Image processing method and non-transitory computer-readable storage medium

• US 10,198,652 B2
• Filed: 07/19/2017
• Issued: 02/05/2019
• Est. Priority Date: 05/17/2017
• Status: Active Grant

• Current Assignee: National Chung Cheng University
• Original Assignee: National Chung Cheng University
• Inventors: Hsu, Wei-Yen, Chang, Nai-En
• Primary Examiner(s): Bekele, Mekonen
• Application Number:
  US15/654,684
• Publication Number:
  US 20180336429A1
• Time in Patent Office: 566 Days
• CPC Class Codes: G02B 5/0257 creating an anisotropic diffusion characteristic, i.e. distributing output differently in two perpendicular axes
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/20012 Locally adaptive
• CPC Class Codes: G06T 2207/20192 Edge enhancement; Edge preservation
• CPC Class Codes: G06T 5/20 using local operators
• CPC Class Codes: G06T 5/70 Denoising; Smoothing
• CPC Class Codes: G06T 5/73 Deblurring; Sharpening
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/269 using gradient-based methods
• CPC Class Codes: G06V 10/30 Noise filtering
• CPC Class Codes: G06V 10/451 with interaction between the filter responses, e.g. cortical complex cells

Abstract

An image processing method includes the following steps. An original image is read, and the original image includes a red channel layer, a green channel layer and a blue channel layer. A processing is performed on the red channel layer, the green channel layer and the blue channel layer, respectively, to get a derived red channel layer, a derived green channel layer and a derived blue channel layer. And the derived red channel layer, the derived green channel layer and the derived blue channel layer are combined to form a new image. The processing includes the following steps. Gradient-variations of a plurality of directions of a region are calculated. An average of the gradient-variations is calculated. A calculating procedure is provided to decide diffusion-coefficient equations of the directions, and each of the diffusion-coefficient equations is substituted into an anisotropic diffusion equation.

Claims

1. An image processing method, comprising:

reading an original image which comprises a red channel layer, a green channel layer and a blue channel layer;

performing a processing on the red channel layer, the green channel layer and the blue channel layer, respectively, to get a derived red channel layer, a derived green channel layer and a derived blue channel layer, the processing comprising;

calculating gradient-variations of a plurality of directions of a region;

calculating an average of the gradient-variations;

providing a calculating procedure to decide diffusion-coefficient equations of the directions, each of the diffusion-coefficient equations being substituted into an anisotropic diffusion equation, wherein the anisotropic diffusion equation is expressed as shown below;

I=I₀+λ

×

Σ

_i=1ⁿ[c(|∇

I_i|)∇

I_i];

if one of the gradient-variations being smaller than or equal to the average, the diffusion-coefficient equation of the corresponding direction being a smoothening equation expressed as shown below;

2. The image processing method of claim 1, wherein a number of the directions is eight, and two horizontal directions, two longitudinal directions and two diagonal directions are included.

3. The image processing method of claim 2, wherein α

of each of the horizontal directions and each of the longitudinal directions is √

2, and α

of each of the diagonal directions is 1.

4. The image processing method of claim 2, wherein β

of each of the horizontal directions and each of the longitudinal directions is 1√

2, and β

of each of the diagonal directions is ½

.

5. The image processing method of claim 1, wherein the process is performed five times.

6. An image processing method, comprising:

reading an original image;

converting the original image to LAB color space to get an L channel layer, an A channel layer and a B channel layer;

performing a processing on the L channel layer to get a derived L channel layer, the processing comprising;

calculating gradient-variations of a plurality of directions of a region;

calculating an average of the gradient-variations;

providing a calculating procedure to decide diffusion-coefficient equations of the directions, each of the diffusion-coefficient equations being substituted into an anisotropic diffusion equation, wherein the anisotropic diffusion equation is expressed as shown below;

I=I₀+λ

×

Σ

_i=1ⁿ[c(|∇

I_i|)∇

I_i];

if one of the gradient-variations being smaller than or equal to the average, the diffusion-coefficient equation of the corresponding direction being a smoothening equation expressed as shown below;

7. The image processing method of claim 6, wherein a number of the directions is eight, and two horizontal directions, two longitudinal directions and two diagonal directions are included.

8. The image processing method of claim 7, wherein α

of each of the horizontal directions and each of the longitudinal directions is √

2, and α

of each of the diagonal directions is 1.

9. The image processing method of claim 7, wherein β

of each of the horizontal directions and each of the longitudinal directions is 1√

2, and β

of each of the diagonal directions is ½

.

10. The image processing method of claim 6, wherein the process is performed five times.

11. A non-transitory computer-readable storage medium, which stores a computer program instruction that performs an image processing method after loading in an electronic device, wherein the image processing method comprises:

reading an original image which comprises a red channel layer, a green channel layer and a blue channel layer;

performing a processing on the red channel layer, the green channel layer and the blue channel layer, respectively, to get a derived red channel layer, a derived green channel layer and a derived blue channel layer, the processing comprising;

calculating gradient-variations of a plurality of directions of a region;

calculating an average of the gradient-variations;

providing a calculating procedure to decide diffusion-coefficient equations of the directions, each of the diffusion-coefficient equations being substituted into an anisotropic diffusion equation, wherein the anisotropic diffusion equation is expressed as shown below;

I=I₀+λ

×

Σ

_i=1ⁿ[c(|∇

I_i|)∇

I_i];

if one of the gradient-variations being smaller than or equal to the average, the diffusion-coefficient equation of the corresponding direction being a smoothening equation expressed as shown below;

12. The non-transitory computer-readable storage medium of claim 11, wherein a number of the directions is eight, and two horizontal directions, two longitudinal directions and two diagonal directions are included.

13. The non-transitory computer-readable storage medium of claim 12, wherein α

of each of the horizontal directions and each of the longitudinal directions is √

2, and α

of each of the diagonal directions is 1.

14. The non-transitory computer-readable storage medium of claim 12, wherein β

of each of the horizontal directions and each of the longitudinal directions is 1/√

2, and β

of each of the diagonal directions is ½

.

15. The non-transitory computer-readable storage medium of claim 11, wherein the process is performed five times.