CN105869171A - Method for quantitatively analyzing human skin line aging - Google Patents
Method for quantitatively analyzing human skin line aging Download PDFInfo
- Publication number
- CN105869171A CN105869171A CN201610240322.2A CN201610240322A CN105869171A CN 105869171 A CN105869171 A CN 105869171A CN 201610240322 A CN201610240322 A CN 201610240322A CN 105869171 A CN105869171 A CN 105869171A
- Authority
- CN
- China
- Prior art keywords
- image
- contrast
- texture
- human body
- entropy
- 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
- 241000282414 Homo sapiens Species 0.000 title claims abstract description 41
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000032683 aging Effects 0.000 title claims abstract description 14
- 230000036548 skin texture Effects 0.000 claims description 26
- 238000004445 quantitative analysis Methods 0.000 claims description 9
- 208000031481 Pathologic Constriction Diseases 0.000 claims description 3
- 210000001215 vagina Anatomy 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 8
- 238000011160 research Methods 0.000 abstract description 6
- 239000011159 matrix material Substances 0.000 abstract description 4
- 238000005457 optimization Methods 0.000 abstract description 2
- 239000003990 capacitor Substances 0.000 abstract 1
- 239000000523 sample Substances 0.000 description 15
- 238000005516 engineering process Methods 0.000 description 5
- 239000013598 vector Substances 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 239000004744 fabric Substances 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000037303 wrinkles Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 210000001061 forehead Anatomy 0.000 description 2
- 239000012939 laminating adhesive Substances 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 241000282412 Homo Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 1
- 230000003712 anti-aging effect Effects 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000037396 body weight Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 239000002537 cosmetic Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000000265 homogenisation Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 239000000741 silica gel Substances 0.000 description 1
- 229910002027 silica gel Inorganic materials 0.000 description 1
- 230000000007 visual effect 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
-
- G06T5/94—
-
- 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
-
- 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
Abstract
The invention relates to a method for quantitatively analyzing human skin line aging and belongs to the technical field of human skin line research. The method comprises a step S1 of applying a capacitor-based fingerprint sensor to collect a human skin line image; a step S2 of adopting histogram equalization to perform gray-level enhance on the collected capacitance gray-level image of human skin lines, and improving image contrast and definition; a step S3 of applying a gray-level co-occurrence matrix algorithm to calculate changes of image secondary moment, contrast, entropy and correlation characteristic parameters; and a step S4 of analyzing relations between the four characteristic parameters including secondary moment, contrast, entropy and correlation of lines of different part of the human body. According to the method, the human skin line aging can be effectively quantitatively analyzed, and the method is of reference significance for analysis of the human skin line process and optimization of the line characteristic parameters.
Description
Technical field
The invention belongs to human body skin texture studying technological domain, relate to a kind of method that quantitative analysis human body skin texture is aging.
Background technology
Skin is one of organ of wanting of body weight for humans, and such as the barrier of human body, it comprises a lot of critical function.The age of one people is more
Coming the biggest, skin the most and then becomes aging, and therefore skin can objectively represent the change at age in the external world.Work as the mankind
Aesthetic standards also stop visual experience from the teeth outwards, skin becomes for the important discrimination standard of one aesthetic in living, because of
This, set up a set of scientifically, exactly, simple and fast analyze the texture aged method of human body skin, be beautifying skin and merit
Effect cosmetics research field needs the problem of solution and the important content of research badly.
At present the method for discrimination that human body skin is texture aged mainly there are two kinds: one is application mechanical detection method, certain with having
Skin surface laminating adhesive is detected by the probe of intensity, and its accuracy and sensitivity is the highest, and it is cumbersome to operate.Another
Kind be widely used be silica gel laminating adhesive, the shaded area formed under skew ray by detection wrinkle, then conversion obtain dermatoglyph and
The degree of depth of wrinkle.But the method there is also certain limitation in terms of sensitivity and precision, there is also equally operates compares
The problem of very complicated.Therefore, be badly in need of at present a kind of can the method for the simple texture aged situation of efficient analysis human body skin.
Along with the fast development of computer technology, computer technology application in image procossing is more extensive, and therein one
Individual important application is exactly the analysis to skin texture feature, and achieves certain achievement in research.At computer digital image
Reason and analytical technology, analyze texture quantitatively, extract effective characteristic parameter, in conjunction with rational mode identification method, Ke Yishi
The now description to different texture image.
Summary of the invention
In view of this, it is an object of the invention to provide a kind of method that quantitative analysis human body skin texture is aging, the method utilizes
Gray level co-occurrence matrixes, is analyzed the facial skin texture of the male of all ages and classes, calculates the direction matrix of four direction, logical
Cross the eigenvalue extracting it, carry out the evaluation that the human body skin of objective quantitative is texture aged, protect for beautifying skin and anti-ageing wrinkle resistant class
The curative effect evaluation of skin product provides strong technical support.
For reaching above-mentioned purpose, the present invention provides following technical scheme:
A kind of method that quantitative analysis human body skin texture is aging, the method comprises the following steps:
S1: human body skin image is acquired;
S2: the skin image collected is carried out pretreatment;
S3: use gray level co-occurrence matrixes algorithm, calculates the second moment of image, contrast, entropy and the change of correlative character parameter;
S4: analyze the second moment of human body different parts texture, contrast, exist between entropy and these four characteristic parameters of dependency
Relation.
Further, in step sl, Fingerprint sensor based on electric capacity is used to gather the face of all ages and classes male
The texture image of portion's different piece skin, it is ensured that the accuracy of image, the process gathering image has hurtless measure, and the fastest
Prompt advantage.
Further, in step s 2, the histogram equalization human body skin to collecting is used with Fingerprint Sensor
The electric capacity gray level image of skin texture carries out grey level enhancement, and then improves contrast and the definition of image.
The beneficial effects of the present invention is: the present invention uses Fingerprint sensor based on electric capacity to gather all ages and classes man
Property the texture image of face's different piece skin, it is ensured that the accuracy of image, gather the process hurtless measure of image, and letter
Single quick;It is then based on the analytical technology of image texture, by using gray level co-occurrence matrixes algorithm, calculates the second moment of image,
Contrast, the change of the characteristic parameter such as entropy and dependency.The most also analyze the second moment of human body different parts texture, contrast,
The relation existed between entropy and these four characteristic parameters of dependency.Through experimental analysis, the feature ginseng extracted with gray level co-occurrence matrixes
Number can be accurate, and effective quantitative analysis human body skin texture is aging.Analysis and optimization texture to human body skin ageing process are special
Levy parameter and have reference.
Accompanying drawing explanation
In order to make the purpose of the present invention, technical scheme and beneficial effect clearer, the present invention provides drawings described below to illustrate:
Fig. 1 is the schematic flow sheet of the method for the invention;
Fig. 2 is four sample graphs chosen in embodiment;
Fig. 3 is the forehead capacitance image of tester in embodiment;
Fig. 4 is the buccal capacitance image of tester in embodiment;
Fig. 5 is the eye capacitance image of tester in embodiment;
Fig. 6 is the characteristic vector of image in embodiment: (a) second order is away from (energy), (b) entropy, (c) contrast, (d) dependency
Curve and error line.
Detailed description of the invention
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are described in detail.
Fig. 1 is the schematic flow sheet of the method for the invention, as it can be seen, the method for the invention comprises the following steps: S1:
Human body skin image is acquired;S2: the skin image collected is carried out pretreatment;S3: use gray level co-occurrence matrixes to calculate
Method, calculates the second moment of image, contrast, entropy and the change of correlative character parameter;S4: analyze human body different parts texture
Second moment, contrast, between entropy and these four characteristic parameters of dependency exist relation.In step sl, use based on electricity
The Fingerprint sensor held gathers the texture image of face's different piece skin of all ages and classes male, it is ensured that image
Accuracy, the process gathering image has hurtless measure, and the advantage of simple and fast.In step s 2, histogram equalization is used
Change the electric capacity gray level image to the human body skin texture collected with Fingerprint Sensor and carry out grey level enhancement, Jin Ergai
The contrast of kind image and definition.
Below by specific embodiment, the method for the present invention is described in detail.
The present invention is initially with the electric capacity of the histogram equalization human body skin texture to collecting with Fingerprint Sensor
Gray level image carries out grey level enhancement, and then improves its contrast and definition.Histogram equalization is turned to a kind of basic contrast
The method that degree adjusts, general profit increases the local contrast of correspondence image, particularly useful data in image in this way
Contrast closely in the case of.By this kind of form, brightness has just had extraordinary distribution on the histogram.By this
The method of kind achieves and strengthens, the contrast of local by adjusting brightness on the premise of the contrast not affecting entirety
Joint just can reach same purpose.The core content that histogram equalization processes is from relatively the grey level histogram of original image
The gray scale interval, somewhere assembled replaces with being uniformly distributed under whole tonal ranges.Its concrete implementation is to adopt image
The mode of negated linear stretch, thus by the sub-distribution again of its pixel value, the particular number of pixel will not change along with grey scale change.
Proposing as the image becoming homogenization distribution to the rectangular histogram set the goal is provided possibility of histogram equalization.
The eigenvalue of gray level co-occurrence matrixes and meaning thereof:
Application gray level co-occurrence matrixes sets up 4 different characteristic vectors to describe skin texture, i.e. angle second moment (ASM), entropy (ENT),
Contrast (CON) and dependency (COR).
1) angle second order is away from (energy):
Representing standardization P (i, j, d, Δ), what G represented is the sum of gray level.
Angle second moment (ASM) represents in gray level co-occurrence matrixes that all elements value is added, after carrying out square calculating, the sum obtained again, it also by
It is called energy.It is evenly distributed degree and texture fineness away from gradation of image can be obtained by analyzing angle second order.When analyzing object
This situation that its whole value of rear discovery is the most equal just illustrates that its angle second moment is relatively small.Analyze and obtain some central value
But big other value is little just illustrates that its angle second moment is relatively large.If its angle second moment is the biggest, then with regard to table
Its texture bright is relatively thick, and energy is the biggest;Angle second moment is relatively small, shows that texture is thinner, and energy is smaller
?.
2) entropy:
The quantity of information of image can be analyzed by entropy (ENT) as a kind of accurate tolerance, most in gray level co-occurrence matrixes
In the case of number element is all one of random distribution, the entropy as a random metric will have the biggest value.Pass through
The value of entropy can clearly be seen that non-uniform degree or the complexity of the texture of a width figure.If image does not has any texture, that
The almost nil battle array of gray level co-occurrence matrixes.If texture is complicated, entropy is big;In the case of Xiang Fan, when the uniform gray level in image is divided
During cloth, it appeared that its interior element size has the biggest difference, so entropy in such cases is less.
3) contrast:
What contrast (CON) reflected is the definition of image, and it can also reflect the degree of the texture rill depth.Can be obtained this
The conclusion of sample: rill is deep, its contrast is the biggest, has the best definition;Otherwise, contrast
The when of smaller, the shallow naturally also ratio of rill is shallower, and effect is the clearest.What gray scale difference referred to is exactly right
Time bigger than degree, just corresponding more pixel pair, the value of gray scale difference is the biggest.In gray level co-occurrence matrixes when with
When diagonal element value apart from each other is the biggest, the value of contrast too can be the biggest.
4) dependency:
What dependency (COR) represented is is expert at or each yuan have the most identical place in a column direction.If the unit in matrix
Have the most identical, then exist for relatively large correlation;Otherwise, that is the value of pixel is the most identical and district
Time the biggest, then correlation is smaller comparatively speaking.Can also draw: when the texture of horizontal direction occurs, this kind
The correlation of type matrix is just larger than other kinds of.
U in formula1, u2,It is respectively defined as:
Embodiment:
When general utilization gray level co-occurrence matrixes is analyzed, for simplicity, the pixel distance parameter of gray level co-occurrence matrixes all takes into 1.
But, when distance change, characteristic parameter can change simultaneously.If it is excessive that distance is chosen, can cause between two pixels
Information dropout, cause gray level co-occurrence matrixes cannot effectively extract the detailed information of texture, so in the present embodiment, choose
The distance parameter scope discussed is 1 12.The picture randomly selected the fourth officer shown in Fig. 2 from picture library carries out eigenvalue
Extract, finally give following 4 different forms: table 1, table 2, table 3, table 4:
Table 1 different pixels apart under ASM value
Pel spacing is from D | Sample one | Sample two | Sample three | Sample four |
1 | 0.2138 | 0.5069 | 0.1700 | 0.1769 |
2 | 0.1749 | 0.4732 | 0.1418 | 0.1410 |
3 | 0.1569 | 0.4596 | 0.1306 | 0.1253 |
4 | 0.1470 | 0.4516 | 0.1237 | 0.1177 |
5 | 0.1404 | 0.4447 | 0.1184 | 0.1128 |
6 | 0.1359 | 0.4391 | 0.1144 | 0.1096 |
7 | 0.1327 | 0.4346 | 0.1114 | 0.1074 |
8 | 0.1305 | 0.4311 | 0.1092 | 0.1056 |
9 | 0.1291 | 0.4273 | 0.1073 | 0.1042 |
10 | 0.1279 | 0.4251 | 0.1061 | 0.1033 |
11 | 0.1274 | 0.4230 | 0.1048 | 0.1028 |
12 | 0.1269 | 0.4216 | 0.1039 | 0.1027 |
Table 2 different pixels apart under ENT value
Pel spacing is from D | Sample one | Sample two | Sample three | Sample four |
1 | 2.4862 | 1.5013 | 2.6538 | 2.6640 |
2 | 2.6156 | 1.5645 | 2.7603 | 2.8132 |
3 | 2.6667 | 1.5847 | 2.7998 | 2.8711 |
4 | 2.6940 | 1.5967 | 2.8243 | 2.8989 |
5 | 2.7124 | 1.6071 | 2.8436 | 2.9180 |
6 | 2.7253 | 1.6147 | 2.8581 | 2.9311 |
7 | 2.7351 | 1.6217 | 2.8706 | 2.9408 |
8 | 2.7417 | 1.6261 | 2.8797 | 2.9486 |
9 | 2.7467 | 1.6308 | 2.8875 | 2.9554 |
10 | 2.7503 | 1.6339 | 2.8924 | 2.9593 |
11 | 2.7526 | 1.6371 | 2.8976 | 2.9617 |
12 | 2.7540 | 1.6390 | 2.9019 | 2.9626 |
Table 3 different pixels apart under CON value
Table 4 different pixels apart under CON value
Pel spacing is from D | Sample one | Sample two | Sample three | Sample four |
1 | 0.0647 | 0.0877 | 0.0602 | 0.0699 |
2 | 0.0441 | 0.0584 | 0.0452 | 0.0518 |
3 | 0.0327 | 0.0476 | 0.0383 | 0.0420 |
4 | 0.0252 | 0.0408 | 0.0333 | 0.0364 |
5 | 0.0200 | 0.0361 | 0.0294 | 0.0323 |
6 | 0.0159 | 0.0319 | 0.0261 | 0.0292 |
7 | 0.0128 | 0.0289 | 0.0232 | 0.0268 |
8 | 0.0106 | 0.0265 | 0.0210 | 0.0247 |
9 | 0.0092 | 0.0243 | 0.0192 | 0.0228 |
10 | 0.0085 | 0.0226 | 0.0181 | 0.0213 |
11 | 0.0081 | 0.0214 | 0.0170 | 0.0204 |
12 | 0.0078 | 0.0206 | 0.0158 | 0.0197 |
From form it can be seen that for energy and entropy, eigenvalue change is universal slowly, is especially apparent when distance is more than 4;And
Contrast and dependency change more obvious with the increase of distance, but can also find and change more stable region at 4-12, this
One result represents that distance is less on the impact of eigenvalue in this case, and the eigenvalue obtained is the most stable.So below
When concrete analysis, the value in selected distance 4-12 interval carries out the extraction of further characteristic vector, simultaneously takes account of distance increase meeting
Affect the accuracy of extraction information, so the present embodiment calculates link in subsequent characteristics value, use distance, i.e. d=4 to calculate.
The present embodiment is for the age in 20-30 year and two healthy male volunteers in 30-40 year, and everyone is at its forehead, cheek
Respectively gathering 5 width electric capacity gray level images with eyes, see Fig. 3, Fig. 4, Fig. 5, wherein, volunteer 1 age is in 20-30 year, will
Hope person 2 age is in 30-40 year.One particularly significant innovation of the present invention is that the collection of face-image is used
Fingerprint Sensor.It is analogous to fingerprint sensor based on electric capacity, possesses 256 × 300 picture element matrixs, each
Every spatial resolution of pixel is 50 microns.Its range areas of measurement altogether is 12.8 × 15 microns.Each pixel essence
On be all a capacitive sensing device.Capacitance sensor mainly generates the capacitance image of a skin surface, in every piece image,
Each pixel can be represented by the 8 of 0-255 gray values, for all of measurement its measurement persistent period all by
It is limited in 5s, shows according to conventional research, utilize Fingerprint Sensor based on electric capacity can collect the most accurate
Human body skin texture picture, for people's volume textures correlation analysis and research, and the process gathered has non-invasive, and simply
Fast.
During concrete analysis, first use histogram equalization to carry out pretreatment the skin image collected, strengthen the contrast of image
And readability.Then by gray level co-occurrence matrixes algorithm to four relevant characteristic vectors of image zooming-out, its four stack features vector
With the age change as shown in Figure 6.
Skin texture second order result of calculation such as Fig. 6 (a) away from (energy) feature.Second order has reacted picture gray scale away from (energy) and has divided
The harmony of cloth and the fineness of human body skin texture.20-30 age bracket relatively, with advancing age, the 30-40 age
It is increasingly thicker that the texture of section skin can become, the most as can be observed from Figure second order away from value be to become big, especially with eye
Show is the most prominent.
Result of calculation such as Fig. 6 (b) for entropy.Entropy and second order are away from being inversely proportional to, and what it reflected is complexity and the ash of texture
The size of the randomness of degree distribution.If the randomness of gradation of image distribution is big, then all nonzero values in gray level co-occurrence matrixes are all
Almost equal, now entropy reaches maximum.From block diagram, second order increases along with the increase at age away from (energy) eigenvalue
Greatly, entropy then can reduce on the contrary, anyway as the same.Thus can obtain, when entropy is the biggest when, its texture will be the most intensive, instead
The sparse Image entropy of texture little.
The result of calculation such as Fig. 6 (c) of contrast. by the statistical data on figure, relative 30-40 age bracket, 20-30 age
The contrast of section is relatively large, and now the definition of texture is the most obvious, and texture is the thinnest.Afterwards, with advancing age, stricture of vagina
Comprehending the sparse random of change, local gray level change reduces, and texture is thicker, and contrast will significantly decrease.
The result of calculation such as Fig. 6 (d) of dependency. dependency reflects texture similarity in terms of certain in image, is image local
The tolerance of gray scale linear correlation.From block diagram it can be seen that contrast and dependency existence necessarily contact, the image that contrast is big,
Dependency is the least, otherwise, the image that dependency is big, contrast is the least.Meanwhile, the Changing Pattern of dependency and the change of second moment
Law is similar, and big at the comparison in difference of different age group.
In sum: the present embodiment, by using gray level co-occurrence matrixes algorithm, calculates the second moment of image, contrast, entropy and
The change of the characteristic parameters such as dependency.The most also analyze the second moment of human body different parts texture, contrast, entropy and dependency
The relation existed between these four characteristic parameters.Through experimental analysis, the characteristic parameter extracted with gray level co-occurrence matrixes can be accurate,
Effective quantitative analysis human body skin texture is aging.The range of age is the value of the value of volunteer's skin texture second moment in 30-40 year
Than the range of age be 20-30 year volunteer big, this illustrates that the age is the biggest, and second moment value is the biggest, and human body skin texture is more
Slightly, the age is the least, and second moment value is the least, and human body skin texture is the thinnest.Entropy reflection be the complexity of texture and gray scale is divided
Cloth situation, when energy eigenvalue increases along with the increase at age, entropy reduces, so entropy is big, shows that skin texture is the most complicated
Intensive, entropy is little, shows that uniform gray level skin texture is the most sparse.Age the least contrast value is relatively large, now texture
Relatively thin, and have texture definition clearly, the local gray level of image texture changes the most greatly.With advancing age, stricture of vagina
Reason local gray level change reduces, and can become sparse random, contrast is also with there occurs significantly decline.Dependency is anti-
Reflect is the linear correlation degree of gradation of image, and contrast and dependency exist certain contact, and contrast is big, and dependency is the least,
Dependency is big, and contrast is the least.
Finally illustrating, preferred embodiment above is only in order to illustrate technical scheme and unrestricted, although by above-mentioned
The present invention is described in detail by preferred embodiment, it is to be understood by those skilled in the art that can in form and
In details, it is made various change, without departing from claims of the present invention limited range.
Claims (3)
1. the method that a quantitative analysis human body skin texture is aging, it is characterised in that: the method comprises the following steps:
S1: human body skin texture image is acquired;
S2: the skin image collected is carried out pretreatment;
S3: use gray level co-occurrence matrixes algorithm, calculates the second moment of image, contrast, entropy and the change of correlative character parameter;
S4: analyze the second moment of human body different parts texture, contrast, exist between entropy and these four characteristic parameters of dependency
Relation.
The method that a kind of quantitative analysis human body skin texture the most according to claim 1 is aging, it is characterised in that: in step
In S1, Fingerprint sensor based on electric capacity is used to gather the stricture of vagina of face's different piece skin of all ages and classes male
Reason image, it is ensured that the accuracy of image.
The method that a kind of quantitative analysis human body skin texture the most according to claim 2 is aging, it is characterised in that: in step
In S2, the electric capacity gray level image of the histogram equalization human body skin texture to collecting with Fingerprint Sensor is used to enter
Row grey level enhancement, and then improve contrast and the definition of image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610240322.2A CN105869171A (en) | 2016-04-18 | 2016-04-18 | Method for quantitatively analyzing human skin line aging |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610240322.2A CN105869171A (en) | 2016-04-18 | 2016-04-18 | Method for quantitatively analyzing human skin line aging |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105869171A true CN105869171A (en) | 2016-08-17 |
Family
ID=56633297
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610240322.2A Pending CN105869171A (en) | 2016-04-18 | 2016-04-18 | Method for quantitatively analyzing human skin line aging |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105869171A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109427053A (en) * | 2017-08-31 | 2019-03-05 | 丽宝大数据股份有限公司 | Skin aging state evaluating method and electronic device |
CN109801320A (en) * | 2019-01-26 | 2019-05-24 | 武汉嫦娥医学抗衰机器人股份有限公司 | A kind of dry skin state Intelligent Identify method and system based on facial subregion |
CN109949279A (en) * | 2019-03-06 | 2019-06-28 | 义乌市悦美科技有限公司 | A kind of Analysis of age system based on skin image |
CN111553352A (en) * | 2020-04-27 | 2020-08-18 | 上海工程技术大学 | DICOM image processing method and system |
CN113051713A (en) * | 2021-03-01 | 2021-06-29 | 东方电气集团科学技术研究院有限公司 | Composite material aging prediction method based on image gray level co-occurrence matrix multi-feature extraction |
CN114511471A (en) * | 2022-04-18 | 2022-05-17 | 广州骏天科技有限公司 | Image optimization method and system based on gray level co-occurrence matrix |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101364263A (en) * | 2008-09-28 | 2009-02-11 | 腾讯科技(深圳)有限公司 | Method and system for detecting skin texture to image |
CN105095836A (en) * | 2014-05-14 | 2015-11-25 | 中国科学院深圳先进技术研究院 | Skin texture detecting method and apparatus based on Gabor features |
-
2016
- 2016-04-18 CN CN201610240322.2A patent/CN105869171A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101364263A (en) * | 2008-09-28 | 2009-02-11 | 腾讯科技(深圳)有限公司 | Method and system for detecting skin texture to image |
CN105095836A (en) * | 2014-05-14 | 2015-11-25 | 中国科学院深圳先进技术研究院 | Skin texture detecting method and apparatus based on Gabor features |
Non-Patent Citations (4)
Title |
---|
冯建 等: "基于灰度共生矩阵的表面粗糙度研究", 《光学与光电技术》 * |
宋佳丽: "皮肤纹理图像特征的提取与分析", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
许舒斐 等: "基于灰度共生矩阵的人体皮肤纹理分析", 《激光生物学报》 * |
郭德军 等: "基于灰度共生矩阵的纹理图像分类研究", 《林业机械与木工设备》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109427053A (en) * | 2017-08-31 | 2019-03-05 | 丽宝大数据股份有限公司 | Skin aging state evaluating method and electronic device |
CN109801320A (en) * | 2019-01-26 | 2019-05-24 | 武汉嫦娥医学抗衰机器人股份有限公司 | A kind of dry skin state Intelligent Identify method and system based on facial subregion |
CN109801320B (en) * | 2019-01-26 | 2020-12-01 | 武汉嫦娥医学抗衰机器人股份有限公司 | Intelligent skin dryness state identification method and system based on facial partition |
CN109949279A (en) * | 2019-03-06 | 2019-06-28 | 义乌市悦美科技有限公司 | A kind of Analysis of age system based on skin image |
CN111553352A (en) * | 2020-04-27 | 2020-08-18 | 上海工程技术大学 | DICOM image processing method and system |
CN111553352B (en) * | 2020-04-27 | 2022-06-24 | 上海工程技术大学 | DICOM image processing method and system |
CN113051713A (en) * | 2021-03-01 | 2021-06-29 | 东方电气集团科学技术研究院有限公司 | Composite material aging prediction method based on image gray level co-occurrence matrix multi-feature extraction |
CN114511471A (en) * | 2022-04-18 | 2022-05-17 | 广州骏天科技有限公司 | Image optimization method and system based on gray level co-occurrence matrix |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105869171A (en) | Method for quantitatively analyzing human skin line aging | |
CN111709902B (en) | Infrared and visible light image fusion method based on self-attention mechanism | |
Yuan et al. | Factorization-based texture segmentation | |
CN103996195B (en) | Image saliency detection method | |
CN102170581B (en) | Human-visual-system (HVS)-based structural similarity (SSIM) and characteristic matching three-dimensional image quality evaluation method | |
CN106600585A (en) | Skin condition quantitative evaluation method based on gray level co-occurrence matrix | |
CN103605958A (en) | Living body human face detection method based on gray scale symbiosis matrixes and wavelet analysis | |
CN103093478B (en) | Based on the allos image thick edges detection method of quick nuclear space fuzzy clustering | |
CN109711278A (en) | A kind of the eeg signal compression and classification method of low complex degree | |
CN102289670B (en) | Image characteristic extraction method with illumination robustness | |
CN111222380B (en) | Living body detection method and device and recognition model training method thereof | |
CN109117880A (en) | Tile image sorting algorithm based on WAVELET PACKET DECOMPOSITION selection coefficient weighting reconstruct | |
CN105842642A (en) | Fractional anisotropy microstructure characteristic extraction method based on kurtosis tensor and apparatus thereof | |
Murray et al. | Low-level spatiochromatic grouping for saliency estimation | |
CN107025444A (en) | Piecemeal collaboration represents that embedded nuclear sparse expression blocks face identification method and device | |
CN106682678A (en) | Image angle point detection and classification method based on support domain | |
Simonson et al. | A statistical approach to combining multisource information in one‐class classifiers | |
CN105740838A (en) | Recognition method in allusion to facial images with different dimensions | |
Al-Ani et al. | Precision statistical analysis of images based on brightness distribution | |
CN107527362A (en) | A kind of apple mouthfeel qualitative identification method based on image texture characteristic index | |
Tao et al. | Illumination-insensitive image representation via synergistic weighted center-surround receptive field model and weber law | |
CN107731306B (en) | Non-contact heart rate extraction method based on thermal imaging technology | |
Heravi et al. | Low price foot pressure distribution screening technique: Optical podoscope with accurate foot print segmentation using hidden Markov random field model | |
Xuan et al. | Subclass representation‐based face‐recognition algorithm derived from the structure scatter of training samples | |
Tamilmani et al. | Early detection of brain cancer using association allotment hierarchical clustering |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160817 |
|
RJ01 | Rejection of invention patent application after publication |