Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Color image enhancement method at night based on purposeful optimization and histogram equalization

A histogram equalization, color image technology, applied in the field of image processing, to achieve fast contrast, enhance contrast, restore image details

Active Publication Date: 2017-02-22
南京多目智能科技有限公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In view of the "halo artifact" phenomenon in the center surround method, Michael Elad et al. proposed a Retinex algorithm based on bilateral filtering, which can effectively eliminate the "halo artifact" phenomenon; Meylan et al. proposed a center / neighborhood-based The adaptive filtering method of the domain Retinex model adaptively adjusts the shape of the filter according to the edge direction of the image to suppress the Halo effect at the edge of the image, but it still inevitably produces over-enhancement at the edge of the image

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
  • Color image enhancement method at night based on purposeful optimization and histogram equalization
  • Color image enhancement method at night based on purposeful optimization and histogram equalization
  • Color image enhancement method at night based on purposeful optimization and histogram equalization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0077] Such as figure 1 Shown, method of the present invention mainly comprises the following steps:

[0078] parameter settings:

[0079] Example (1) β=2000, γ=0.1, δ=0.7, α=1 / 2550, η=1 / 255, θ=0.1

[0080] Example (2) β=1, γ=0.99, δ=0.99, α=1 / 2550, η=1 / 255, θ=0.02

[0081] Example (3) β=4, γ=0.5, δ=0.45, α=1 / 2550, η=1 / 255, θ=0.1

[0082] Example (4) β=18, γ=0.5, δ=0.7, α=1 / 2550, η=1 / 255, θ=0.9

[0083] Parameter setting rules:

[0084] β indicates the degree of fidelity between the result image and the original image, and the value is [1,2000]. The smaller the value, the better the fidelity.

[0085] γ is the degree of image contrast enhancement, the value is [0.1, 0.99], the smaller the value, the greater the degree of enhancement,

[0086] δ is the degree of image brightness enhancement, the value is [0.45, 0.99], the smaller the value, the greater the degree of enhancement,

[0087] α, η, are the control parameters of pixel classification, selected according to the di...

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 nighttime color image enhancement method based on purpose optimization and histogram equalization, and belongs to the technical field of image processing. The nighttime color image enhancement method based on purpose optimization and histogram equalization is characterized by comprising the steps that optimum control is carried out on the quadratic sum of the differences of pixel values of points of an image to be processed, gradient components, in the x direction and y direction, of the points of the image to be processed, the quadratic sum of the differences of pixel values of points of a result image, and gradient components, in the x direction and y direction, of the points of the result image, so that image contrast is improved, wherein a parameter theta which controls the gradient components is used for controlling the gradient components, in the x direction and the y direction, of the result image, when the absolute value of the gradient component, in the x direction, of each pixel point of the image to be processed and the absolute value of the gradient component, in the y direction, of the pixel point of the image to be processed are smaller than the theta, the values of the gradient components, in the x direction and the y direction, of the corresponding point of the result image are kept unchanged, and when the absolute value of the gradient component, in the x direction, of each pixel point of the image to be processed and the absolute value of the gradient component, in the y direction, of the pixel point of the image to be processed are larger than or equal to the theta, the values of the gradient components, in the x direction and the y direction, of the corresponding point of the result image are enhanced through a Gamma correction function; improved histogram equalization processing is carried out, and therefore a result which is better than an existing algorithm provided by Michael Elad and an MSRCR algorithm is obtained.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a nighttime color image processing method and system. Background technique [0002] Nighttime image enhancement technology has great application significance in the fields of computational photography and computer vision, mainly in that nighttime image enhancement technology can effectively enhance photography; For night images, night image enhancement technology can increase the adaptability of such algorithms; some advanced tasks (such as: video surveillance) will also benefit from night image enhancement technology. [0003] At present, the technologies for image quality enhancement at night mainly include image fusion and image enhancement. Image fusion technology includes fusion of nighttime images and visible light images, and fusion of nighttime images and infrared images. These methods all need to collect multiple images with different spectrums in the same scene, and the...

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): G06T5/40
Inventor 赵华夏赵宏宇段娟肖创柏
Owner 南京多目智能科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products