CN113989139A - Processing method for extracting red blood silk from facial skin image and forming blood silk spectrum - Google Patents
Processing method for extracting red blood silk from facial skin image and forming blood silk spectrum Download PDFInfo
- Publication number
- CN113989139A CN113989139A CN202111225646.6A CN202111225646A CN113989139A CN 113989139 A CN113989139 A CN 113989139A CN 202111225646 A CN202111225646 A CN 202111225646A CN 113989139 A CN113989139 A CN 113989139A
- Authority
- CN
- China
- Prior art keywords
- image
- facial skin
- channel
- blood streak
- red blood
- 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.)
- Pending
Links
- 239000008280 blood Substances 0.000 title claims abstract description 40
- 210000004369 blood Anatomy 0.000 title claims abstract description 40
- 230000001815 facial effect Effects 0.000 title claims abstract description 38
- 238000001228 spectrum Methods 0.000 title claims abstract description 19
- 238000003672 processing method Methods 0.000 title claims abstract description 15
- 230000009466 transformation Effects 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 8
- 230000002708 enhancing effect Effects 0.000 claims description 6
- 206010015150 Erythema Diseases 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000003745 diagnosis Methods 0.000 abstract description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000003796 beauty Effects 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a processing method for extracting red blood silk from a facial skin image and forming a blood silk spectrum, which comprises the steps of obtaining the facial skin image; carrying out image color space transformation on the facial skin image; extracting a V channel image of the HSV image; extracting an A channel image of the LAB image, and performing automatic harmonic enhancement on the image; newly building a blank image Mat, and dividing the Mat into HSV channels, wherein the value of the H channel is zero; assigning the S channel as the enhanced result MatA obtained in the step four; assigning the V channel value to the V channel image MatV extracted in the third step; and converting the HSV space image into an RGB space image. The facial skin redness identification technology of the invention carries out comprehensive examination on the facial skin of a client in a unique processing mode, shows the problems of redness of the skin which is seen through the eyes and is difficult to distinguish, and provides scientific reference for diagnosis and treatment of redness of the facial skin and medical cosmetology.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a processing method for extracting red blood silk from a facial skin image and forming a blood silk spectrum.
Background
In the dermatology department of hospitals and the medical beauty industry, when the red blood streak condition of the facial skin of a client is checked, the treatment is generally performed by taking a shot facial skin image as a reference. However, the blood vessels hidden under the skin are difficult to be completely presented due to the limitation of the current shooting and imaging technology, so that the image loses the guiding function, and the problems that the treatment for the red blood streak is difficult to cure and the like occur.
Disclosure of Invention
In order to solve the defects of the technology, the invention provides a processing method for extracting red blood silk from a facial skin image and forming a blood silk spectrum.
In order to solve the technical problems, the invention adopts the technical scheme that: a processing method for extracting red blood silk from a facial skin image and forming a blood silk spectrum comprises the following steps:
step one, acquiring a facial skin image under PL light and carrying out primary processing;
secondly, performing image color space transformation on the facial skin image, and converting the RGB color space of the image into an LAB color space and an HSV color space so as to obtain the LAB image and the HSV image;
step three, extracting a V channel image of the HSV image, and expressing the V channel image by using MatV;
extracting an A channel image of the LAB image, performing automatic harmonic enhancement on the image, and recording an image enhancement result as MatA;
step five, newly building a blank image Mat, and dividing the Mat into HSV channels, wherein the value of the H channel is zero; assigning the S channel as the enhanced result MatA obtained in the step four; assigning the V channel value to the V channel image MatV extracted in the third step;
and step six, converting the HSV space image obtained in the step five into an RGB space image to obtain a synthesized RGB color image, so that a red blood silk spectrum image of the facial skin is obtained.
Further, the method for harmonically enhancing the a-channel image in step four is as follows: all pixel values of the A channel image are arranged from small to large in sequence, and the minimum value min and the maximum value max after the harmony are obtained.
Further, for each pixel of the A channel image, if the pixel value is less than min, the blended pixel value is zero; if the pixel value is greater than max, the reconciled pixel value is 1.
Further, for the remaining pixel values, the reconciled pixel values are:
further, when the harmonic parameter percentage is 0.0, the minimum value and the maximum value of the pixel are the minimum value and the maximum value of the pixel of the present image.
Further, when the harmonic parameter is more than 0.0 and less than or equal to 1.0, the minimum value min is the sum of pixels multiplied by the harmonic parameter; the maximum value max is the sum of pixels x (1-harmonic parameter percent).
Further, the preliminary processing of the facial skin image in the first step includes Bessel cubic spline interpolation curve function processing.
Further, the input and output parameters of the Bessel cubic spline interpolation curve function are [55,38,211,200 ].
And further, enhancing the RGB color image obtained in the step six by using a Bessel cubic spline interpolation curve function.
Further, the input and output parameters of the bezier cubic spline interpolation curve function are as follows: [38,36,129,164].
Bezier cubic spline interpolation: an image processing algorithm that brightens or darkens an image to increase or decrease the contrast of the image.
The facial skin redness identification technology of the invention carries out comprehensive examination on the facial skin of a client in a unique processing mode, shows the problems of redness of the skin which is seen through the eyes and is difficult to distinguish, and provides scientific reference for diagnosis and treatment of redness of the facial skin and medical cosmetology.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
FIG. 2 is a facial skin image taken prior to processing by the method of the present invention.
FIG. 3 is a facial red blood streak spectral image obtained after processing by the method of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
As shown in fig. 1, a processing method for extracting red blood streak from a facial skin image and forming a blood streak spectrum comprises the following steps:
step one, acquiring a facial skin image under PL light through an instrument, as shown in fig. 2, and enhancing the image by using a Bessel cubic spline interpolation curve function and a saturation function.
The input and output parameters of the Bessel cubic spline interpolation curve function are [55,38,211,200 ]. The parameters of the image saturation function are-30.
And step two, image color space transformation. Converting an RGB color space of an image into an LAB color space; and simultaneously converting the RGB color space of the image into HSV color space.
Converting the image LAB into 32-bit floating point numbers and converting the values into 0-1 closed interval decimal numbers;
the image HSV converts to a 32-bit floating point number and converts the value to a 0-1 closed interval cell.
And step three, extracting the V channel image of the HSV image, and expressing the V channel image by using MatV.
And step four, enhancing the A channel image in an LAB color space mode. And extracting an A channel image of the LAB image, performing automatic harmonic enhancement on the image, and recording an image enhancement result as MatA. The concrete contents are as follows:
arranging all pixel values of the image of the channel A from small to large in sequence, and solving a minimum value min and a maximum value max after blending;
when the harmonic parameter percent is 0.0, the minimum value and the maximum value of the pixel are the minimum value and the maximum value of the pixel of the image;
thirdly, when the harmonic parameter is more than 0.0 and less than or equal to 1.0, the minimum value min is equal to the sum of the pixels multiplied by the harmonic parameter; maximum max is total pixel sum x (1-harmonic parameter percentage); as shown in the following formula:
min＝sort_result.at＜float＞(0,(int)row*col*percent)；
max＝sort_result.at＜float＞(0,(int)row*col*(1.0-percent))；
if the pixel value of each pixel of the A channel image is less than min, the blended pixel value is zero; if the pixel value is larger than max, the blended pixel value is 1;
for the remaining pixel values, the reconciled pixel values are:
and step five, reshaping the color image according to the color channel. Newly building a blank image Mat with the same size as the original image; partitioning Mat into HSV channels, wherein the value of the H channel is zero; assigning the enhancement result MatA obtained in the step four to an S channel of the newly-built blank image Mat; assigning the V channel image MatV extracted in the step three to a V channel of the newly-built blank image Mat; and the H channel value, the S channel value and the V channel value are all enlarged by 255 times and are converted into 8-bit unsigned data.
And step six, converting the HSV space image obtained in the step five into an RGB space image to obtain a synthesized RGB color image. The RGB color image was again curve enhanced once to obtain a red blood streak spectral image, as shown in FIG. 3. The curve parameters used were: [38,36,129,164].
The above embodiments are not intended to limit the present invention, and the present invention is not limited to the above examples, and those skilled in the art may make variations, modifications, additions or substitutions within the technical scope of the present invention.
Claims (10)
1. A processing method for extracting red blood silk from a facial skin image and forming a blood silk spectrum is characterized by comprising the following steps of: the method comprises the following steps:
step one, obtaining a facial skin image and carrying out primary processing;
secondly, performing image color space transformation on the facial skin image, and converting the RGB color space of the image into an LAB color space and an HSV color space so as to obtain the LAB image and the HSV image;
step three, extracting a V channel image of the HSV image, and expressing the V channel image by using MatV;
extracting an A channel image of the LAB image, performing automatic harmonic enhancement on the image, and recording an image enhancement result as MatA;
step five, newly building a blank image Mat, and dividing the Mat into HSV channels, wherein the value of the H channel is zero; assigning the S channel as the enhanced result MatA obtained in the step four; assigning the V channel value to the V channel image MatV extracted in the third step;
and step six, converting the HSV space image obtained in the step five into an RGB space image to obtain a synthesized RGB color image, so that a red blood silk spectrum image of the facial skin is obtained.
2. The processing method for extracting red blood streak from facial skin image and forming blood streak spectrum according to claim 1, wherein: the method for harmoniously enhancing the A channel image in the fourth step comprises the following steps: all pixel values of the A channel image are arranged from small to large in sequence, and the minimum value min and the maximum value max after the harmony are obtained.
3. The processing method for extracting red blood streak from facial skin image and forming blood streak spectrum according to claim 2, wherein: for each pixel of the A channel image, if the pixel value is less than min, the blended pixel value is zero; if the pixel value is greater than max, the reconciled pixel value is 1.
4. The processing method for extracting red blood streak from facial skin image and forming blood streak spectrum according to claim 3, wherein: for the remaining pixel values, the reconciled pixel values are:
5. the processing method for extracting red blood streak from facial skin image and forming blood streak spectrum according to claim 4, wherein: when the harmonic parameter percentage is 0.0, the minimum value and the maximum value of the pixel are the minimum value and the maximum value of the pixel of the image.
6. The processing method for extracting red blood streak from facial skin image and forming blood streak spectrum according to claim 5, wherein: when the harmonic parameter is more than 0.0 and less than or equal to 1.0, the minimum value min is equal to the pixel sum multiplied by the harmonic parameter; the maximum value max is the sum of pixels x (1-harmonic parameter percent).
7. The method for extracting red blood streak from facial skin image and forming blood streak spectrum according to any one of claims 1-6, wherein: the preliminary processing of the facial skin image in the first step comprises Bessel cubic spline interpolation curve function processing.
8. The processing method for extracting red blood streak from facial skin image and forming blood streak spectrum according to claim 7, wherein: the input and output parameters of the Bessel cubic spline interpolation curve function are [55,38,211,200 ].
9. The method for extracting red blood streak from facial skin image and forming blood streak spectrum according to any one of claims 1-6, wherein: and enhancing the RGB color image obtained in the step six by using a Bessel cubic spline interpolation curve function.
10. The processing method for extracting red blood streak from facial skin image and forming blood streak spectrum according to claim 9, wherein: the input and output parameters of the Bezier cubic spline interpolation curve function are as follows: [38,36,129,164].
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111225646.6A CN113989139A (en) | 2021-10-21 | 2021-10-21 | Processing method for extracting red blood silk from facial skin image and forming blood silk spectrum |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111225646.6A CN113989139A (en) | 2021-10-21 | 2021-10-21 | Processing method for extracting red blood silk from facial skin image and forming blood silk spectrum |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113989139A true CN113989139A (en) | 2022-01-28 |
Family
ID=79739863
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111225646.6A Pending CN113989139A (en) | 2021-10-21 | 2021-10-21 | Processing method for extracting red blood silk from facial skin image and forming blood silk spectrum |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113989139A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108171648A (en) * | 2017-11-27 | 2018-06-15 | 北京美摄网络科技有限公司 | A kind of method and apparatus of U.S.'s face skin color transition |
| CN109730637A (en) * | 2018-12-29 | 2019-05-10 | 中国科学院半导体研究所 | A kind of face face-image quantified system analysis and method |
| US20200184642A1 (en) * | 2018-12-11 | 2020-06-11 | H-Skin Aesthetics Co., Ltd. | Method for skin examination based on rbx color-space transformation |
| CN112215808A (en) * | 2020-09-24 | 2021-01-12 | 深圳数联天下智能科技有限公司 | Method and related device for generating human face skin sensitive image |
-
2021
- 2021-10-21 CN CN202111225646.6A patent/CN113989139A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108171648A (en) * | 2017-11-27 | 2018-06-15 | 北京美摄网络科技有限公司 | A kind of method and apparatus of U.S.'s face skin color transition |
| US20200184642A1 (en) * | 2018-12-11 | 2020-06-11 | H-Skin Aesthetics Co., Ltd. | Method for skin examination based on rbx color-space transformation |
| CN109730637A (en) * | 2018-12-29 | 2019-05-10 | 中国科学院半导体研究所 | A kind of face face-image quantified system analysis and method |
| CN112215808A (en) * | 2020-09-24 | 2021-01-12 | 深圳数联天下智能科技有限公司 | Method and related device for generating human face skin sensitive image |
Non-Patent Citations (1)
| Title |
|---|
| 穆锦荣;顾瑛;: "基于监督学习半自动检测鲜红斑痣病灶的方法", 中国激光医学杂志, no. 02, 15 April 2018 (2018-04-15), pages 49 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1565881B1 (en) | Image signal processing | |
| WO2019062608A1 (en) | Image processing method and device, electronic device and computer storage medium | |
| CN107705336B (en) | Pathological image dyeing component adjusting method | |
| CN114529475B (en) | Image enhancement method and system based on two-dimensional gamma correction and tone mapping | |
| CN108172278B (en) | HE staining pathological image color normalization method | |
| CN113344836B (en) | Face image processing method and device, computer readable storage medium and terminal | |
| CN106056565B (en) | A kind of MRI and PET image fusion method decomposed based on Multiscale Morphological bilateral filtering and contrast is compressed | |
| CN105631826B (en) | A kind of color image saturation Enhancement Method and system | |
| CN117496254A (en) | Intelligent identification method, device and equipment for black tea fermentation state and storage medium | |
| Ali et al. | Medical images enhanced by using fuzzy logic depending on contrast stretch membership function | |
| CN113989139A (en) | Processing method for extracting red blood silk from facial skin image and forming blood silk spectrum | |
| CN117575924A (en) | Visible light and near infrared fluorescence image fusion method of unified model | |
| JP5203159B2 (en) | Image processing method, image processing system, and image processing program | |
| CN111815548A (en) | Medium-long wave dual-waveband infrared image fusion method | |
| CN112233024A (en) | Medium-long wave dual-waveband infrared image fusion method based on difference characteristic color mapping | |
| JP4742068B2 (en) | Image processing method, image processing system, and image processing program | |
| CN113129356A (en) | Capsule endoscope system, image staining area recognition method thereof and computer-readable storage medium | |
| CN113989138A (en) | Method for extracting inflammation of facial skin image and forming red region spectrum | |
| CN107610186B (en) | Image processing method and device | |
| CN114418906A (en) | Image contrast enhancement method and system | |
| CN115880208A (en) | Image processing method, image processing apparatus, and medical device | |
| Saha et al. | A novel method for automated correction of non-uniform/poor illumination of retinal images without creating false artifacts | |
| CN113808057A (en) | Endoscope image enhancement method based on unsupervised learning | |
| Chen et al. | Multi-stage domain adversarial style reconstruction for cytopathological image stain normalization | |
| CN112614095B (en) | Method and system for analyzing liver meridian energy based on image processing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |