Aedes identification method based on support vector machine

Abstract

The invention discloses an aedes identification method based on a support vector machine. The method comprises a training stage and a testing stage. Wherein in the training stage, firstly, image preprocessing is carried out, and the sizes of collected color mosquito images are normalized; then, image feature extraction is carried out, and color histogram features and direction gradient histogram features are extracted respectively and fused in a series connection mode; and finally, a support vector machine classifier is trained, and the sample is trained by adopting a linear kernel support vector machine function. In the testing stage, the tested mosquito images are sequentially subjected to preprocessing and feature extraction according to the training stage, the obtained features are input into the trained model, and the types of the mosquito images are output. The method is simple and easy to implement, the extracted features have little dependence on the size, direction and visualangle of the image, good invariance can be kept for geometric and optical deformation of the image, and therefore high robustness is achieved.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to view more

AI Technical Summary

Benefits of technology

This technology allows us to identify different types of insects that are more difficult or expensive than others because they have similar colors but may change their appearance depending upon how it's seen from them. It uses an algorithm called Support Vector Machines (SVM) with this extra characteristic to extract specific characteristics about these objects like shape changes caused by light exposures during flight. These attributes help distinguish between those who don’t want harmful pests such as Anopheles spp., Dengue fever virus, etc.

Problems solved by technology

Technological Problem: Current techniques used for detecting denguefections are slow and require expensive equipment that can be difficult to interpret correctly due to their complexity. Additionally, there may still exist false alarms caused by incorrect recognition during this process.