CN105869151A - Tongue segmentation and tongue coating and tongue body separation method - Google Patents
Tongue segmentation and tongue coating and tongue body separation method Download PDFInfo
- Publication number
- CN105869151A CN105869151A CN201610173867.6A CN201610173867A CN105869151A CN 105869151 A CN105869151 A CN 105869151A CN 201610173867 A CN201610173867 A CN 201610173867A CN 105869151 A CN105869151 A CN 105869151A
- Authority
- CN
- China
- Prior art keywords
- tongue
- image
- value
- channel
- skin
- 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.)
- Granted
Links
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a tongue segmentation and tongue coating and tongue body separation method. The method comprises the steps of shooting a mouth image; obtaining a main red false grey image; obtaining a primary tongue binary image; obtaining a final tongue binary image to obtain a final tongue image; obtaining a five-channel image of the tongue image, wherein the five-channel image has five channels of s, v, g, b and rg; drawing distribution histograms of the five channels; smoothing the drawn histograms; scoring the smoothed histogram images to obtain scores as corresponding channel scores; and performing two-dimensional 2-K-means clustering by utilizing the two channels with the highest scores to obtain tongue coating and tongue body images. According to the method, results obtained by the method are all superior to those obtained by an existing clustering-based tongue body separation algorithm in whether a clustering effect index or a tongue body separation effect.
Description
Technical field
The invention belongs to digital image processing field category, a kind of from the image with tongue, lip, tooth and mouth surrounding skin, tongue is partitioned into, and tongue is divided into tongue fur and the two-part method of body of the tongue.
Background technology
The introducing of new technique, the development to medical science serves critical impetus, and digital image processing techniques application in terms of medical science is filled with fresh blood to medical circle equally.The gradually perfect and computer computation ability along with Digital Image Processing and analyzed in theory and technology and the fast development of numeral Medical Imaging Technology, the process of digitized medical images and analysis are increasingly becoming domestic and international study hotspot.
If the application that Digital Image Processing is in terms of medical science is a big branch of Digital Image Processing, then Digital Image Processing utilization in terms of the traditional Chinese medical science is also that Digital Image Processing is particularly important and an important arteries and veins of potentiality Bright Prospect.Along with developing rapidly of modern science and technology, the development of the traditional Chinese medical science in the last few years has come into the achievement in research that new stage, particularly people obtain in terms of Computer Science and Technology and has constantly been applied to medical domain.Chinese medicine is the rarity of Chinese traditional culture, instructs China's clinical overall process cured the disease of diagnosing a disease for thousands of years, and its marrow is " dialectical treat ".Wherein, the four of " dialectical " big Main Means are: hope, hear, ask, cut.During traditional tcm diagnosis, the main information of doctor is by " hope, hear, ask, the cut " four diagnostic methods, and inspection is exactly that doctor uses vision to observe the change of expression, shape and the state of systemic or local.
Inspection of the tongue is the important content of tcm inspection, is also the most frequently used, one of diagnostic method of Traditional Chinese Medicine having clinical value most.The scope of application of inspection of the tongue is the widest, it may be said that the various aspects in medical treatment and healthcare field have actual application.Since thousand of years, inspection of the tongue development in practice, have accumulated rich experience, define the theory of comparison system, in terms of human body diseases is spied out in examination, truly have the biggest remarkable ability.The health status of human body can be made analysis by inspection of the tongue, and the diagnosis for disease provides foundation.Substantial amounts of clinical practice shows, position and the degree thereof of pathological changes not only can be analyzed and be diagnosed to be to inspection of the tongue well, and, in some cases it is also possible to find the disease that modern medical equipment all can not check out.Meanwhile, inspection of the tongue diagnoses a kind of holographic diagnostics technology of developing direction (painless and noninvasive wound) as representing future medicine, can be used not only for medical diagnosis on disease, reflects " barometer " of human physiology and psychology holistic health the most in time.Thus, inspection of the tongue is a theory of medicine highly studied and inquire into.But, all the time, several factors all hampers the fast development of inspection of the tongue.On the one hand, in China's Evolution of Tongue Inspection of TCM history of thousand of years, Traditional Chinese Medicine inspection of the tongue method subjectivity is too strong, and the overwhelming majority lacks objective indicator, and is unable to reach in research repeatably requirement.On the other hand, due to the restriction of Traditional Chinese Medicine self-condition, a lot of valuable medical informations are difficult to accurately record and properly preserve, and have both been unfavorable for that spreading of Chinese traditional treatment technology is also unfavorable for that the diagnostic history of patient is inquired about.Therefore, make with modern science and technology means that Evolution of Tongue Inspection of TCM is more scientific, objectify, embody, precision is extremely important and necessary.
1985, Anhui Chinese Medicine College and Chinese University of Science and Technology opened the gate of Externalization of Application of Tongue Inspection of TCM research, took the lead in having carried out the quantitative analysis experiment of colour of the tongue.Beijing Academy of Traditional Chinese Medicine has carried out Quantitative Study to the color of body of the tongue, tongue fur subsequently.Feng Chia University Qiu creates and dry utilizes image technology that tongue fur body of the tongue character is done Quantitative Study, and its thinking is that the research of many decades thereafter lays the foundation, and its method has become the common recognition of industry research person.
Tongue segmentation, coating nature separate, and are the first two steps of tongue reconstruction, are also crucial bases, directly influence feasibility and the accuracy of tongue reconstruction.
Tongue segmentation is from the image being made up of tongue, lip (small part comprises tooth) and mouth surrounding skin, the process being automatically partitioned into by tongue body；It is exactly tongue fur and body of the tongue part to be automatically separated from tongue image that coating nature separates.Both are inherently the image segmentation problem in field of medical image processing.
Common tongue dividing method has thresholding method, region-growing method, rim detection split-run, chrominance space split-run, cluster segmentation method.These methods under given conditions, can obtain good effect, but be as the change of environment, and the effect that segmentation obtains tends not to satisfactory, it is emphasized that lip separates the quality to segmentation with tongue creates large effect.
The separation of tongue fur body of the tongue is based primarily upon two kinds of methods, and threshold value separates and cluster partition method.Either threshold value still clusters, it is required for from known attribute (such as: H, S, the V etc. under R, G, B and HSV color space rgb color space) selected attribute to separate, but due to body of the tongue and the equal more than one of tongue fur, fixing one or several attributes tend not to that coating nature separates this image segmentation actual task and preferably describe, it is difficult to from these attributes, find the attribute of all tongue images in applicable whole data set, the a part of tongue image of data set is suitable for some attributes, and another part then utilizes other attribute can obtain more preferable effect.
Summary of the invention
The present invention provides a kind of and is partitioned into by tongue from the image with tongue, lip, tooth and mouth surrounding skin, and tongue is divided into tongue fur and the two-part method of body of the tongue.Technical scheme is as follows:
A kind of tongue segmentation and tongue fur body of the tongue separation method, comprise the following steps:
1) in camera and scene colour temperature all under conditions of 5500K, the mouth stretching out tongue is shot, obtains mouth image；
2) according to mouth image, the mouth image under its gray level image and HSV color space is obtained；
3) utilizing gray scale and HSV color space threshold value to carry out skin extraction, by non-skin partial filtration in image, obtain skin image, wherein, the gray value of H (0,0.139) and S (0.23,0.68) and pixel is more than 80；
4) utilize the mouth image under skin image and HSV color space, first obtain the most normalized main red pseudo-gray value i.e. RG' of each skin pixels point in figurej, formula is as follows:
RG'j=255 × | 1-2 × Hj|
In formula: RG'jFor pixel j the most normalized RG value in figure；HjFor pixel j H channel value under HSV color space and H [0,1],
The RG' of recycling each pointjValue calculates the main red pseudo-gray value i.e. RG of each pointj, formula is as follows:
RGj=255 × (RG'j-RG'min)÷(RG'max-RG'min)
In formula: RGjRG value for pixel j；RG'minFor all skin pixels point RG'jMinima；RG'maxFor all skin pixels point RG'jMaximum；
Last again by main for non-skin partial pixel point in figure red pseudo-gray value i.e. RGjValue is set to 50, obtains main red pseudo-gray level image；
5) main red pseudo-gray level image obtained in the previous step is carried out Da-Jin algorithm foreground extraction, the prospect obtained is carried out dilation erosion process, then according to area information, the prospect after dilation erosion is carried out contours extract, after obtaining the profile that area is maximum, this profile is carried out expansion process again, thus obtains preliminary tongue bianry image；
6) according to geometrical rule, preliminary tongue bianry image is carried out compensation, carry out the most again expanding obtaining final tongue bianry image with corrosion treatmentCorrosion Science, thus obtain final tongue image；
7) tongue image s, v, g, b, rg Five-channel image is obtained, respective channel under wherein s, v are HSV color space, g, b are the respective channel under rgb color space, and rg is main red pseudo-gray channel, and each attribute span is 0-255, obtain Five-channel distribution histogram；
8) draw the distribution histogram of Five-channel, and peak value is set to 300；
9) rectangular histogram drawn is carried out smoothing techniques；Processing procedure is: first dilation erosion, after take outermost profile；
10) formula is utilizedFor the histogram image scoring after smoothing, this score i.e. respective channel score；In formula: g is the score of histogram image；s1The area covered by summit；s2The area covered by the second peak；sallArea for whole distribution histogram image；D is the distance between two peaks；T1Property value corresponding to summit；T is the property value that between two peaks, the lowest point is corresponding；
11) two passages utilizing highest scoring carry out two-dimentional 2 class K-means clusters and respectively obtain tongue fur, body of the tongue image, initial center is obtained by the bimodal of highest scoring passage, tongue fur and body of the tongue is distinguished by the average distance of two class pixel point sets to tongue center, average distance greatly body of the tongue, on the contrary it is tongue fur.
The tongue fur body of the tongue separation method that the present invention proposes, remains and completes coating nature separation task by clustering algorithm.The method realizes Attributions selection by the distribution function of each attribute, thus each example for cluster finds the attribute being best suitable for self, substantially achieves the dimensionality reduction of cluster attribute.Either from Clustering Effect index still in terms of coating nature separating effect, the result that the method obtains is superior to existing coating nature separation algorithm based on cluster.
Accompanying drawing explanation
Fig. 1 is an example of picture collection
Fig. 2 is the mouth image intercepted out
Fig. 3 is the skin image obtained after skin extraction
Fig. 4 is the main red pseudo-gray level image of Fig. 3
Fig. 5 is that Fig. 4 is carried out the prospect that Da-Jin algorithm foreground extraction obtains
Fig. 6 is the preliminary bianry image of tongue
Fig. 7 is the final bianry image of tongue
Fig. 8 is tongue image
Fig. 9 is the distribution histogram of 5 passages, a () is g passage distribution histogram, (b) is b passage distribution histogram, and (c) is s passage distribution histogram, d () is v passage distribution histogram, (e) is rg passage distribution histogram
Figure 10 is the distribution histogram after 5 passages smooth, a () is g passage distribution histogram, b () is b passage distribution histogram, c () is s passage distribution histogram, d () is v passage distribution histogram, (e) is rg passage distribution histogram
Figure 11 is coating nature separating resulting, and (a) is body of the tongue image, and (b) is tongue fur image
Figure 12 is the method flow diagram of the present invention
Detailed description of the invention
Below as a example by an instantiation, describe this invention and realize the process that tongue segmentation separates with coating nature.
1) utilizing logitech C920 high-definition camera, in camera and scene colour temperature all under conditions of 5500K, shoot the mouth stretching out tongue, shooting gained picture size is 1920*1080.Picture collection one example such as Fig. 1.
2) reducing image and intercept, make whole mouth the most complete and enrich in whole intercepting picture after intercepting, intercepting picture size is 300*300, mouth image such as Fig. 2 after intercepting.
3) according to mouth image, the mouth image under its gray level image and HSV color space is obtained.Utilize gray scale and HSV color space threshold value to carry out skin extraction, by non-skin partial filtration in image, obtain skin image such as Fig. 3.
4) utilize the mouth image under skin image and HSV color space, obtain the main red pseudo-gray value of non-skin part in main red pseudo-gray level image, and figure and be set to 50, gained image such as Fig. 4.
5) main red pseudo-gray level image is carried out Da-Jin algorithm foreground extraction, obtain prospect such as Fig. 5.
6) corrosion that size is 15 pixels is carried out after the prospect obtained first being carried out the expansion that size is 3 pixels, then according to area information, the prospect after dilation erosion is carried out contours extract, after obtaining the profile that area is maximum, this profile is carried out the expansion that size is 15 pixels again, thus obtains preliminary tongue bianry image.Result such as Fig. 6.
7) to the profile extracted according to geometrical relationship, carry out compensation, then successively carry out size and be 10 pixels and the expansion of 15 pixels and corrosion obtains final tongue bianry image, such as Fig. 7.
8) according to the final bianry image of tongue, obtain tongue image, complete tongue segmentation, tongue image such as Fig. 8.
9) tongue image s, v, g, b, rg Five-channel image is obtained, wherein rg is main red pseudo-gray level image, and Five-channel attribute value is 0-255, obtain Five-channel distribution histogram and obtain the distribution histogram of 5 passages of tongue image, draw the distribution histogram of Five-channel, and peak value is set to 300, such as Fig. 9.
10) rectangular histogram drawn first carrying out dilation erosion then extract outermost profile and carry out smoothing techniques, the distribution histogram of smoothing, such as Figure 10.
11) formula is utilizedMarking rectangular histogram, this example is the 5th and the 2nd rectangular histogram highest scoring, utilizes respective channel to carry out two-dimentional two class K-means clusters, completes coating nature and separate, respectively obtain body of the tongue and tongue fur image such as Figure 11.
Claims (1)
1. tongue segmentation and a tongue fur body of the tongue separation method, comprise the following steps:
1) in camera and scene colour temperature all under conditions of 5500K, the mouth stretching out tongue is shot, obtains mouth image；
2) according to mouth image, the mouth image under its gray level image and HSV color space is obtained；
3) utilize gray scale and HSV color space threshold value to carry out skin extraction, by non-skin partial filtration in image, obtain skin image, wherein,
The gray value of H (0,0.139) and S (0.23,0.68) and pixel is more than 80；
4) utilize the mouth image under skin image and HSV color space, first obtain the most normalized main red pseudo-ash of each skin pixels point in figure
Angle value i.e. RG'j, formula is as follows:
RG'j=255 × | 1-2 × Hj|
In formula: RG'jFor pixel j the most normalized RG value in figure；HjFor pixel j H channel value under HSV color space and H [0,1],
The RG' of recycling each pointjValue calculates the main red pseudo-gray value i.e. RG of each pointj, formula is as follows:
RGj=255 × (RG'j-RG'min)÷(RG'max-RG'min)
In formula: RGjRG value for pixel j；RG'minFor all skin pixels point RG'jMinima；RG'maxFor all skin pixels point RG'j
Maximum；
Last again by main for non-skin partial pixel point in figure red pseudo-gray value i.e. RGjValue is set to 50, obtains main red pseudo-gray level image；
5) main red pseudo-gray level image obtained in the previous step is carried out Da-Jin algorithm foreground extraction, the prospect obtained is carried out dilation erosion process, then
According to area information, the prospect after dilation erosion is carried out contours extract, after obtaining the profile that area is maximum, then this profile is carried out expansion process, from
And obtain preliminary tongue bianry image；
6) according to geometrical rule, preliminary tongue bianry image is carried out compensation, carry out the most again expanding obtaining final tongue bianry image with corrosion treatmentCorrosion Science, from
And obtain final tongue image；
7) obtaining tongue image s, v, g, b, rg Five-channel image, the respective channel under wherein s, v are HSV color space, g, b are RGB
Respective channel under color space, rg is main red pseudo-gray channel, and each attribute span is 0-255, obtains Five-channel distribution histogram；
8) draw the distribution histogram of Five-channel, and peak value is set to 300；
9) rectangular histogram drawn is carried out smoothing techniques；Processing procedure is: first dilation erosion, after take outermost profile；
10) formula is utilizedFor the histogram image scoring after smoothing, this score i.e. respective channel score；In formula: g
Score for histogram image；s1The area covered by summit；s2The area covered by the second peak；sallFor whole distribution histogram image
Area；D is the distance between two peaks；T1Property value corresponding to summit；T is the property value that between two peaks, the lowest point is corresponding；
11) two passages utilizing highest scoring carry out two-dimentional 2 class K-means clusters and respectively obtain tongue fur, body of the tongue image, and initial center is by score
The bimodal of high channel obtains, the average distance of two class pixel point sets to tongue center distinguish tongue fur and body of the tongue, average distance greatly body of the tongue, otherwise
For tongue fur.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610173867.6A CN105869151B (en) | 2016-03-24 | 2016-03-24 | Tongue segmentation and tongue fur tongue nature separation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610173867.6A CN105869151B (en) | 2016-03-24 | 2016-03-24 | Tongue segmentation and tongue fur tongue nature separation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105869151A true CN105869151A (en) | 2016-08-17 |
| CN105869151B CN105869151B (en) | 2018-12-25 |
Family
ID=56625650
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610173867.6A Expired - Fee Related CN105869151B (en) | 2016-03-24 | 2016-03-24 | Tongue segmentation and tongue fur tongue nature separation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105869151B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106370618A (en) * | 2016-08-26 | 2017-02-01 | 天津中医药大学 | Human body tongue nature and tongue fur separation method based on double wavelength spectrum differentiation index |
| CN108629780A (en) * | 2018-04-23 | 2018-10-09 | 闽江学院 | Tongue image dividing method based on color decomposition and threshold technology |
| CN109886983A (en) * | 2018-12-27 | 2019-06-14 | 新绎健康科技有限公司 | A kind of image tongue body dividing method, device and computer equipment |
| CN113241182A (en) * | 2021-03-04 | 2021-08-10 | 武汉未康未病医学有限公司 | APP mathematical model for identifying tongue fur shape and tongue fur quality |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102147921A (en) * | 2011-04-08 | 2011-08-10 | 浙江理工大学 | Graph theory-based Chinese medicinal tongue nature and tongue coat separation algorithm |
| KR20130067658A (en) * | 2011-12-14 | 2013-06-25 | 한국 한의학 연구원 | Apparatus and method of diagnosing health by separating region of tongue coating from region of tongue substance |
| CN103745217A (en) * | 2013-12-31 | 2014-04-23 | 北京工业大学 | Automatic analysis method of tongue color and coating color in traditional Chinese medicine based on image retrieval |
| CN103946868A (en) * | 2013-05-13 | 2014-07-23 | 黄勃 | Processing method and system for medical images |
-
2016
- 2016-03-24 CN CN201610173867.6A patent/CN105869151B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102147921A (en) * | 2011-04-08 | 2011-08-10 | 浙江理工大学 | Graph theory-based Chinese medicinal tongue nature and tongue coat separation algorithm |
| KR20130067658A (en) * | 2011-12-14 | 2013-06-25 | 한국 한의학 연구원 | Apparatus and method of diagnosing health by separating region of tongue coating from region of tongue substance |
| CN103946868A (en) * | 2013-05-13 | 2014-07-23 | 黄勃 | Processing method and system for medical images |
| CN103745217A (en) * | 2013-12-31 | 2014-04-23 | 北京工业大学 | Automatic analysis method of tongue color and coating color in traditional Chinese medicine based on image retrieval |
Non-Patent Citations (3)
| Title |
|---|
| DU JIAN-QIANG 等: "A Novel Approach of Tongue Body and Tongue Coating Separation Based on FCM", 《BIOINFORMATICS AND BIOMEDICAL ENGINEERING.2008.ICBBE.2008.THE 2ND INTERNATIONAL CONFERENCE ON》 * |
| 刘峰 等: "聚类分析在舌苔舌质分离中的运用", 《漳州师范学院学报(自然科学版)》 * |
| 杜建强 等: "一种中医舌象的舌质舌苔分离方法", 《计算机应用研究》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106370618A (en) * | 2016-08-26 | 2017-02-01 | 天津中医药大学 | Human body tongue nature and tongue fur separation method based on double wavelength spectrum differentiation index |
| CN106370618B (en) * | 2016-08-26 | 2021-10-08 | 天津中医药大学 | Method for separating human tongue and tongue coating by dual-wavelength spectral difference index |
| CN108629780A (en) * | 2018-04-23 | 2018-10-09 | 闽江学院 | Tongue image dividing method based on color decomposition and threshold technology |
| CN108629780B (en) * | 2018-04-23 | 2020-01-03 | 闽江学院 | Tongue image segmentation method based on color decomposition and threshold technology |
| CN109886983A (en) * | 2018-12-27 | 2019-06-14 | 新绎健康科技有限公司 | A kind of image tongue body dividing method, device and computer equipment |
| CN113241182A (en) * | 2021-03-04 | 2021-08-10 | 武汉未康未病医学有限公司 | APP mathematical model for identifying tongue fur shape and tongue fur quality |
| CN113241182B (en) * | 2021-03-04 | 2024-08-02 | 武汉未康未病医学有限公司 | Construction method for identifying tongue fur shape and fur prime mathematical model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105869151B (en) | 2018-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200303062A1 (en) | Medical image aided diagnosis method and system combining image recognition and report editing | |
| Nida et al. | Melanoma lesion detection and segmentation using deep region based convolutional neural network and fuzzy C-means clustering | |
| Sobhaninia et al. | Brain tumor segmentation using deep learning by type specific sorting of images | |
| Xu et al. | Sliding window and regression based cup detection in digital fundus images for glaucoma diagnosis | |
| CN109472781B (en) | Diabetic retinopathy detection system based on serial structure segmentation | |
| CN104299242B (en) | Fluoroscopic visualization eye fundus image extracting method based on NGC ACM | |
| CN105869151B (en) | Tongue segmentation and tongue fur tongue nature separation method | |
| Abbas et al. | Combined spline and B-spline for an improved automatic skin lesion segmentation in dermoscopic images using optimal color channel | |
| SG172159A1 (en) | A method and system for determining the position of an optic cup boundary | |
| WO2017051191A2 (en) | Method and apparatus for tissue recognition | |
| Ali et al. | Melanoma detection using fuzzy C-means clustering coupled with mathematical morphology | |
| Celebi et al. | Guest editorial skin lesion image analysis for melanoma detection | |
| Salih et al. | Fast optic disc segmentation using FFT-based template-matching and region-growing techniques | |
| Prentasic et al. | Weighted ensemble based automatic detection of exudates in fundus photographs | |
| CN112560911A (en) | Tongue image classification method and system in traditional Chinese medicine | |
| Domínguez Hernández et al. | Development of an expert system as a diagnostic support of cervical cancer in atypical glandular cells, based on fuzzy logics and image interpretation | |
| CN108629780B (en) | Tongue image segmentation method based on color decomposition and threshold technology | |
| Rashid et al. | Unsupervised color image segmentation of red blood cell for thalassemia disease | |
| Maity et al. | Fusion of entropy-based thresholding and active contour model for detection of exudate and optic disc in color fundus images | |
| Bansal et al. | Performance analysis of color based region split and merge and otsu’s thresholding techniques for brain tumor extraction | |
| Xiaofang et al. | Lip analysis in traditional chinese medicine | |
| CN106991289A (en) | A kind of capsule endoscope image auxiliary interpretation method | |
| Harangi et al. | Improving automatic exudate detection based on the fusion of the results of multiple active contours | |
| Kuan et al. | A comparative study of segmentation algorithms in the classification of human skin burn depth | |
| Das et al. | Entropy thresholding based microaneurysm detection in fundus images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181225 Termination date: 20190324 |