 Method and apparatus to detect capillary indentations |
| OF THE INVENTION In FIG. 1, a system incorporating the present invention is shown. The system ... |
|
| Vision coprocessing |
| We claim: 1. A digital image processing system including A. bus means for carrying control, data ... |
|
| Digital image capture control |
| It is therefore an object of the invention to provide an intuitive, object-oriented user interface ... |
|
| Continuous diffuse illumination method and apparatus |
| The practice of the concepts of the invention are primarily utilized in machine vision applications ... |
|
| Inspecting apparatus of mounted component |
| The object of the present invention is therefore to provide an inspecting apparatus which can ... |
|
| Method and apparatus for high speed identification of objects having an identifying feature |
| The invention is directed to a method and apparatus for identifying an object having an identifying ... |
|
| Image rotating method for locating bond pads in an image |
| The foregoing objects are attained by the invention which provides a method for operating a digital ... |
|
| Method and apparatus for inspection of the appearance of bumps |
| The object of the present invention is therefore to provide a method and apparatus for inspecting ... |
|
| Vision coprocessing |
| We claim: 1. In a rank value filter apparatus of the type having input means for inputting a ... |
|
|
Point pattern matching method and system as well as picture recognizing method and system using the same
| Details |
Inventors: Sakou, Hiroshi; Uecker, Darrin R.;
Assignee: Hatachi, Ltd. (Tokyo, JP)
Primary Examiner: Razavi; Michael T.
Assistant Examiner: Klocinski; Steven P.
Attorney, Agent or Firm: Fay, Sharpe, Beall, Fagan, Minnich & McKee
A point pattern matching method and system for use in an object recognizing system for deciding pair combinations between a first group of n points x.sub.j (n: integer of 2 or more) (j: integer between 1 and n) in a K-dimensional space (K: integer of 2 or more) and a second group of n second points x.sub.i (i: integer between 1 and n) in the same space as the K-dimensional space. A total of n.sup.2 of neurons are provided one for each one of point pair combinations between the first group of points and the second group of points, and, when an output of each of the neurons has a value of substantially "1", it is determined that the point pair combination associated with the neuron is matched, whereas, when the output of the neuron has a value of substantially "0", it is determined that the point pair combination associated with the neuron is not matched. |
|
DETAILED DESCRIPTION When it is desired to obtain optimum one of all combinations regardless of the magnitude of matching errors, such a prior art method as mentioned above cannot cope with it.
This is because, even when a certain allowable matching error is set, there is a possibility that the optimum matching error itself exceeds the allowable matching error, depending on the shape of an input object to be recognized.
In addition, there sometimes occurs such a situation that it is impossible to estimate the allowable matching error.
It is an object of the present invention to provide a point pattern matching method and system for enabling acquisition of the optimum matching combination while eliminating the need for computing n! of all matching errors, and also to provide a picture recognition method and system using the former method and system.
Another object of the present invention is to provide a point pattern matching method and system for enabling matching between a group of characteristic points obtained from a picture and a group of predetermined model characteristic points for automatic recognition of an object, and also to provide a picture recognition method and system using the former method and system.
In accordance with the present invention, in order to attain these objects, there are provided a point pattern matching method and system for deciding pair combinations between a first group of n points x.
sub.
j (n: integer of 2 or more) (j: integer between 1 and n) in a K-dimensional space (K: integer of 2 or more) and a second group of n second points x.
sub.
i (i: integer between 1 and n) in the same space as the K-dimensional space.
A neural network having a total of n.
sup.
2 of neurons is provided one for each one of point pair combinations between the first group of points and the second group of points to determine, on the basis of an output of each of the neurons, the point pair combination associated with the neuron.
That is, a first threshold value substantially close to 1 and a second threshold value substantially close to 0 are prepared
|
|
Image Analysis 
