Unlock instant, AI-driven research and patent intelligence for your innovation.

Fast Adaptive Optimizing Method of Digital Image under Low Illumination

A digital image and optimization technology, applied in the field of image processing, can solve problems such as time-consuming, unfavorable real-time processing of color images, and inability to use video fields

Inactive Publication Date: 2016-05-11
CHONGQING MEDICAL UNIVERSITY
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method needs to be realized by changing the value of the transformation parameter Delta of the Zadeh-X transformation one by one, which takes a long time, is not conducive to the real-time processing of color images, and cannot be used in the video field.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Fast Adaptive Optimizing Method of Digital Image under Low Illumination
  • Fast Adaptive Optimizing Method of Digital Image under Low Illumination
  • Fast Adaptive Optimizing Method of Digital Image under Low Illumination

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] like figure 1 The flow shown: a fast adaptive optimization method for digital images under low illumination, including the following steps:

[0043] Step 1: Select a digital image acquired in low light figure 2 (a) is the source image S, obtain the chrominance values ​​R(x, y), G(x, y), and B(x, y) of the red, green and blue components of each pixel of the source image S, According to the method in the Chinese patent "High-resolution detection method for image grayscale / chromaticity information for underlying image mining" (patent number: 200610054324.9), the chromaticity spectrum of the three components of red, green and blue is made, and each The luminance value L(x, y) of pixel points obtains the average luminance AL=6.7573 of the source image S;

[0044] Step 2: Generate a standardized image B of the source image S, and the standardized image B is obtained by the following methods:

[0045] (1) Search for the left boundary values ​​Leftr, Leftg, Leftb and right ...

Embodiment 2

[0064] This embodiment is substantially the same as Embodiment 1, and the difference lies in that the source image S of this embodiment is as follows: image 3 As shown in (a), the calculated average brightness is 47.2394; the final optimized image is as follows image 3 As shown in (b), the average brightness is 106.4164. Compared with the source image, the average brightness of the optimized image has been improved, and from the perspective of human visual effects, the quality is also better.

Embodiment 3

[0066] The source image S used in this embodiment is as follows Figure 4 As shown in (a), it is a grayscale image, and the process of fast adaptive optimization is as follows figure 1 shown, including the following steps:

[0067] Step 1: Select a digital image acquired in low light Figure 4 (a) is the source image S, because the chromaticity values ​​R(x, y), G(x, y), and B(x, y) of the red, green, and blue components of the grayscale image are the same, according to The method in the Chinese patent "High-resolution detection method of image grayscale / chromaticity information for underlying image mining" (patent number: 200610054324.9), the grayscale spectrum of the image is obtained, and the brightness value L of each pixel point is calculated. (x, y), the average brightness AL=8.8283 of the source image S is obtained;

[0068] Step 2: Generate a normalized image B of the source image S, and the normalized image B is obtained by the following methods:

[0069] (1) sear...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a quick self-adaption optimizing method for a digital image at a low illumination level. The method comprises the following steps of: selecting the digital image acquired at the low illumination level as a source image, acquiring chromatic values of red, green and blue components of each pixel point of the source image to make chroma spectrum of the red, green and blue components, and calculating the mean brightness of the source image; generating a standard image of the source image; and quickly optimizing the standard image to acquire an optimal image. The quick self-adaption optimizing method has the beneficial effects that the optimization of the digital image at the low illumination level can be realized in a self-adaption mode according to the mean brightness of the original image without multiple times of scanning, so that the processing time is greatly saved, and the real-time processing on quality optimization of the digital image is realized; and the method is effectively applied to the field of video processing.

Description

technical field [0001] The invention belongs to the technical field of image processing, and uses a Zadeh-X transformation method to adaptively and quickly obtain digital images with optimized quality. Background technique [0002] When people use photography and camera equipment, they generally hope to get the best quality images. But few methods are concerned with optimizing the quality of color images. The inventor previously proposed a method for obtaining color images with the best quality (patent number: ZL200910190834.2), which can obtain the maximum value of the color image quality evaluation function NCAF by scanning the value of the transformation parameter Delta of the Zadeh-X transformation, to obtain the best quality image corresponding to the original color image. However, this method needs to change the value of the transformation parameter Delta of the Zadeh-X transformation one by one, which takes a long time, is not conducive to the real-time processing o...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T5/00
Inventor 熊兴良王志芳谢正祥
Owner CHONGQING MEDICAL UNIVERSITY