基于LBP和SVM的工件图像特征识别研究  

Research on Workpiece Image Feature Recognition Based on LBP and SVM

作　　者：吴益红[1] 许钢[1] 江娟娟[1] 毕运锋 

机构地区：[1]安徽工程大学安徽检测技术与节能装置省级实验室,安徽芜湖241000

出　　处：《重庆理工大学学报（自然科学）》2016年第1期77-84,共8页Journal of Chongqing University of Technology：Natural Science

基　　金：国家自然科学基金资助项目(61271377);安徽省高等教育提升计划省级自然科学研究一般项目(2014B02)

摘　　要：针对工业现场诸如粉尘、光照、遮挡、摄像机抖动等复杂环境下工件目标的识别问题,提出一种基于局部二值模式(local binary pattern,LBP)和支持向量机(support vector machine,SVM)的组合模型,对工件图像进行特征提取与类别判定。运用基本LBP模式、LBP等价模式以及LBP旋转不变模式,并结合多种去噪方法对工件图片进行特征提取,得出LBP特征直方图。根据这些特征直方图,利用分类模型对工件进行分类识别。实验结果表明:基于均值滤波去噪的LBP基本特征算子较好地满足了工件图像的特征提取要求,为后续的工件图片分类提供了保障,使得图片识别准确率达96%,识别效果较佳。Aiming at the problem of workpiece identification in the complex environment of industry field such as dust, light, shelter, and camera shake, this paper proposed a combined model based on local binary pattern （LBP for short） and support vector machine（ SVM for short） for feature extraction and recognition of the workpiece images. By using basic LBP pattern, LBP uniform pattern and LBP rotation invariant pattern and combining with various noise attenuation, we extracted and analyzed workpieee image features, and obtained LBP feature histogram, and then classified and recognized the workpiece image by utilizing classification models according to these characteristics. The experimental results indicate that the basic LBP pattern on Mean Filter is more suitable for the feature extraction and provides guarantees for classification of the workpiece images, and the image recognition effect is better and the recognition rate is up to 96%.

关 键 词：工件图像 局部二值模式 支持向量机 特征提取 工件分类 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]