Recognition processing method and image processing device using the same

Abstract

A recognition processing method and an image processing device ends recognition of an object within a predetermined time while maintaining the recognition accuracy. The device extracts combinations of three points defining a triangle whose side length satisfy predetermined reference values from feature points of the model of a recognition object, registers the extracted combinations as model triangles, and similarly extracts combinations of three points defining a triangle whose side lengths satisfy predetermined reference values from feature points of the recognition object. The combinations are used as comparison object triangles and associated with the respective model triangles. The device calculates a transformation parameter representing the correspondence relation between each comparison object triangle and the corresponding model triangle using the coordinates of the corresponding points (A and A', B and B', and C and C'), determines the goodness of fit of the transformation parameters on the relation between the feature points of the model and those of the recognition object.The object is recognized by specifying the transformation parameters representing the correspondence relation between the feature points of the model and those of the recognition object according to the goodness of fit determined for each association.

Description

technical field [0001] The present invention relates to a recognition processing method and an image processing device using the method. In this method, a set of points (hereinafter also referred to as "feature point groups") representing features of a recognition object is compared with a pre-registered recognition target The position and posture of the object to be recognized are recognized by the corresponding relationship of the model feature point group of the object. Background technique [0002] In two-dimensional image processing, as a typical method for recognizing the position and posture of an object to be recognized in an image to be processed, there is a method of obtaining a correlation value between a pre-registered model image and an image to be processed. method (for example, Patent Document 1). In addition, there is a method of obtaining three-dimensional coordinates of feature points of a plurality of recognition objects by performing three-dimensional me...

AI Technical Summary

Problems solved by technology

At this time, there is also the following problem: the more diverse the combination of the position and direction of the model feature point group, the longer the processing time

This type of recognition processing is often performed as pre-processing for measurement and inspection, so it is not desirable to increase the processing time.

Images