IMAGE RECTIFICATION METHOD

• US 20120163728A1
• Filed: 12/22/2010
• Published: 06/28/2012
• Est. Priority Date: 12/22/2010
• Status: Active Grant

• Current Assignee: Arcsoft Corporation Limited
• Original Assignee: ArcSoft, Inc.
• Inventors: Wang, Jin, Sun, Wei-Ning
• Granted Patent: US 8,503,813 B2
• Time in Patent Office: Days
• US Class Current: 382/260
• CPC Class Codes: G06T 2207/20061 Hough transform
• CPC Class Codes: G06T 5/80 Geometric correction
• CPC Class Codes: G06T 5/92 based on global image properties
• CPC Class Codes: G06V 10/24 Aligning, centring, orientation detection or correction of the image

Abstract

An image rectification method includes the steps of: detecting edges in an image by using a Canny filter; performing Hough transform on the edges to detect lines in the image; selecting a candidate quadrangle from quadrangles formed by the detected lines; obtaining a transform matrix for transforming the candidate quadrangle to a rectangle by homographic transform; rectifying the image by using the transform matrix; and enhancing the rectified image

Claims

1. An image rectification method comprising:

detecting edges in an image by using a Canny filter;

performing Hough transform on the edges to detect lines in the image;

selecting a candidate quadrangle from quadrangles formed by the detected lines;

obtaining a transform matrix for transforming the candidate quadrangle to a rectangle by homographic transform;

rectifying the image by using the transform matrix; and

enhancing the rectified image.

2. The image rectification method according to claim 1, wherein the step of obtaining the transform matrix comprises:

setting vertex positions of the rectangle; and

obtaining the transform matrix by homographic transform according to the vertex positions of the candidate quadrangle and the vertex positions of the rectangle.

3. The image rectification method according to claim 2, wherein the transform matrix is obtained by the formula:

λ

=(A^TA)<sup>−

1</sup>A^TB, wherein λ

is a transform matrix,

A is

4. The image rectification method according to claim 1, further comprising a step of:

performing bilinear interpolation to obtain extra pixels in the rectified image.

5. The image rectification method according to claim 1, wherein the step of enhancing the rectified image comprises:

building a luminance histogram of the image, wherein the luminance histogram has a low region, a middle region, and a high region; and

extending the range of the middle region, wherein the percentage of the low region in the image and the percentage of the high region in the image are larger than a threshold value.

6. The image rectification method according to claim 5, wherein the threshold value is 10%.

7. The image rectification method according to claim 5, wherein the step of enhancing the rectified image further comprises:

performing gamma transform on the rectified image.

8. The image rectification method according to claim 1, wherein the step of selecting the candidate quadrangle comprises:

forming all possible quadrangles based on the detected lines;

counting the pixel quantity of each of the formed quadrangles;

filtering the formed quadrangles according to the pixel quantity; and

selecting one of the filtered quadrangles containing the most corners as the candidate quadrangle.