基于Bag of Features模型的害虫图像分类技术研究

STUDY ON PEST IMAGE CLASSIFICATION WITH BASE ON BAG OF FEATURES MODEL

将Bag of Features模型结合OpenCV开源图像库提取害虫图像的特征,然后用Kmedoids算法对其进行聚类,生成关键字,最后用AdaBoosting算法构建分类器,实验采用Pascal Voc图像库中的数据进行训练和测试,实验表明,该算法分类精度高、特征提取速度和分类速度也比较快。

In this paper, the Bag of features model had been combined with the OpenCV open source to extract image feature of insect, and then using K-medoids algorithm to cluster them and generate the key words dictionary query needs. Finally, it builds the sorter with adaboosting algorithm. The experiment uses the data in pascal image libary to do training and testing. The result shows that this algorithm has high training and testing speed, high accuracy on classification, ect. Moreover, the feature extraction and classificiton speed is very high.