CVB ShapeFinder - Object recognition using geometric information
Using CVB ShapeFinder patterns are recognised based on geometric information. CVB ShapeFinder works by matching the inner and outer edge contours of an object with an edge model and provides the position, scale and rotation of the object by matching these contour points. One of the software's most remarkable characteristics is its resistance to interference when recognising partially overlaid, noisy or reflection inducing objects and materials.
By changing a number of parameters, users can choose an optimum path between very fast but less accurate settings and slightly slower, but more accurate ones. Optionally, CVB ShapeFinder is also able to recognise and report rotated or scaled objects within a range of user defined parameters.
CVB ShapeFinder uses a generalised form of the Hough transformation where patterns are located solely on the basis of localised contrast in the greyscales of an image. These contrasts correspond to pixels around which the greyscale values change significantly. In contrast the algorithm ignores image areas with only a low level of greyscale variation.
Users can define an appropriate contrast threshold and thus control the computational demands and the quality of the results. Another interesting characteristic is its ability to search for more than one pattern type at the same time, with minimum increase in search time as the search window only needs to be scanned once when searching for multiple models.
This video shows in an easy to follow step by step explanation how to acquire
and display an image with the STEMMER IMAGING machine vision software Common
Vision Blox (CVB). This tutorial is mainly intended for beginners in CVB