朱维斌,李继哲,叶树亮.基于SIFT的小模数齿轮图像亚像素级配准研究[J].仪器仪表学报,2017,38(9):2326-2334
基于SIFT的小模数齿轮图像亚像素级配准研究
Research on sub pixel registration of fine pitch gear image based on SIFT
  
DOI:
中文关键词:  视觉测量  小模数齿轮  图像配准  全局直方图均衡化  两倍中误差准则
英文关键词:vision measurement  fine pitch gear  image registration  global histogram equalization  2σ criterion
基金项目:
作者单位
朱维斌 中国计量大学工业与商贸计量技术研究所杭州310018 
李继哲 中国计量大学工业与商贸计量技术研究所杭州310018 
叶树亮 中国计量大学工业与商贸计量技术研究所杭州310018 
AuthorInstitution
Zhu Weibin Institute of Industry and Trade Measurement Technique, China University of Metrology, Hangzhou 310018, China 
Li Jizhe Institute of Industry and Trade Measurement Technique, China University of Metrology, Hangzhou 310018, China 
Ye Shuliang Institute of Industry and Trade Measurement Technique, China University of Metrology, Hangzhou 310018, China 
摘要点击次数: 408
全文下载次数: 608
中文摘要:
      为解决小模数齿轮视觉测量中凸显的工业相机高空间分辨率与大视场相互制约的问题,对轮廓光条件下前景背景对比度过强、局部对比度不足,存在大面积同色区域的小模数齿轮图像亚像素级配准方法进行研究。针对传统基于特征点的图像配准流程在小模数齿轮图像配准中存在特征点数量稀少、正确匹配率过低的问题,介绍了适用于小模数齿轮图像的配准流程;引入直方图均衡化改善图像对比度,丰富灰度色调,增晰图像暗部特征以提升特征点数量和正确匹配率;为了克服传统匹配对提纯算法中阈值设置不准确、参数调整困难及模型不唯一的缺点,结合两倍中误差准则提出全局自适应参数匹配点对提纯方法,保证提纯结果唯一性的同时,其自适应调整判别阈值的方法可避免人为误差进而保证结果的重复性。实验结果表明,利用介绍的方法对图像进行预处理可大幅度提升特征点数量与正确匹配率,取提纯所得平移量的平均值作为配准结果,其正确度和精密度均优于传统算法,针对轮廓光条件下的小模数齿轮图像,配准精度优于0.083 pixel,对于小模数齿轮视觉测量具有实际应用价值。
英文摘要:
      In order to solve the problem of mutual restriction between high spatial resolution and large field of view of industrial cameras prominently protruded in the visual measurement of fine pitch gear, this paper studies on the sub pixel image registration method for fine pitch gear that has strong foreground background contrast, insufficient local contrast and large area of the same color under rimming light condition. Aiming at the problem of less feature points and low correct matching rate in the image registration process based on feature points in fine pitch gear image registration, the registration process suitable for fine pitch gear image is described in this paper, the global histogram equalization is introduced to improve image contrast, enrich grey level and enhance the feature information in dark part of the image, so that the number of feature points and correct matching rate are improved. In order to overcome the deficiency of incorrect threshold setting, parameter adjustment difficulty and model nonuniqueness of traditional matching pair purification algorithm, combining with 2σ criterion, the global self adaptive parameter matching point pair purification algorithm is put forward, which not only ensures the uniqueness of the purification result, but also adjust the judgment threshold adaptively to avoid artificial error and ensure the repeatability of result. Experiment results show that the number of feature points and correct matching rate are greatly increased when the image is preprocessing with the method described in this paper. Besides, the registration result measured by the average of translation amount purified with the method described in this paper outperforms that of the traditional method in correctness and precision. Aiming at the fine pitch gear image under rimming light condition, the registration precision is better than 0.083 pixel, which has great practical application value for the visual measurement of fine pitch gear.
查看全文  查看/发表评论  下载PDF阅读器