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

An automatic detail analysis method for objectively evaluating dead leaf images for image quality

An image quality and automatic analysis technology, applied in image analysis, image enhancement, image data processing, etc., can solve the problems of large error in detail parameters, difficulty in accurately evaluating dead leaf images, etc., and achieve the effect of improving analysis efficiency

Active Publication Date: 2019-06-25
易诚博睿(南京)科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide an automatic analysis method for the details of the dead leaf map for objective evaluation of the image quality, to solve the problem that the detail parameters extracted by the existing extraction method have large errors and are difficult to accurately evaluate the dead leaf map

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
  • An automatic detail analysis method for objectively evaluating dead leaf images for image quality

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] A detailed automatic analysis method for objectively evaluating dead leaf maps for image quality, comprising the following steps: automatic segmentation of dead leaf map regions based on frequency domain templates; map classification based on high-brightness grayscale; dead leaf map PSD calculation; Noise PSD calculation for regions; detail parameter estimation.

[0035] In this embodiment, the automatic segmentation of the dead leaf map area based on the frequency domain template, the specific method is as follows:

[0036] Extract the batch dead leaf map area, perform Fourier transform on the dead leaf map in this area, take the normalized amplitude spectrum for average, and obtain the reference dead leaf map amplitude spectrum and phase spectrum;

[0037] Perform band-pass filtering on the reference amplitude spectrum to remove high-frequency noise and the influence of DC;

[0038] The segmented image is to be divided into overlapping blocks, and then Fourier transf...

Embodiment 2

[0043] A detailed automatic analysis method for objectively evaluating dead leaf maps for image quality, comprising the following steps: automatic segmentation of dead leaf map regions based on frequency domain templates; map classification based on high-brightness grayscale; dead leaf map PSD calculation; Noise PSD calculation for regions; detail parameter estimation.

[0044] In the present embodiment, the specific method of the map classification based on the highlighted gray scale is as follows:

[0045] Perform grayscale processing on the chart image, then calculate the grayscale histogram of the image, calculate the cumulative grayscale histogram of the histogram, and use the minimum grayscale with a cumulative histogram frequency greater than 99% to binarize the image;

[0046] Perform morphological opening operations on the binarized image;

[0047] Based on the convex hull algorithm, extract all the closure areas in the noise-removed binary image, and calculate the r...

Embodiment 3

[0050] A detailed automatic analysis method for objectively evaluating dead leaf maps for image quality, comprising the following steps: automatic segmentation of dead leaf map regions based on frequency domain templates; map classification based on high-brightness grayscale; dead leaf map PSD calculation; Noise PSD calculation for regions; detail parameter estimation.

[0051] In this embodiment, the noise PSD calculation based on multiple regions, the specific method is as follows:

[0052] After the position estimation of the dead leaf map area is completed, combined with the recognized map type, extract the map smooth area of ​​the entire map, including the grayscale area (except for the area with text information);

[0053] Calculate the mean value of each region with different attributes, subtract the mean value from the gray value of the original image, and remove the fixed bias;

[0054] Calculate the difference distribution of all removed offset regions, and perform ...

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 relates to the field of image evaluation, in particular to an automatic detail analysis method for objectively evaluating dead leaf image according to image quality, which comprises thefollowing steps: automatic segmentation of dead leaf image region based on frequency domain template; automatic segmentation of dead leaf image region based on frequency domain template. Graphic CardClassification Based on Highlight Gray Level; PSD calculation of dead leaf graph; Noise PSD Calculation Based on Multiple Regions; Detail parameter estimation. The invention achieves the purpose of analyzing the details of the batch dead leaf map and improves the analysis efficiency by automatically dividing the dead leaf map area. The method uses multi-region to calculate image noise, which is more consistent with the average noise model. Through the fitting of fixed model, the abrupt change of noise PSD caused by the change of position can be eliminated, which makes the noise PSD more accurate and improves the accuracy of detail analysis.

Description

technical field [0001] The invention relates to the field of image evaluation, in particular to an automatic detail analysis method for objectively evaluating dead leaf images for image quality. Background technique [0002] In the field of objective image quality evaluation, the process and method of extracting the detailed parameters of the dead leaf map currently used are mainly realized by the following means: manually or automatically calibrate the area to be evaluated (markers are required); extract the dead leaf map area, calculate The power spectral density function PSD of the dead leaf map area; extract the power spectral density function PSD of the noise area; according to the definition of MTF, extract the MTF of the dead leaf map area, and then calculate the detail preservation according to the provided resolution, cut-off frequency and observation distance Accuracy and degree of loss. [0003] The above method of dead leaf map analysis is convenient and simple ...

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): G06T7/00G06T7/11G06T7/44G06T7/62
CPCG06T7/0002G06T7/11G06T7/44G06T7/62G06T2207/20048G06T2207/30188
Inventor 董波王道宁张亚东
Owner 易诚博睿(南京)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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com