CN110322450A - The method for improving binarization threshold selection accuracy - Google Patents
The method for improving binarization threshold selection accuracy Download PDFInfo
- Publication number
- CN110322450A CN110322450A CN201810275496.1A CN201810275496A CN110322450A CN 110322450 A CN110322450 A CN 110322450A CN 201810275496 A CN201810275496 A CN 201810275496A CN 110322450 A CN110322450 A CN 110322450A
- Authority
- CN
- China
- Prior art keywords
- brightness
- image
- carries out
- processing
- accuracy
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 230000011218 segmentation Effects 0.000 claims abstract description 12
- 238000001514 detection method Methods 0.000 claims abstract description 8
- 238000006243 chemical reaction Methods 0.000 claims abstract description 7
- 238000007689 inspection Methods 0.000 claims 1
- 230000002401 inhibitory effect Effects 0.000 abstract description 2
- 230000000875 corresponding Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000034 method Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006011 modification reaction Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
Abstract
The invention discloses the methods for improving binarization threshold selection accuracy, are related to image grayscale binary conversion treatment, including Threshold Segmentation Algorithm, further comprising the steps of: S1 obtains 3 or more images, and carries out gray processing processing；S2 carries out brightness detection to gray level image, obtains 3 or more brightness of image mean values, take the brightness population mean of 3 images above；S3 takes the image closest to brightness population mean to carry out luminance segmentation processing, coefficient of the part as brightness regulation higher than 128；S4 carries out binary conversion treatment using Threshold Segmentation Algorithm using coefficient as threshold value.The brightness detection can also be using contrast, saturation degree as target.The present invention can play inhibiting effect to excessive lightness or darkness image, improve the accuracy of binarization threshold selection, improve the accuracy of later image processing.
Description
Technical field
The present invention relates to a kind of image grayscale binary conversion treatments, and in particular to improves the side of binarization threshold selection accuracy
Method.
Background technique
Threshold value selection is always the problem of field of image processing, and threshold value determines the journey of information loss after binary image
Degree, and then influence the effect of image procossing.
Summary of the invention
Algorithm is insufficient when background too dark or too bright the technical problem to be solved by the present invention is to conventional images binary conversion treatment,
It is designed to provide the method for improving binarization threshold selection accuracy, is solved the above problems.
The method for improving binarization threshold selection accuracy, including Threshold Segmentation Algorithm, further comprising the steps of:
S1, obtains 3 or more images, and carries out gray processing processing；
S2 carries out brightness detection to gray level image, obtains 3 or more brightness of image mean values, take the bright of 3 images above
Spend population mean；
S3 takes the image closest to brightness population mean to carry out luminance segmentation processing, and the part higher than 128 is as brightness tune
The coefficient of section；
S4 carries out binary conversion treatment using Threshold Segmentation Algorithm using coefficient as threshold value.
S1,3 images above can be avoided random error；S2, population mean is for ensuring that image is not in mutation feelings
Condition；S3,128 be the center of pixel region 0-255, and population mean can effectively represent deviation post with 128 difference, is obtained most
Good threshold condition.
Further, the brightness detection can also be using contrast, saturation degree as target.Contrast and saturation degree and
Brightness detection has corresponding relation, therefore can also be used as the reference frame of binarization threshold choice accuracy.
Compared with prior art, the present invention having the following advantages and benefits:
The method that the present invention improves binarization threshold selection accuracy can play inhibition to excessive lightness or darkness image and make
With the accuracy of raising binarization threshold selection improves the accuracy of later image processing.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below with reference to embodiment, the present invention is made
Further to be described in detail, exemplary embodiment of the invention and its explanation for explaining only the invention, are not intended as to this
The restriction of invention.
Embodiment
The method that the present invention improves binarization threshold selection accuracy, including Threshold Segmentation Algorithm, further comprising the steps of:
S1, obtains 3 or more images, and carries out gray processing processing；
S2 carries out brightness detection to gray level image, obtains 3 or more brightness of image mean values, take the bright of 3 images above
Spend population mean；
S3 takes the image closest to brightness population mean to carry out luminance segmentation processing, and the part higher than 128 is as brightness tune
The coefficient of section；
S4 carries out binary conversion treatment using Threshold Segmentation Algorithm using coefficient as threshold value.S1,3 images above can be kept away
Exempt from random error；S2, population mean is for ensuring that image is not in catastrophe；S3,128 is in pixel region 0-255
The heart, population mean can effectively represent deviation post with 128 difference, obtain optimal threshold condition.
The brightness detection can also be using contrast, saturation degree as target.Contrast and saturation degree and brightness detect
There is corresponding relation, therefore can also be used as the reference frame of binarization threshold choice accuracy.
Above-described specific embodiment has carried out further the purpose of the present invention, technical scheme and beneficial effects
It is described in detail, it should be understood that being not intended to limit the present invention the foregoing is merely a specific embodiment of the invention
Protection scope, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should all include
Within protection scope of the present invention.
Claims (2)
1. the method for improving binarization threshold selection accuracy, including Threshold Segmentation Algorithm, which is characterized in that further include following step
It is rapid:
S1, obtains 3 or more images, and carries out gray processing processing；
S2 carries out brightness detection to gray level image, obtains 3 or more brightness of image mean values, take the brightness of 3 images above total
Body mean value；
S3 takes the image closest to brightness population mean to carry out luminance segmentation processing, and the part higher than 128 is as brightness regulation
Coefficient；
S4 carries out binary conversion treatment using Threshold Segmentation Algorithm using coefficient as threshold value.
2. the method according to claim 1 for improving binarization threshold selection accuracy, which is characterized in that the brightness inspection
Surveying can also be using contrast, saturation degree as target.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810275496.1A CN110322450A (en) | 2018-03-30 | 2018-03-30 | The method for improving binarization threshold selection accuracy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810275496.1A CN110322450A (en) | 2018-03-30 | 2018-03-30 | The method for improving binarization threshold selection accuracy |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110322450A true CN110322450A (en) | 2019-10-11 |
Family
ID=68111337
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810275496.1A Withdrawn CN110322450A (en) | 2018-03-30 | 2018-03-30 | The method for improving binarization threshold selection accuracy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110322450A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111739110A (en) * | 2020-08-07 | 2020-10-02 | 北京美摄网络科技有限公司 | Method and device for detecting image over-darkness or over-exposure |
-
2018
- 2018-03-30 CN CN201810275496.1A patent/CN110322450A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111739110A (en) * | 2020-08-07 | 2020-10-02 | 北京美摄网络科技有限公司 | Method and device for detecting image over-darkness or over-exposure |
| CN111739110B (en) * | 2020-08-07 | 2020-11-27 | 北京美摄网络科技有限公司 | Method and device for detecting image over-darkness or over-exposure |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105913396B (en) | A kind of image border holding mixing denoising method of noise estimation | |
| CN105741245B (en) | Adaptive contrast enhancement algorithm based on greyscale transformation | |
| CN104331863B (en) | A kind of image filtering denoising method | |
| CN108109123B (en) | Image denoising method | |
| CN107025641B (en) | Image interfusion method based on Analysis of Contrast | |
| CN111429372A (en) | Method for enhancing edge detection effect of low-contrast image | |
| CN110322450A (en) | The method for improving binarization threshold selection accuracy | |
| CN112488968A (en) | Image enhancement method for balanced fusion of degree-based histograms | |
| CN101211459A (en) | Boundary point processed histogram balancing method | |
| CN105447491A (en) | Signboard image binaryzation method and device | |
| CN107256539B (en) | Image sharpening method based on local contrast | |
| Dhal et al. | Entropy based range optimized brightness preserved histogram-equalization for image contrast enhancement | |
| Ziaei et al. | A novel approach for contrast enhancement in biomedical images based on histogram equalization | |
| CN105976342B (en) | A kind of adaptive gray level image Pseudo Col ored Image method | |
| CN104616259A (en) | Non-local mean image de-noising method with noise intensity self-adaptation function | |
| CN1316818C (en) | Image contrast intensifying method | |
| CN110321898A (en) | The method that grayscale binarization method accuracy improves | |
| CN112598607B (en) | Endoscope image blood vessel enhancement algorithm based on improved weighted CLAHE | |
| CN105740796B (en) | Lane line image binaryzation method after a kind of perspective transform based on grey level histogram | |
| CN113379649A (en) | Image enhancement method, device, equipment and storage medium | |
| JP2006270897A (en) | Image processing device, method and program | |
| CN112699760A (en) | Face target area detection method, device and equipment | |
| Ning et al. | A image fog removal method based on human visual property | |
| Astawa et al. | Histogram equalization and gaussian filtering combination method for face image optimization | |
| CN109410160A (en) | The infrared polarization image interfusion method driven based on multiple features and feature difference |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20191011 |