基于BoW模型的油茶害虫图像分类

Classifi cation research of oil-tea pest images based on BoW model

针对目前图像识别在油茶害虫这个领域的应用中存在的问题,提出一种基于BoW模型的油茶害虫图像识别的方法。首先对油茶害虫图像进行SIFT特征提取,然后通过Bo W模型来描述各幅图像,针对每类油茶害虫,利用支持向量机(SVM)训练,进而从图像中识别出油茶害虫的种类。实验结果表明:该方法用在油茶害虫图像模式分类问题上取得了较好的识别率,其平均识别率达到了83.3%,由此表明BoW模型用于油茶害虫图像分类的有效性。

For the existing problem of image recognition applying in the ifeld of Camellia pests, a Camellia pest image recognition method was put forward based on BoW model. Firstly, the SIFT features of oil-tea pest image were extracted, and then by using BoW model the images were described, and last the species of oil-tea pests were identiifed through support vector machine （SVM） training. The experimental results show that the method used in oil-tea pest image pattern classiifcation had a better recognition rate, with an average recognition rate of 83.3%.