Method and apparatus for image registration

• US 6,690,841 B2
• Filed: 02/27/2002
• Issued: 02/10/2004
• Est. Priority Date: 07/07/1997
• Status: Expired due to Term

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Nguyen, Van-Duc, Nzomigni, Victor, Stewart, Charles Vernon
• Primary Examiner(s): Mehta, Bhavesh M.
• Assistant Examiner(s): DESIRE, GREGORY M
• Application Number:
  US10/085,159
• Publication Number:
  US 20020118893A1
• Time in Patent Office: 713 Days
• Field of Search: 382/100, 382/103, 382/106, 382/141, 382/145, 382/149-150, 382/154, 382/209, 382/218, 382/224, 382/270, 382/282, 382/284, 382/291, 382/294, 382/296, 382/203, 348/36, 348/87, 348/590, 348/42, 348/169, 356/237, 356/239, 356/371, 356/394, 356/239.8, 356/390, 356/611, 356/613, 345/418-419, 345/425-427, 345/216, 345/218, 345/214, 345/953
• US Class Current: 382/294
• CPC Class Codes: G01N 2021/8887 based on image processing techniques
• CPC Class Codes: G01N 21/9515 Objects of complex shape, e.g. examined with use of a surface follower device measuring contours and curvatures G01B11/24
• CPC Class Codes: G06T 3/073 Transforming surfaces of revolution to planar images, e.g. cylindrical surfaces to planar images
• CPC Class Codes: G06V 10/7515 Shifting the patterns to accommodate for positional errors
• CPC Class Codes: G06V 20/64 Three-dimensional objects
• CPC Class Codes: Y10S 345/953 Geometric processing

Abstract

A machine vision system includes an apparatus for registering an input image of an object, such as an aircraft engine blade, to a reference image comprising ideal specifications for the object in order to detect flaws in the object. The system includes one or more imaging devices for obtaining the input image representing the object. The system further includes a processor for registering the input image to the reference image. The processor includes a patch determining device for identifying low curvature portions of the reference image off-line. A transformation estimator matches the low curvature portions of the reference image to corresponding low curvature portions of the object, and provides a transformation matrix which maps points on the reference image 11 to corresponding points on the input image for precise and fast registration.

Claims

1. A method of registering surface measurements taken from an object to reference data representing specifications for said object, the method implemented on a programmable computer, the method comprising the steps of:

measuring said surface of said object to obtain a plurality of surface data points q_i;

analyzing said reference data to determine a plurality of

patches P_i each comprising one or more sections having curvature corresponding to local minima;

determining a surface normal vector n_i, and center location p_i for each of said patches P_i;

projecting a line from p_i, along n_i to intersect a surface data point q_i; and

calculating a sum of distances d(P,P′

) between points p_i and q_i for a plurality i of said low curvature surface patches to a obtain pose error.

2. The method of claim 1 further including the step of correcting said pose error.

3. The method of claim 2 wherein the step of correcting said pose error is accomplished by the steps of:

minimizing said pose error for variables W, t″

, said pose error being described by the relationship;

$\mathrm{pose}<br><br>\text{\hspace{1em}<br><br>}<br><br>\mathrm{error}=W,t^{\mathrm{″<br><br>}}<br><br>\underset{i}{\sum <br><br>}<br><br>{\left[{\left(\left(I-W/2\right)<br><br>q_i-\left(I+W/2\right)<br><br>p_i-t^{\mathrm{″<br><br>}}\right)}^T<br><br>n_i\right]}^2$$\mathrm{where}<br><br>\text{\hspace{1em}<br><br>}<br><br>I<br><br>\text{\hspace{1em}<br><br>}<br><br>\mathrm{is}<br><br>\text{\hspace{1em}<br><br>}<br><br>\mathrm{an}<br><br>\text{\hspace{1em}<br><br>}<br><br>N\times <br><br>N<br><br>\text{\hspace{1em}<br><br>}<br><br>\mathrm{identity}<br><br>\text{\hspace{1em}<br><br>}<br><br>\mathrm{matrix};<br><br>$$\mathrm{and}<br><br>\text{\hspace{1em}<br><br>}<br><br>W=\left[\begin{array}{ccc}1& -{\mathrm{\omega <br><br>}}_z& {\mathrm{\omega <br><br>}}_y\\ {\mathrm{\omega <br><br>}}_z& 1& -{\mathrm{\omega <br><br>}}_x\\ -{\mathrm{\omega <br><br>}}_y& {\mathrm{\omega <br><br>}}_x& 1\end{array}\right]<br><br>\text{\hspace{1em}<br><br>}<br><br>\mathrm{for}<br><br>\text{\hspace{1em}<br><br>}<br><br>a<br><br>\text{\hspace{1em}<br><br>}<br><br>3<br><br>D<br><br>\text{\hspace{1em}<br><br>}<br><br>\mathrm{space};<br><br>$

b) converting W to a rotation R and translation t, said rotation R and translation t representing pose error, by means of the following equation;

4. The method of claim 1 further comprising the step of utilizing said pose error to detect irregularities between said computer model and said surface of said object.

5. The method of claim 1 further comprising the step of displaying an indication of said irregularities to an operator.