基于云计算的图像分类算法  

Image classification algorithm based on cloud computing

作　　者：黄金国[1] 

机构地区：[1]江苏开放大学信息与机电工程学院,江苏南京210017

出　　处：《现代电子技术》2017年第5期63-65,69,共4页Modern Electronics Technique

基　　金：江苏省高校自然科学研究项目(15KJD520003)

摘　　要：针对单节点的图像分类算法效率低,实时性差的难题,提出基于云计算的图像分类算法。首先提取图像数据库中的图像分类特征;然后将待分类图像通过云计算模式与图像库中的特征进行匹配,并根据匹配结果将其划分到相应的类别中;最后采用UPenn和Caltech-101数据库测试算法的可行性。结果表明,该算法降低了图像分类的时间复杂度,取得了不错的图像分类结果,且分类效率要明显优于对比算法,具有良好的实际应用价值。Since the image classification algorithm for the single node has low efficiency and poor real-time performance, an image classification algorithm based on cloud computing is proposed. With the algorithm, the classification features of the images in the image database are extracted, and then the images under classification are matched with the feature in the image library by means of the cloud computing mode and divided into the corresponding classes according to the matching results. The databases of UPenn and Cahech-lO1 are used to test the feasibility of the algorithm. The results show that the algorithm has reduced the time complexity of image classification, obtained a good image classification result, its classification efficiency is obviously supe- rior to the comparing algorithm, and has a certain practical application value.

关 键 词：云计算 海量图像数据库 图像分类器 图像特征 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP181[自动化与计算机技术—计算机科学与技术]