摘要
针对低分辨率图像边缘模糊,难以精确定位和测量的问题,分析高低分辨率边缘梯度沿梯度方向的统计特性,以广义高斯分布对梯度统计特性进行描述。通过大量训练样本建立高低分辨率梯度统计特性之间的关系,从而在低分辨率视觉图像中重建高分辨率边缘梯度图。并在此基础上实现边缘的精确定位,完成工件的准确测量。实验结果证明:所提出的方法要优于单纯基于高精度插值的亚像素方法。
To solve the problem of precise edge localization and measurement on low-resolution images, statistics characteristics of edge gradient magnitude of both high and low resolution images along the gradient direction are extracted and analyzed. The gradient magnitude statistics is described with general Gaussian distribution （GGD）. The relationship between statistics of high and low resolution images is established via GGD analysis on training samples, based on which a high resolution gradient image is re-constructed from a low resolution image. Precise edge location and measurement are then achieved by double threshold edge detection and interpolation. Experiments show that the proposed method has better performance on precise measurement on two dimensional work-pieces than sub-pixel method which only based on high precision interpolation.
出处
《传感器与微系统》
CSCD
北大核心
2010年第8期126-128,共3页
Transducer and Microsystem Technologies
基金
中国博士后科学基金资助项目(20080430161)
江苏省博士后科学基金资助项目(0801008B)
关键词
二维测量
高分辨率重建
梯度图
广义高斯分布
2D measurement
high resolution reconstruction
gradient images, general Gaussian distribution （GGD）
