Underwater image enhancement method based on multi-interval sub-histogram equalization

A histogram equalization and underwater image technology, applied in the field of image processing, can solve problems such as unbalanced lighting and difficulty in recovering underwater image information, and achieve improved details in dark places, good color correction effects, and uniform distribution of histograms Effect

Pending Publication Date: 2022-03-25
DALIAN MARITIME UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These factors lead to unbalanced lighting
Therefore, severe deterioration makes underwater image information difficult to recover

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
  • Underwater image enhancement method based on multi-interval sub-histogram equalization
  • Underwater image enhancement method based on multi-interval sub-histogram equalization
  • Underwater image enhancement method based on multi-interval sub-histogram equalization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0159] Such as figure 2 As shown, firstly, the first foggy image is processed by various algorithms; diagram 2-1 -1 is the result image processed by the IBLA algorithm. It can be seen that the result image is still foggy, and the details are slightly blurred, which did not achieve the expected effect. diagram 2-1 -2 is the result map processed by the ICM algorithm. It can be seen that the contrast of the result map has been improved, but the details are not clear, and the effect needs to be improved. diagram 2-1 -3 is the result image processed by the RGHS algorithm. It can be seen that the result image has a better dehazing effect and some details have been improved, but the image still has the problem of color cast, which has not achieved the expected effect. diagram 2-1 -4 is the result map processed by the UWCNN algorithm. It can be seen that the result map has serious color cast problems, detailed information cannot be obtained, and the processing result is very poo...

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 provides an underwater image enhancement method based on multi-interval sub-histogram equalization. The method comprises the following steps: performing color correction processing on a source image; the method comprises the following steps: performing contrast enhancement processing on an image, processing a source image histogram on R, G and B channels by adopting a multi-interval sub-histogram equalization method, performing threshold selection and separating a plurality of sub-intervals, thereby obtaining a plurality of sub-histograms and completing multi-interval sub-histogram equalization operation; and performing multi-scale fusion on the image after color correction and the image after contrast enhancement, and reconstructing a final defogged image. According to the method, the single-channel histogram of the source image is more accurately divided based on the multi-interval sub-histogram equalization method, and meanwhile, multi-scale fusion is performed on the single-channel histogram and the image subjected to color correction processing, so that the dark details of the source image are better displayed, the contrast ratio and the color are effectively improved, the noise is reduced, and image defogging is realized.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an underwater image enhancement method based on multi-interval sub-histogram equalization. Background technique [0002] The physical properties of the underwater medium prevent degradation of normal images taken in the air. As light travels through water, the intensity of the light decays exponentially according to the wavelengths of the color spectrum. Light attenuation makes underwater objects less visible. Furthermore, light decays exponentially with distance and depth, mainly due to absorption and scattering effects. In summary, the low quality of underwater images is mainly caused by the following factors: low contrast, blur, reduced true color of objects, bright artifacts, floating particles, and non-uniform illumination. These factors lead to unbalanced lighting. Therefore, severe deterioration makes underwater image information difficult to recover. ...

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 Applications(China)
IPC IPC(8): G06T5/00G06T5/40G06T5/50
CPCG06T5/009G06T5/40G06T5/50G06T2207/10024G06T2207/20221
Inventor 张维石庞磊张得欢曹微周景春
Owner DALIAN MARITIME UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products