会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 8. 发明授权
    • Method and apparatus for object recognition
    • 用于对象识别的方法和装置
    • US06424745B1
    • 2002-07-23
    • US09081469
    • 1998-05-19
    • Mark Henry HansenHarald F. HessPartha Pratim MitraGordon Albert Thomas
    • Mark Henry HansenHarald F. HessPartha Pratim MitraGordon Albert Thomas
    • G06K946
    • G06K9/522G06K2209/17
    • A method and system for optically recognizing an object from a reference library of known products based on a spectrum of local radius of curvature of the object. A surface portion of an object is illuminated with a pattern of light that permits the extraction of three dimensional coordinates for a set of points on the surface portion of the object. An image data set of the surface portion of the object is then captured with a capture device that is positioned at an angular offset with respect to a source of the light. That is, the combination of the light pattern and the imaging device together generate a two dimensional captured image, from which it is possible to extract the three dimensional coordinates for the set of points on the surface portion of the object. A set of local radii of curvatures are then determined for selected data points in the image data set. A spectrum representing a distribution of the curvatures is then computed for the set of local radii of curvatures. If the data set is for the generation of a library of spectra, it is processed with a dimension reduction analysis to determine a single set of basis functions representing all of the objects and a corresponding set of basis coefficients for each different type of object. If the data set is for an unknown object, then the dimension reduction analysis and the basis functions are applied to the data set to generate an unidentified set of basis coefficients. This latter set is then statistically compared with the reference library of spectra to identify the product or at least designate the closest known products.
    • 一种用于基于对象的局部曲率半径的光谱从已知产品的参考库光学地识别对象的方法和系统。 物体的表面部分用允许提取物体的表面部分上的一组点的三维坐标的图案来照亮。 然后利用相对于光源以角度偏移定位的捕获装置捕获对象的表面部分的图像数据集。 也就是说,光图案和成像装置的组合一起产生二维拍摄图像,从该图像可以提取对象的表面部分上的该组点的三维坐标。 然后对图像数据集中的选定数据点确定一组局部曲率半径。 然后,对于局部曲率半径的集合计算表示曲率分布的光谱。 如果数据集用于生成光谱库,则通过维数减小分析来处理数据集,以确定表示所有对象的单个基函数集合,以及每个不同类型对象的对应的一组基准系数。 如果数据集用于未知对象,则将维度减小分析和基函数应用于数据集以生成未识别的基系数集合。 然后将后一组与谱的参考文献库进行统计学比较以鉴定产物或至少指定最接近的已知产物。