System and method for finding edge points of an object

• US 8,249,354 B2
• Filed: 09/01/2008
• Issued: 08/21/2012
• Est. Priority Date: 12/27/2007
• Status: Expired due to Fees

• Current Assignee: Hong Fu Jin Precision Industry (Shenzhen) Co., Ltd. (Hon Hai Precision Industry Co., Ltd.), Hon Hai Precision Industry Co., Ltd.
• Original Assignee: Hong Fu Jin Precision Industry (Shenzhen) Co., Ltd. (Hon Hai Precision Industry Co., Ltd.), Hon Hai Precision Industry Co., Ltd.
• Inventors: Chang, Chih-Kuang, Chen, Xian-Yi, Li, Dong-Hai, Yuan, Zhong-Kui
• Primary Examiner(s): Newman, Michael A
• Application Number:
  US12/202,390
• Publication Number:
  US 20090169111A1
• Time in Patent Office: 1,450 Days
• Field of Search: 382/199, 382/141, 382/144, 382/145, 382/152, 382/181, 382/209, 382/214, 382/217, 382/266, 382/305
• US Class Current: 382/199
• CPC Class Codes: G06T 2207/30176 Document
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06V 10/443 by matching or filtering

Abstract

A method for finding edge points of an object is disclosed. The method includes receiving an electronic image of an object, selecting one or more edge points in the image of the object, creating an image template for each edge point in the object image. The method further includes receiving a command to measure a second object of the same kind as the object and obtaining a measured object image, reading the image templates for the same kind of object from the storage device, and finding a matched sub-image to each image template from the measured object image according to an image matching algorithm, obtaining a central point of each matched sub-image and displaying coordinates of the central point of the matched sub-image.

Claims

1. A computer-implemented method for finding edge points of an object, the method comprising:

receiving an electronic image of the object;

selecting one or more edge points of the object in the image of the object;

creating an image template for each edge point in the image of the object and storing the image template into a storage device, the image template comprising the edge point and points around the edge point, wherein the points around the edge point comprise pixel points in a rectangle having a specified height value and width value, and a central point of the rectangle that is regarded as the edge point;

receiving a command to measure a second object of the same kind as the object and obtaining a measured object image;

reading the image templates of the object from the storage device, and finding a matched sub-image in the measured object image for each image template according to an image matching algorithm, comprising;

putting the image template on the measured object image;

determining a similarity value between the image template and a sub-image of the measured object image under the image template using a preset formula, the preset formula comprising;

a first formula of

2. The method according to claim 1, further comprising:

filtering noises in each image template according to an image filtering algorithm after the image template is created; and

filtering noises in the measured object image according to the image filtering algorithm before the finding a matched sub-image in the measured object image for each image template step.

3. The method according to claim 2, wherein the image filtering algorithm comprises a Median Filtering Algorithm.

4. A non-transitory computer-readable medium having stored thereon instructions that, when executed by a computer, causing the computer to:

receive an electronic image of an object;

select one or more edge points of the object in the image of the object;

create an image template for each edge point in the image of the object and storing the image template into a storage device, the image template comprising the edge point and points around the edge point, wherein the points around the edge point comprise pixel points in a rectangle having a specified height value and width value, and a central point of the rectangle that is regarded as the edge point;

receive a command to measure a second object of the same kind as the object and obtaining a measured object image;

read the image templates of the object from the storage device, and finding a matched sub-image in the measured object image for each image template according to an image matching algorithm, comprising;

putting the image template on the measured object image;

determining a similarity value between the image template and a sub-image of the measured object image under the image template using a preset formula, the preset formula comprising;

a first formula of

5. The non-transitory computer-readable medium according to claim 4, wherein the medium is selected from the group consisting of a hard disk drive, a compact disc, a digital video disc, and a tape drive.

6. A computing system for finding edge points of an object, comprising:

a template creating module configured for receiving an electronic image of an object and one or more edge points of the object in the image of the object, creating an image template for each edge point in the object image, and storing the image template into a storage device, the image template comprising the edge point and points around the edge point, wherein the points around the edge point comprise pixel points in a rectangle having a specified height value and width value, and a central point of the rectangle that is regarded as the edge point;

a command receiving module configured for receiving a command to measure a second object of the same kind as the object and obtaining a measured object image;

an image matching module configured for reading the image templates of the object from the storage device, finding a matched sub-image in the measured object image for each image template according to an image matching algorithm, comprising;

putting the image template on the measured object image;

determining a similarity value between the image template and a sub-image of the measured object image under the image template using a preset formula, the preset formula comprising;

a first formula of

7. The system according to claim 6, wherein the computer further comprises an image filtering module, wherein:

the image filtering module is configured for filtering noises in each image template according to an image filtering algorithm after the image template is created; and

the image filtering module is further configured for filtering noises in the measured object image according to the image filtering algorithm before the finding a matched sub-image in the measured object image for each image template step.

8. The system according to claim 7, wherein the image filtering algorithm comprises a Median Filtering Algorithm.