Object recognize apparatus
First Claim
1. An object recognition apparatus comprising:
- image input means for imaging an object an arbitrary position so as to input an image;
means for specifying a recognition object as a set including a plurality of lower-level recognition objects;
means for setting, for each of said lower-level recognition objects, at least a preprocessing operation of said each lower-level recognition object, features and contour shape of said each lower-level recognition object as attribute data corresponding to a judgment operation of said each lower-level recognition object and orientation base, position base, measurement items, collision check and coordinate conversion parameters as optional data of said each lower-level recognition object;
means for performing a processing for said each lower-level recognition object according to said preprocessing operation, said judgment operation and said measurement items of said each lower-level recognition object;
means for obtaining geometric features from said inputted image by performing a preprocessing according to said preprocessing operation of said each lower-level recognition object;
means for effecting a judgment and detection of said lower-level recognition objects by comparing said geometric features obtained from said inputted image to features and contour shape of said each lower-level recognition object corresponding to said judgment operation; and
means for detecting a recognition object including said lower-level recognition objects on the basis of results of said detection effected on said each lower-level recognition level object.
1 Assignment
0 Petitions
Accused Products
Abstract
An object recognize apparatus suitable for recognition of a complex object constituted with a plurality of elements. When specifying a recognition object, a plurality of elements constituting the finally required recognition object are respectively designated as recognition objects, and when specifying an upper-level recognition object, lower-level recognition objects thereof are designated. Furthermore, for each lower-level recognition object, geometric features necessary for the recognition are specified. In an analysis of image data, the lower-level recognition objects are first detected by use of the geometric features so as to next attain the upper-level recognition object based on results of the detection. As a result, a complex object existing at an arbitrary position can be judged and the position thereof is obtained.
-
Citations
4 Claims
-
1. An object recognition apparatus comprising:
-
image input means for imaging an object an arbitrary position so as to input an image; means for specifying a recognition object as a set including a plurality of lower-level recognition objects; means for setting, for each of said lower-level recognition objects, at least a preprocessing operation of said each lower-level recognition object, features and contour shape of said each lower-level recognition object as attribute data corresponding to a judgment operation of said each lower-level recognition object and orientation base, position base, measurement items, collision check and coordinate conversion parameters as optional data of said each lower-level recognition object; means for performing a processing for said each lower-level recognition object according to said preprocessing operation, said judgment operation and said measurement items of said each lower-level recognition object; means for obtaining geometric features from said inputted image by performing a preprocessing according to said preprocessing operation of said each lower-level recognition object; means for effecting a judgment and detection of said lower-level recognition objects by comparing said geometric features obtained from said inputted image to features and contour shape of said each lower-level recognition object corresponding to said judgment operation; and means for detecting a recognition object including said lower-level recognition objects on the basis of results of said detection effected on said each lower-level recognition level object. - View Dependent Claims (2, 3, 4)
-
Specification