has not been fully utilized as identification evidence

Images