A method of image defogging enhancement
An image and grayscale image technology, applied in the field of image defogging enhancement, can solve problems such as color distortion, achieve the effect of eliminating degradation, improving clarity and contrast, and improving display quality
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0037] Embodiment 1: as figure 1 As shown, this embodiment provides a method for image defogging enhancement, which includes the following steps:
[0038] S01: convert the image to be processed into a grayscale image, and count the grayscale histogram and grayscale mean value L of the grayscale image;
[0039] S02: If figure 2 As shown, from the gray histogram along the direction of the gray maximum value to the gray minimum value to find the valley point of the histogram value change ( figure 2 The position in the middle circle drawing), each valley point is compared with the gray level mean value L, and the first valley point found greater than the gray level mean value L is set as the threshold point A of the gray level histogram ;
[0040] S03: Determine and identify the white bright area of the image to be processed;
[0041] S04: Calculate the pixel number S1 of the identified region of the image to be processed and the pixel number S of the entire image, and cal...
example 1
[0051] Example 1: The original pending image is image 3 ( image 3 It can be a color picture), which is converted into a grayscale image through the method S01 of the present invention, and the grayscale histogram and grayscale mean value L of the grayscale image are calculated; and continue to obtain the grayscale threshold point A of this figure through S02 =173, figure 2 Be the grayscale histogram of example 1; After step S03 we get Figure 5 , Figure 5 The white bright area (sky part) in the middle of the trees on both sides of the image is accurately identified. According to the identification results, and through S04, the ratio of the pixels on the right side to the total pixels is 19.67%, and the ratio of the pixels identified as the white highlighted area to the total pixels is 23.38%. On this basis, the figure is calculated The correction factor β value is 4.28.
[0052] Introduce the correction coefficient β into the formula J=J′×(1-β)+I×β to correct the imag...
example 2
[0053] Example 2: If Figure 7 to Figure 10 as shown, Figure 7 is another image to be processed, Figure 8 is the image processed by the existing technology (dark channel prior algorithm), Figure 9 It is an image post-processed by the method S03 of the present invention; Figure 10 It is the image processed through the method of the present invention; through the information entropy, PSNR and MSE calculation results (as shown in table 1) of two images in example 1 and example 2 respectively, it is shown that, objectively, the image processing provided by the method of the present invention This method can significantly improve the image quality.
[0054] Table 1
[0055]
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More