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

A Multi-Exposure Fusion Image Quality Evaluation Method

A technology that integrates images and quality evaluation, applied in image analysis, image enhancement, image data processing and other directions, can solve the problem that the correlation needs to be improved, and achieve the effect of high consistency and improved correlation.

Active Publication Date: 2022-07-15
NINGBO UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The correlation between the objective evaluation results and subjective perception of the above multi-exposure fusion image quality evaluation methods needs to be improved

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
  • A Multi-Exposure Fusion Image Quality Evaluation Method
  • A Multi-Exposure Fusion Image Quality Evaluation Method
  • A Multi-Exposure Fusion Image Quality Evaluation Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be further described in detail below with reference to the embodiments of the accompanying drawings.

[0041] A multi-exposure fusion image quality evaluation method proposed by the present invention, the overall implementation block diagram is as follows figure 1 shown, it includes the following steps:

[0042] Step 1: Select a multi-exposure fusion image as the multi-exposure fusion image to be evaluated, and denote it as S mefi , while setting S mefi The corresponding three original images with different exposure levels, namely the normal exposure image, the overexposed image and the underexposed image, are correspondingly denoted as S. normal , S over-ex , S under-ex ; where S mefi , S normal , S over-ex , S under-ex has width W and height H.

[0043] Step 2: Calculate S mefi , S normal , S over-ex , S under-ex The respective gradient map, corresponding to G mefi , G normal , G over-ex , G under-ex ; where G mefi , G nor...

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 multi-exposure fusion image quality evaluation method, which extracts the maximum gradient map from the gradient maps of three original images, and then obtains gradient features; and obtains the structure tensor of the pixel points in the gradient maps of the original images. , and obtain the structure tensor of the pixels in the gradient map of the multi-exposure fusion image, and obtain the structure feature by calculating the cosine distance between the structure tensors; by calculating the exposure, contrast and saturation of each pixel in the original image Then use the pyramid fusion technology to upsample the original image to generate a Laplacian pyramid, upsample the weight map to generate a Gaussian pyramid, obtain a pseudo-reference fusion image, and then obtain global perceptual features; The feature vector composed of structural features and global perception features is used as input, combined with support vector regression technology, to obtain the predicted value of objective quality evaluation; the advantage is that it can improve the correlation between objective evaluation results and subjective perception.

Description

technical field [0001] The invention relates to an image quality evaluation method, in particular to a multi-exposure fusion image quality evaluation method. Background technique [0002] Dynamic range refers to the ratio of the maximum to minimum light intensity in a scene. The dynamic range in natural scenes is usually far beyond the dynamic range of digital photos captured by ordinary digital cameras. On the other hand, in a high dynamic range scene, existing display devices can only handle very limited This results in that a single digital photo cannot show all the details in the natural scene, which is manifested in the loss of details in the bright and dark areas of the digital photo. During the shooting process of ordinary digital cameras, there are over-exposure and under-exposure phenomena, which lead to the phenomenon of low dynamic range. In a special shooting environment, such as in the sky, due to the particularity of the light environment, there is a phenomen...

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): G06T7/00G06T5/00
CPCG06T7/0002G06T2207/10024G06T2207/20221G06T5/92
Inventor 姜求平徐佳武邵枫
Owner NINGBO UNIV