Rapid low-illumination image enhancing method based on improved dark channel prior
A dark channel prior and dark channel image technology, applied in the field of fast low-light image enhancement, can solve the problems of poor processing effect, poor real-time performance, and inapplicability of light-colored areas, so as to enhance brightness and contrast, and improve image and video quality Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0030] Specific implementation manner 1: The fast low-illumination image enhancement method with improved dark channel prior of this embodiment includes the following steps:
[0031] Step 1: Input image I(i,j), get the size of image I(i,j) as w*h, and the RGB three-channel image IR(i,j), IG(i) of image I(i,j) ,j), IB(i,j), where w is the width of the image, h is the height of the image, IR(i,j), IG(i,j), IB(i,j) are the red and green of the image respectively Blue three-channel image;
[0032] Step 2: For each pixel of the image I(i,j), find the minimum value of the grayscale of the RGB three-channel image IR(i,j), IG(i,j), IB(i,j), Recorded as Imin (i, j), the calculation formula is as follows:
[0033] I min ( i , j ) = min c A { R , G , B , } ( I c ( x , y ) )
[0034] For each pixel in the image Imin(i,j), the minimum filtering process is performed, and the calculation formula of D(i,j) is obtained as foll...
Example Embodiment
[0089] Specific implementation manner 2: This implementation manner is different from the specific implementation manner in that the method for judging light-colored areas in an image in step four is:
[0090] A. The absolute value of the difference between the gray levels of the RGB three channels is less than 5;
[0091] B. The dark channel gray value corresponding to the pixel is greater than the mean dark channel gray value meangray;
[0092] C. The gray value of the dark channel corresponding to the pixel is less than half maxgray / 2 of the maximum dark channel gray value. Other steps and parameters are the same as in the first embodiment.
Example Embodiment
[0093] Specific embodiment three: This embodiment is different from specific embodiment one or two in that the steps of performing linear smoothing on the modified dark channel image in step five are:
[0094] a. Determine the size of the window used to smooth the dark channel image according to the size of the image I(i, j);
[0095] b. Calculate linear approximation parameters for each window a k And b k ;
[0096] c. Approximate parameters a for all windows containing each pixel k And b k Perform averaging to obtain approximate parameters after averaging;
[0097] d. Linearly approximate the image with the averaged approximate parameters;
[0098] Among them, the linear smoothing formula for the modified dark channel image is: for the window W centered at point k and the size is M*M k All pixels in x: E x =a k D x +b k , M=N-2, N is the size of the window used when obtaining the dark channel image, where D x Is the modified dark channel image, E x Is the smoothed result, a k And b k ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap