Plant species identification method based on leaf HOG features and intelligent terminal platform

Abstract

The invention relates to a plant species identification method based on leaf HOG (Histograms of Oriented Gradients) features and an intelligent terminal platform. The method comprises the following steps that: (1) a client obtains leaf images; (2) the obtained leaf images are preprocessed and are then transmitted to a server end, and meanwhile, an identification request is sent to the server end; (3) after the server end receives the identification request, the leaf images are subjected to HOG feature extraction; (4) the extracted HOG features are used as the input of a trained SVM (Support Vector Machine) classifier, and the leaf images are subjected to classification identification; (5) plant species information of categories corresponding to the current leaf images is found from a plant species database according to identification results, and is sent to the client; and (6) the client displays the identification results and the corresponding plant species information. Compared with the prior art, the plant species identification method has the advantages that the accuracy is high, the use is convenient, and the like.

Description

technical field [0001] The invention relates to an image processing technology, in particular to a plant species identification method based on leaf HOG features and an intelligent terminal platform. Background technique [0002] At present, there are three main methods of plant species identification: [0003] (1) Manually affixed species labels: This is a method adopted by most botanical gardens or parks to facilitate tourists to identify plant species, that is, to paste labels engraved with plant-related information on plant branches for tourists to read . This method has congenital deficiencies such as consuming manpower and material resources, conveying less information, not being eye-catching, and easily corroded labels. Limited to this, it is only popularized in fee-paying or protected scenic spots; [0004] (2) QR code pasted manually: This method can be regarded as an upgraded version of method (1), which is the product of the combination of species labeling and t...

AI Technical Summary

Problems solved by technology

This method has congenital deficiencies such as consuming manpower and material resources, conveying less information, not being eye-catching, and easily corroded labels. Limited to this, it is only popularized in fee-paying or protected scenic spots;

[0004] (2) QR code pasted manually: This method can be regarded as an upgraded version of method (1), which is the product of the combination of species labeling and the development of modern electronic technology. Tourists scan the QR code pasted on the branches of plants , access to the Internet can obtain rich plant species information. This method overcomes the shortcomings of the method (1) in the transmission of less information, but there are still shortcomings such as labor-intensive physics and labels are easy to be corroded. It is only available in a very small number of parks. implementation, which is still in the experimental phase;

[0005] (3) Research by professional plant taxonomy workers: This is the most traditional plant taxonomy research method. Researchers classify specimens by collecting specimens and manual measurements, combined with empirical knowledge and book guidance. This method works The volume is huge and requires a lot of expertise, which can only be implemented in the field of scientific research

The objects of these studies are mostly limited to several plants in a specific field, and have not been popularized.

Images