DIGITAL IMAGE ANALYZING METHOD AND RELATED COMPUTER PROGRAM PRODUCT

• US 20110235917A1
• Filed: 07/21/2010
• Published: 09/29/2011
• Est. Priority Date: 03/29/2010
• Status: Active Grant

• Current Assignee: AnMo Electronics Corporation
• Original Assignee: AnMo Electronics Corporation
• Inventors: WU, Paul Neng-Wei
• Granted Patent: US 8,358,851 B2
• Time in Patent Office: Days
• US Class Current: 382/190
• CPC Class Codes: G06T 2207/30108 Industrial image inspection
• CPC Class Codes: G06T 7/13 Edge detection

Abstract

A computer program product capable of enabling a computer to perform a digital image analyzing operation, wherein the digital image analyzing operation comprises: receiving settings of a plurality of lines corresponding to one or more image edges of a digital image; and identifying a plurality of intersections of the plurality of lines and the one or more image edges of the digital image.

Claims

1. A computer program product capable of enabling a computer to perform a digital image analysis operation, the digital image analysis operation comprising:

receiving settings of a plurality of lines corresponding to one or more image edges of a digital image; and

identifying a plurality of intersections of the plurality of lines and the one or more image edges of the digital image.

2. The computer program product of claim 1, wherein the digital image analysis operation further comprises:

connecting the plurality of intersections to recognize at least one partial edge of the digital image.

3. The computer program product of claim 2, wherein the digital image analysis operation further comprises:

displaying a plurality of recognization pattern options; and

receiving settings of one or more recognization patterns selected by a user.

4. The computer program product of claim 3, wherein the operation of connecting the plurality of intersections comprises:

connecting the plurality of intersections according to the one or more selected recognization patterns.

5. The computer program product of claim 3, wherein the operation of connecting the plurality of intersections comprises:

determining a plurality of edge lines based on the one or more selected recognization patterns and the plurality of intersections; and

determining one or more edge portions or whole boundary of the digital image according to the plurality of edge lines.

6. The computer program product of claim 3, wherein the one or more selected recognization patterns correspond to the shape of the digital image.

7. The computer program product of claim 3, wherein the quantity of the plurality of lines is corresponding to the one or more selected recognization patterns.

8. The computer program product of claim 2, wherein the digital image analysis operation further comprises:

determining a position of a geometrical feature of the digital image according to at least one edge portion of the digital image.

9. The computer program product of claim 2, wherein the digital image analysis operation further comprises:

calculating a geometrical feature value or image feature value of the digital image according to the edge recognization result.

10. The computer program product of claim 1, wherein the digital image analysis operation further comprises:

calculating an interval between the plurality of intersections or a path length of the plurality of intersections according to a zooming scale of the digital image.

11. The computer program product of claim 1, wherein the operation of identifying the plurality of intersections comprises:

analyzing the pixel value of pixels on the path of each line to determine an intersection of the line and the image edge of the digital image.

12. The computer program product of claim 11, wherein the operation of analyzing the pixel value of pixels on the path of each line comprises:

computing pixel value difference between adjacent pixels on the path of each line; and

setting a position with the maximum pixel value difference as an intersection of the line and the image edge of the digital image.

13. The computer program product of claim 11, wherein the operation of analyzing the pixel value of pixels on the path of each line comprises:

computing pixel value difference between adjacent pixels on the path of each line along a predetermined direction; and

setting the first position where the pixel value difference reaches or exceeds a predetermined threshold as an intersection of the line and the image edge of the digital image.

14. The computer program product of claim 11, wherein the operation of analyzing the pixel value of pixels on the path of each line comprises:

comparing the pixel value of pixels on the path of each line with a predetermined threshold along a predetermined direction; and

setting the first position where the pixel value reaches or is across the predetermined threshold as an intersection of the line and the image edge of the digital image.

15. The computer program product of claim 14, wherein the operation of analyzing the pixel value of pixels on the path of each line comprises:

setting the predetermined threshold for each line based on the pixel values on the path of each line.

16. A digital image analyzing method, comprising:

receiving settings of a plurality of lines corresponding to one or more image edges of a digital image; and

identifying a plurality of intersections of the plurality of lines and the one or more image edges of the digital image.

17. The digital image analyzing method of claim 16, further comprising:

displaying a plurality of recognization pattern options; and

receiving settings of one or more recognization patterns selected by a user;

determining a plurality of edge lines based on the one or more selected recognization patterns and the plurality of intersections; and

recognizing one or more edge portions or whole boundary of the digital image according to the plurality of edge lines.

18. The digital image analyzing method of claim 17, wherein the one or more selected recognization patterns correspond to the shape of the digital image, and the quantity of the plurality of lines is corresponding to the one or more selected recognization patterns.

19. The digital image analyzing method of claim 17, further comprising:

calculating a geometrical feature value or image feature value of the digital image according to the edge recognization result.

20. The digital image analyzing method of claim 16, further comprising:

calculating an interval between the plurality of intersections or a path length of the plurality of intersections according to a zooming scale of the digital image.