CN111724348B - Method for calculating texture attribute of skin image based on texture hill and groove features - Google Patents
Method for calculating texture attribute of skin image based on texture hill and groove features Download PDFInfo
- Publication number
- CN111724348B CN111724348B CN202010473377.4A CN202010473377A CN111724348B CN 111724348 B CN111724348 B CN 111724348B CN 202010473377 A CN202010473377 A CN 202010473377A CN 111724348 B CN111724348 B CN 111724348B
- Authority
- CN
- China
- Prior art keywords
- pixel
- image
- texture
- value
- point
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000012935 Averaging Methods 0.000 claims description 5
- 238000003384 imaging method Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 abstract description 3
- 230000036548 skin texture Effects 0.000 description 10
- 238000011156 evaluation Methods 0.000 description 8
- 238000001514 detection method Methods 0.000 description 5
- 210000001061 forehead Anatomy 0.000 description 5
- 238000005070 sampling Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000011496 digital image analysis Methods 0.000 description 3
- 238000012163 sequencing technique Methods 0.000 description 3
- 238000005286 illumination Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000037303 wrinkles Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- 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
- G06T2207/10004—Still image; Photographic 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
- G06T2207/10—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
- G06T2207/30004—Biomedical image processing
- G06T2207/30088—Skin; Dermal
Abstract
The invention discloses a method for calculating texture attributes of a skin image based on texture hillock features, and belongs to the technical field of skin image processing application. Graying the skin image, calculating to obtain a tri-value Cugou image, and calculating to obtain a texture attribute characteristic value for identifying the texture characteristics of the skin image. By adopting the technical scheme provided by the invention, the accuracy of detecting the texture attribute of the skin image is higher, and the method has practical application value.
Description
Technical Field
The invention relates to a skin image texture attribute calculating method, in particular to a method for calculating skin image texture attributes based on texture hillock features, and belongs to the technical field of skin image processing application.
Background
The skin surface state detection is one of important indexes for objectively evaluating the skin care effect of skin care products, the most commonly used skin state detection method at present is to shoot skin images at a short distance, statistically analyze the surface characteristics of the skin through an algorithm in the image field, and calculate the attribute value of the skin characteristics so as to evaluate the skin state.
The skin surface is mainly characterized by texture, wrinkles, pores, roughness, fat spots, fluorescent spots, glossiness, etc. Skin texture is one of the important attribute indicators of skin surface features, and is also the most difficult attribute to identify for computation.
Skin texture studies currently include two main branch methods, namely machine learning methods and computer image analysis methods. The machine learning method needs a large number of learning samples, has low calculation speed and has high accuracy; the computer image analysis method has the advantages of high difficulty in identifying and calculating the skin texture characteristics and low accuracy.
Disclosure of Invention
The invention provides a method for calculating texture attributes of a skin image based on texture sulcus features, which aims at carrying out texture analysis on a digital color image of the skin at a close-range forehead and an eye corner part with the same resolution and uniform illumination, and calculates attribute index values of the density, depth and width of the skin texture according to the texture sulcus features, wherein the index values can identify the texture features of the skin image. The accuracy of detecting the texture attribute of the skin image is higher by the skin texture attribute identification analysis algorithm, and the method has practical application value.
The invention calculates the texture attribute of the skin image based on the texture sulcus feature, which mainly comprises the following steps: (1) reading a skin color image into a computer memory; (2) graying the skin image and calculating a mean value; (3) Traversing pixels column by column, and calculating to obtain a tri-valued hill-and-groove image img2 (background 127, hill 255, groove 0 value); (4) Texture attribute feature values (width, depth, density) are calculated.
Specifically:
A. reading a skin color image to a computer memory to obtain RGB values of an image file, wherein the method comprises the following specific operations:
A1. the only parameter of the algorithm is an image file stored on a hard disk, and each image has a unique ID value;
A2. the image files may be stored on a local, network or other media medium, but the storage path needs to be recorded in a database,
the image file is accessible according to the unique ID;
A3. reading RGB values of the image file to a computer memory;
A4. image file formats include, but are not limited to jpg, bmp, png, etc.;
B. the skin image is grayed and the gray image mean value is calculated, and the specific steps are as follows:
B1. graying the color image to obtain a graying value of each pixel in the image;
averaging, graying and counting the color components of three channels of each pixel RGB of the read skin color image
The calculation formula is as follows:
Vgray＝(Vr+Vg+Vb)/3
wherein Vgray is a graying value of a pixel, vr, vg and Vb are three color components of RGB of the pixel respectively, and the image after graying of the color image is a gray image img1;
B2. calculating a gray image average value avg, wherein all pixel points of the gray image img1 participate in average value calculation, and the gray average value avg is obtained;
C. the three-valued hill-and-groove image img2 (background value of 127, hill value of 255, groove value of 0) is calculated as follows:
C1. setting the initial values of all pixels of img2 to the background color (i.e., the value is 127);
C2. each column of pixels of the grayscale image img1 is processed separately: for each column of pixels on img1, calculating all hills and furrows characteristic points of the column of pixels, and marking on img 2;
the specific operation is as follows:
c2.1 traversing each column of pixels of the gray image img1;
traversing all columns on the gray image img1, wherein each column is independently processed, and executing steps C2.4 and C2.5;
this treatment is mainly directed to the subject of the present study: forehead or canthus textures that have apparent lateral texture features and that will be identified as textures at the forehead or canthus;
c2.2, setting a skin background color gray value threshold range span, and taking the average value avg of the skin gray image as the skin background color when the average value avg of the skin gray image is in the gray value threshold range;
the threshold span is determined, the skin texture is characterized as a bright (hills) and dark (furrows) feature near the gray average value, a gray value threshold range which is slightly different from the gray image average value avg of the skin is defined as the background color of the skin, and if span=3 is defined, the range [ -3,3] is the background color of the skin.
Setting a step length, and traversing to sample one pixel point every step pixel points;
determining a step length, wherein the gray scale of continuous pixels is not strictly increased or decreased, and sampling a pixel at intervals for reducing gray scale jitter, wherein the method can effectively reduce a plurality of local hills and groove characteristic points which occur due to small jitter of gray values of continuous pixels when the groove characteristic points are calculated later, and if the step length step=5 can be determined, sampling a pixel at intervals of 5 pixel points;
c2.4 each column sequentially traverses the pixel points p on the column according to a specified step length step from top to bottom (or from bottom to top), determines that the attribute of the p pixel is one of a hills (255), a furrows (0) and a background (127), and one column of pixels is represented by a segment of background pixels, a segment of hills pixels, a segment of background pixels, a segment of furrows pixels, a segment of background pixels and a segment of hills pixels … …, and the specific steps are as follows:
c2.4.1 calculating the difference v between the gray value g of the pixel p and the gray image average avg, namely v=g-avg;
c2.4.2 a segment of hiller pixel starting points;
searching a first pixel point p with a v value larger than span, marking the pixel point p as s1 (the pixel point visually appears brighter than the average value of skin), wherein the s1 point is the starting point of a section of continuous hilly pixels in the column, and assigning the corresponding pixel value of the s1 point on img2 as 255 (hills);
c2.4.3 a segment of the hill pixel end point;
starting from the point s1, searching a first pixel point p with a v value smaller than span, wherein the point p at the moment is the ending point of a segment of hillock pixels, the pixel point p is marked as t1, and the pixels on the column start from the point s1 to the ending point of the point t1 are marked as complete;
c2.4.4 searching a segment of ditch pixel starting point;
searching a first pixel point p enabling v < -span from a point t1, marking the pixel point p as u1, wherein the point u1 is the starting point of a section of ditch pixel in the column, and assigning a corresponding pixel value of the point u1 on img2 as 0 (ditch);
c2.4.5 find a segment of trench pixel end points;
starting from a u1 point, searching a first v > -span pixel point p, wherein the p point at the moment is a section of groove pixel end point, marking the pixel point p as a point w1, finishing a section of groove pixel mark from the u1 point to the w1 point end of the column of pixels, simultaneously calculating the distance w between the u1 and w1 points, taking the distance w as the width of a groove, saving the width, and obtaining the point H of the minimum v value in the u1 and w1 sections as the deepest point of the groove; obtaining the average value d of gray values of all pixels on the gray image img1 corresponding to the u1 section and the w1 section, and taking the average value d as the depth attribute of the groove section and storing the depth attribute;
c2.5 traversing each column of pixels of the gray level image img1 to obtain all hilly pixel segments and all sulcus pixel segments in the gray level image img1; further calculating the distance s of the deepest points H of two adjacent grooves, and taking the distance s as the interval attribute of the two adjacent grooves and storing the interval attribute;
C3. after all columns of the gray image img1 are traversed, a tri-valued image img2 is obtained: value 127 identifies background pixels, value 255 identifies hill pixels, and value 0 identifies ditch pixels;
D. calculating texture attribute characteristic values (including width, depth and density), wherein the specific steps are as follows:
D1. calculating a texture width attribute value;
step C2.4.5 calculates and stores w values, averages all w values, and the obtained average value is texture width attribute width;
D2. calculating a texture depth attribute value;
step C2.4.5 calculates and stores d values, averages all d values to obtain an average value d1, avg-d1-span is texture Depth attribute Depth, the Depth value is positive, and the larger the value is, the deeper the texture is;
D3. calculating a texture density attribute value;
step C2.4.6 calculates and stores s values, averages all s values to obtain an average value s1, s1 is the distance between textures, and the greater the density degree density=1/s 1 of the textures, the denser the textures are represented, and conversely, the sparser is represented.
By the steps, the texture attribute of the skin image is calculated based on the texture sulcus features.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a method for calculating texture attributes of a skin image based on texture sulcus features, which adopts a computer image analysis method to perform texture analysis on a close-range forehead and canthus skin digital color image with the same resolution and uniform illumination, and calculates attribute index values of skin texture density, depth and width according to the texture sulcus features, wherein the index values are used for marking the texture features of the skin image. By adopting the technical scheme provided by the invention, the accuracy of detecting the texture attribute of the skin image is higher, and the method has practical application value.
Drawings
FIG. 1 is a block diagram of the apparatus architecture of a skin image texture attribute assessment system implemented in an embodiment of the present invention.
FIG. 2 is a flow chart of a method for skin texture assessment using a skin image texture attribute assessment system according to an embodiment of the present invention.
FIG. 3 is a block flow diagram of the skin texture calculation performed by the method of the present invention.
FIG. 4 is a schematic representation of a series of pixel gray scale hill-groove features in a skin image in accordance with an embodiment of the present invention.
FIG. 5 is a partial image interface screenshot of a skin image texture attribute evaluation system employed to calculate texture in accordance with an embodiment of the invention.
FIG. 6 is an interface screenshot of a system of an embodiment of the invention ordering skin images by attribute value.
Detailed Description
The invention is further described below with reference to the accompanying drawings by a set of embodiments of skin detection systems that have been deployed to be implemented. The hardware configuration of the skin image texture attribute evaluation system implemented by deployment is as follows in table 1:
TABLE 1 device configuration of skin image evaluation System of embodiments of the invention
| Name of the name | Apparatus and method for controlling the operation of a device | Quantity of |
| Skin image capturing device | Micro-distance skin imaging equipment for acquiring 1000 x 1000 skin color images | 5 |
| Cloud server | Windows server 2012、MySql5.7.16 | 1 |
| Client terminal | Android client of mobile phone | 5 |
The skin image texture attribute evaluation system comprises a skin imaging hardware device, a computer server side and a mobile phone client side, referring to fig. 1, a skin image texture evaluation flow chart of the skin image evaluation system referring to fig. 2, a skin image texture calculation flow chart referring to fig. 3, and the specific implementation steps are as follows:
A. the method for reading the skin color image into the computer memory comprises the following specific contents:
A1. the only parameter of the algorithm is an image file stored on a hard disk, and each image has a unique ID value;
A2. the image file may be stored on a local, network or other media medium, but the storage path needs to be recorded in a database, and the image file is accessible according to the unique ID;
A3. reading RGB values of the image file to a computer memory;
A4. image file formats include, but are not limited to jpg, bmp, png, etc.;
B. the skin image is grayed and the gray image mean value is calculated, and the specific steps are as follows:
B1. graying the color image;
graying skin image by simple average method for three channel color components of each pixel RGB of read skin color image
The calculation formula is as follows:
Vgray＝(Vr+Vg+Vb)/3
where Vgray is the graying value of a pixel, vr, vg, vb are the RGB three color components of the pixel respectively,
the image after the gray-scale of the color image is a gray-scale image img1;
B2. calculating a gray image average value avg, wherein all pixel points of the gray image img1 participate in average value calculation, and the gray average value avg is obtained;
C. the three-valued hill-and-groove image img2 (background value of 127, hill value of 255, groove value of 0) is calculated as follows:
C1. setting the initial values of all pixels of img2 to the background color (i.e., the value is 127);
C2. each column of pixels of the grayscale image img1 is processed separately: for each column of pixels on img2, calculating all hills and furrows characteristic points of the column of pixels, and marking on img 2; the specific operation is as follows:
c2.1 traversing each column of pixels of the gray image img1;
all columns are traversed on the gray image img1, and each column is independently operated, and the processing is mainly aimed at the research object of the invention: forehead or canthus textures, which have pronounced lateral texture features;
c2.2 determines a threshold span, the skin texture is characterized as a bright (hills) and dark (furrows) feature near the gray average, defines a range of gray value thresholds that differ little from the gray image average avg of the skin as the background color of the skin, and if span=3 is defined, the range [ -3,3] is the background color of the skin.
C2.3 determining a step length step, wherein the continuous pixel gray scale is not strictly gray scale increment or decrement, in order to reduce gray scale jitter, sampling a pixel point at regular intervals, and the method can effectively reduce a plurality of local hills and groove characteristic points which appear due to small jitter of continuous pixel gray scale values when the groove hills characteristic points are calculated later, if the step length step=5 can be determined, sampling a pixel point at every 5 pixel points;
c2.4 each column sequentially traverses the pixel points p on the column according to a specified step length step from top to bottom (or from bottom to top), determines that the attribute of the p pixel is one of a hills (255), a furrows (0) and a background (127), and one column of pixels is represented by a segment of background pixels, a segment of hills pixels, a segment of background pixels, a segment of furrows pixels, a segment of background pixels and a segment of hills pixels … …, and the specific steps are as follows:
c2.4.1 calculating the difference v between the gray value g of the pixel p and the gray image average avg, namely v=g-avg;
c2.4.2 find a segment of hillock pixel starting points;
searching a first pixel point p with a v value larger than span, marking the pixel point p as s1 (the pixel point visually appears brighter than the average value of skin), wherein the s1 point is the starting point of a section of continuous hilly pixels on the column, and assigning the corresponding pixel value of the s1 point on img2 as 255 (hills);
c2.4.3 find a segment of the mound pixel end point;
starting from the point s1, searching a first pixel point p with a v value smaller than span, wherein the point p at the moment is the ending point of a segment of hillock pixels, the pixel point p is marked as t1, and the pixels on the column start from the point s1 to the ending point of the point t1 are marked as complete;
c2.4.4 searching a segment of ditch pixel starting point;
searching a first pixel point p enabling v < -span from a point t1, marking the pixel point p as u1, wherein the point u1 is the starting point of a section of groove pixel on the column, and assigning a corresponding pixel value of the point u1 on img2 as 0 (groove);
c2.4.5 find a segment of trench pixel end points;
starting from a u1 point, searching a first v > -span pixel point p, wherein the p point is a section of ditch pixel end point, marking the pixel point p as a point w1, finishing a section of ditch pixel mark from the u1 point to the w1 point end of the column of pixels, simultaneously calculating the distance w between the u1 and w1 points, taking the distance w as the width of a ditch and saving, solving the point H of the minimum v value in the u1 and w1 sections as the deepest point of the ditch, taking the average value of all pixel gray values on gray images img1 corresponding to the u1 and w1 sections as d, and taking the average value as the depth attribute of the section of ditch and saving;
C2.4.6. repeating steps C2.4.2-C2.4.5, identifying all the mound pixel segments and the ditch pixel segments on the column until the pixel points p on the column are traversed, and calculating the distance s of the deepest points H of two adjacent ditches as the interval attribute of the two adjacent ditches and storing the distance s in the process of traversing ditches and mounds; C3. after all columns of the gray image img1 are traversed, a tri-valued image img2 is obtained: value 127 identifies background pixels, value 255 identifies hill pixels, and value 0 identifies ditch pixels;
D. calculating texture attribute characteristic values (including width, depth and density), wherein the specific steps are as follows:
D1. calculating a texture width attribute value;
step C2.4.5 calculates and stores w values, averages all w values, and the obtained average value is texture width attribute width;
D2. calculating a texture depth attribute value;
step C2.4.5 calculates and stores d values, averages all d values to obtain an average value d1, avg-d1-span is texture Depth attribute Depth, the Depth value is positive, and the larger the value is, the deeper the texture is;
D. calculating a texture density attribute value;
step C2.4.6 calculates and stores s values, averages all s values to obtain an average value s1, s1 is the distance between textures, and the greater the density degree density=1/s 1 of the textures, the denser the textures are represented, and conversely, the sparser is represented.
By the steps, the texture attribute of the skin image is calculated based on the texture sulcus features. FIG. 4 is a schematic diagram of a row of pixel mound, groove identification and texture sparseness, depth and width attributes calculation.
The embodiment results show that the method for calculating the texture attribute of the skin image based on the texture sulcus features, which is realized by the method, has the advantages of rapid detection result and higher accuracy of the detection result. In this embodiment, the texture features of 200 skin images are ordered according to quantitative values of different attributes, specifically, 5 different clients can log in respectively and pick up skin images with a micro distance and upload the skin images to a computer server, the computer server calculates the texture density, depth and width attributes of each image respectively by adopting the method of the present invention, fig. 5 is a partial image in the texture features, and the corresponding texture attributes are calculated to obtain values (the values are processed in percentage so that a user of a mobile phone client can understand the meaning of the values) from interface screenshot of a skin image evaluation system, and table 2 is shown in the following description.
Table 2 calculation of texture multiple attribute values for skin images using the method of the present invention
In fig. 5, the middle value under each picture is a texture depth value, and the partial images sequenced according to the attribute values of the texture obtained by calculation (from the interface screenshot of the skin image evaluation system, the middle value under each picture is a value for sequencing the texture), and from the sequencing result, the calculation accuracy of the texture attribute values calculated by the hill-and-groove method is higher, the sequencing result is shown in fig. 6, the calculation speed of the algorithm is high, and the total calculation time of 200 images is less than 2 minutes.
It should be noted that the purpose of the disclosed embodiments is to aid further understanding of the present invention, but those skilled in the art will appreciate that: various alternatives and modifications are possible without departing from the spirit and scope of the invention and the appended claims. Therefore, the invention should not be limited to the disclosed embodiments, but rather the scope of the invention is defined by the appended claims.
Claims (10)
1. A method for calculating texture attribute of skin image based on texture sulcus feature comprises graying skin image, calculating to obtain tri-valued sulcus image, and calculating to obtain texture attribute feature value; the method comprises the following steps:
A. reading a color skin image and acquiring RGB values of the image;
B. graying the skin image and calculating to obtain a gray image mean value, wherein the method comprises the following specific steps:
B1. graying the color image to obtain a graying value of each pixel in the image and a gray image img1;
particularly, the color components of three channels of each pixel RGB of the skin color image are averaged, and the average value is the graying value of the pixel; the image after the gray-scale of the color image is a gray-scale image img1;
B2. calculating to obtain a gray level image average avg: averaging the graying values of all pixel points of the gray image img1 to obtain a gray image average avg;
C. calculating to obtain a tri-valued dune image img2, and identifying pixel points in the image as one of a background, a dune and a ditch, wherein the value of the attribute is 127, the value of the attribute is 255, and the value of the attribute is 0; the method comprises the following operations:
C1. setting the initial values of all the pixels of img2 as background color, namely, the value of 127;
C2. each column of pixels of the grayscale image img1 is processed separately: for each column of pixels on img1, calculating all hills and furrows characteristic points of the column of pixels, and marking on img 2; the specific operation is as follows:
C21. setting a skin background color gray value threshold range span, and taking the average value avg of the skin gray image as the skin background color when the average value avg of the skin gray image is in the gray value threshold range;
C22. setting a step length, and traversing to sample a pixel point every step pixel points;
C23. traversing each column of pixels of the gray level image img1 according to the step length step in sequence, determining the attribute of the pixel point p, and identifying the pixel point in the image as one of a background, a hills and a furrows; the method specifically comprises the following operations:
c231 calculates the difference between the gray value g of the pixel point p and the gray image average avg to obtain a gray value v, namely v=g-avg;
c232 determines the starting point of a segment of hiller pixels:
searching a first pixel point p with a v value larger than span, marking the pixel point p as s1, wherein s1 is the starting point of a section of continuous hills pixels in the column, assigning a corresponding pixel value of the s1 point on img2 as 255, and indicating that the pixel attribute is hills;
c233 determines a segment of hill pixels ending points;
starting from the s1 point, searching a first pixel point p with a v value smaller than span, wherein the p point at the moment is the end point of a segment of hillock pixels, and marking the pixel point p as t1; that is, the section of pixels from the s1 point to the t1 point of the column of pixel points is identified as a hill pixel;
c234 determines a starting point for a segment of trench pixels;
searching a first pixel point p with a v value smaller than-span from a point t1, marking the pixel point p as u1, wherein the point u1 is the starting point of a section of ditch pixel in the column, assigning a corresponding pixel value of the point u1 on img2 as 0, and identifying the point as the ditch pixel;
c235 determining a segment of trench pixel end points;
starting from a u1 point, searching a first pixel point p with a v value larger than-span, wherein the p point at the moment is the ending point of the segment of ditch pixel, and marking the pixel point p as a point w1; that is, the section of pixels from the u1 point to the w1 point of the column of pixel points is identified as ditch pixels;
calculating the distance w between two points u1 and w1 in the pixel of the groove section, and taking the distance w as the width of the groove and storing the width;
obtaining a point H of a minimum v value in the segment of groove pixels as a deepest point of the groove;
obtaining the average value d of gray values of all pixels on the gray image img1 corresponding to the segment of ditch pixels, and taking the average value d as the depth attribute of the segment of ditch pixels and storing the depth attribute;
C24. traversing each column of pixels of the gray image img1 to obtain all hilly pixel segments and all ditches pixel segments in the gray image img1; further calculating the distance s of the deepest points H of two adjacent grooves, and taking the distance s as the interval attribute of the two adjacent grooves and storing the interval attribute;
C3. after all columns of the gray image img1 are traversed, a tri-valued image img2 is obtained: a pixel point value of 127 in img2 represents a background pixel, a value of 255 represents a hill pixel, and a value of 0 represents a groove pixel;
D. calculating to obtain texture attribute characteristic values, including width, depth and density;
through the steps, the texture attribute of the skin image is obtained based on texture hill groove feature calculation.
2. The method of computing skin image texture attributes based on texture sulcus features as claimed in claim 1, wherein step D computes texture attribute feature values, comprising:
D1. calculating texture width attribute values: averaging all w values to obtain an average value which is texture width attribute width;
D2. calculating texture depth attribute values: averaging all d values to obtain an average value d1;
texture Depth attribute depth=avg-d 1-span; the Depth value is positive, the larger the value is, the deeper the texture is;
D3. calculating texture density attribute values: averaging all the s values to obtain an average value s1, wherein s1 is the inter-texture distance;
texture density degree Density=1/s 1; the larger the density value, the denser the texture, and conversely the more sparse.
3. The method of computing skin image texture attributes based on texture sulcus features of claim 1, wherein the skin color image comprises an image file in jpg, bmp, png format.
4. The method of computing skin image texture attributes based on texture sulcus features of claim 1, wherein the specific calculation formula for graying the skin image in step B is as follows:
Vgray＝(Vr+Vg+Vb)/3
where Vgray is a grayscale value of a pixel, and Vr, vg, and Vb are RGB three color components of the pixel, respectively.
5. The method of computing skin image texture attributes based on texture sulcus features as claimed in claim 1, wherein in step C2.2, the threshold span takes a value of 3; the pixel gray value in the range of-3, 3 indicates that the pixel is the background color of the skin.
6. The method of claim 1, wherein in step C2.3, the step value is 5.
7. A skin image texture attribute assessment system implementing the method of computing skin image texture attributes based on texture sulcus features of any one of claims 1-6.
8. The system of claim 7, wherein the system comprises a skin imaging hardware device, a computer server side, and a client side.
9. The system of claim 8, wherein the skin imaging hardware device is a macro skin imaging device for acquiring 1000 x 1000 skin color images.
10. The system of claim 8, wherein the computer server is a cloud server, and specifically operates a system Windows server 2012 and a database mysql5.7.16; and/or the client is an Android mobile phone.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010473377.4A CN111724348B (en) | 2020-05-29 | 2020-05-29 | Method for calculating texture attribute of skin image based on texture hill and groove features |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010473377.4A CN111724348B (en) | 2020-05-29 | 2020-05-29 | Method for calculating texture attribute of skin image based on texture hill and groove features |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111724348A CN111724348A (en) | 2020-09-29 |
| CN111724348B true CN111724348B (en) | 2024-03-26 |
Family
ID=72565298
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010473377.4A Active CN111724348B (en) | 2020-05-29 | 2020-05-29 | Method for calculating texture attribute of skin image based on texture hill and groove features |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111724348B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107169960A (en) * | 2017-05-15 | 2017-09-15 | 精诚工坊电子集成技术（北京）有限公司 | A kind of skin surface pore size detection method based on color of image space |
| CN107157447A (en) * | 2017-05-15 | 2017-09-15 | 精诚工坊电子集成技术（北京）有限公司 | The detection method of skin surface roughness based on image RGB color |
| CN107564079A (en) * | 2017-08-28 | 2018-01-09 | 北京白鹭时代信息技术有限公司 | A kind of undulating topography generation method |
| CN109949273A (en) * | 2019-02-25 | 2019-06-28 | 北京工商大学 | Skin image texture segmentation method and system based on texture symmetry |
| CN110853009A (en) * | 2019-11-11 | 2020-02-28 | 北京端点医药研究开发有限公司 | Retina pathology image analysis system based on machine learning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10702160B2 (en) * | 2018-05-02 | 2020-07-07 | Canfield Scientific, Incorporated | Skin assessment using image fusion |
-
2020
- 2020-05-29 CN CN202010473377.4A patent/CN111724348B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107169960A (en) * | 2017-05-15 | 2017-09-15 | 精诚工坊电子集成技术（北京）有限公司 | A kind of skin surface pore size detection method based on color of image space |
| CN107157447A (en) * | 2017-05-15 | 2017-09-15 | 精诚工坊电子集成技术（北京）有限公司 | The detection method of skin surface roughness based on image RGB color |
| CN107564079A (en) * | 2017-08-28 | 2018-01-09 | 北京白鹭时代信息技术有限公司 | A kind of undulating topography generation method |
| CN109949273A (en) * | 2019-02-25 | 2019-06-28 | 北京工商大学 | Skin image texture segmentation method and system based on texture symmetry |
| CN110853009A (en) * | 2019-11-11 | 2020-02-28 | 北京端点医药研究开发有限公司 | Retina pathology image analysis system based on machine learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111724348A (en) | 2020-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108921130B (en) | Video key frame extraction method based on saliency region | |
| CN108109147B (en) | No-reference quality evaluation method for blurred image | |
| CN111369597B (en) | Particle filter target tracking method based on multi-feature fusion | |
| KR20090111136A (en) | Method and Apparatus of Selecting Best Image | |
| CN107169960A (en) | A kind of skin surface pore size detection method based on color of image space | |
| JP2010537585A5 (en) | Detect and classify matches between time-based media | |
| CN105550694B (en) | Method for measuring fuzzy degree of face image | |
| US11244429B2 (en) | Method of providing a sharpness measure for an image | |
| CN108230325A (en) | The compound degraded image quality evaluating method and system decomposed based on cartoon texture | |
| CN104077776B (en) | A kind of visual background extracting method based on color space adaptive updates | |
| US9153013B2 (en) | Image processing apparatus, image processing method and computer readable medium | |
| CN116452598A (en) | Axle production quality rapid detection method and system based on computer vision | |
| CN111709914A (en) | Non-reference image quality evaluation method based on HVS characteristics | |
| CN116071271A (en) | Analysis method for image capturing of tablet personal computer | |
| CN106529441A (en) | Fuzzy boundary fragmentation-based depth motion map human body action recognition method | |
| CN115346126A (en) | Side slope crack identification method | |
| US8537212B2 (en) | Recording apparatus and recording method thereof | |
| CN111724348B (en) | Method for calculating texture attribute of skin image based on texture hill and groove features | |
| CN108416770B (en) | Image quality evaluation method based on visual saliency | |
| Li et al. | A modified histogram equalization approach for image contrast enhancement | |
| Wang et al. | Image quality assessment based on local orientation distributions | |
| CN114549872A (en) | Target feature calculation method based on color and structure | |
| Le Moan et al. | Towards exploiting change blindness for image processing | |
| CN111861981B (en) | Image color space fat point detection and evaluation method based on dotted line and plane | |
| CN113344001A (en) | Organism weight estimation method, device, equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |