CN115953392A - Tongue body coating quality evaluation method based on artificial intelligence - Google Patents
Tongue body coating quality evaluation method based on artificial intelligence Download PDFInfo
- Publication number
- CN115953392A CN115953392A CN202310223940.6A CN202310223940A CN115953392A CN 115953392 A CN115953392 A CN 115953392A CN 202310223940 A CN202310223940 A CN 202310223940A CN 115953392 A CN115953392 A CN 115953392A
- Authority
- CN
- China
- Prior art keywords
- tongue
- image
- tongue body
- judging
- artificial intelligence
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Image Analysis (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a tongue body coating quality evaluation method based on artificial intelligence, which comprises the following steps: s1, acquiring a tongue image to be analyzed; s2, detecting a tongue body in the tongue image, and positioning and performing edge segmentation to obtain a tongue body image; s3, processing the tongue image in a blocking mode to obtain a blocking image P 1 ,P 2 ,......,P n And carrying out normalization processing to obtain image block pixel p x (i, j); s4 pairs of image block pixels p x (i, j) carrying out histogram information statistics, and recording the occurrence frequency of each pixel value as F x (ii) a S5, judging granularity according to the counted times, and analyzing the tongue fur quality; the concept of granularity is put forward and the local information of the tongue body image acquired by the tongue image instrument based on constant illumination intensity is usedThe method is mapped to the granularity, whether the tongue body is in a normal coating, a rotten coating or a greasy coating state is evaluated, and compared with other methods, the method has higher universality and adaptability to external factors such as environmental illumination change and the like and the specificity of the tongue body.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a tongue body coating quality evaluation method based on artificial intelligence.
Background
The science of traditional Chinese medicine considers that: the tongue proper is generated by stomach qi, and the five zang-organs and six fu-organs all inherit the stomach qi and communicate with the zang-organs, so it can reflect the internal state of the human body. The tongue proper can reflect the internal state of the human body, so the evaluation of the tongue proper is an important link in the diagnosis of TCM. The tongue proper of the normal people is generally that the tongue coating is thin and evenly spread on the tongue surface, the middle part and the root part of the tongue surface are thicker, and the body fluid is evenly distributed; when a person suffers from a disease, the color, quality and distribution of body fluids of the tongue can change, which can reflect the severity and location of the disease. Therefore, the distribution of the tongue coating and body fluid can be observed frequently during the diagnosis of traditional Chinese medicine, which is of great significance for judging the health condition of the patient.
At present, the diagnosis and treatment of doctors of traditional Chinese medicine mainly adopts subjective evaluation of tongue quality, however, the diagnosis process has certain subjectivity, for example, the diagnosis modes of doctors of traditional Chinese medicine to patients are different, and the diagnosis of different doctors to the same patient is also inconsistent, and the method extremely depends on the experience of doctors and has strong subjectivity. In recent years, many researchers have developed auxiliary analysis methods using computer technology in order to provide objective tongue information. The artificial intelligence method or the traditional method mainly used at present focuses on local features and ignores information contained in the whole tongue body image, so that the generalization capability of the evaluation methods is insufficient, and the accuracy of the algorithm is easily reduced due to the influence of external factors such as acquisition environment and the like.
Disclosure of Invention
The invention aims to solve the problems and designs a tongue body coating quality evaluation method based on artificial intelligence.
The invention achieves the above purpose through the following technical scheme:
the tongue body coating quality evaluation method based on artificial intelligence comprises the following steps:
s1, acquiring a tongue image to be analyzed;
s2, detecting a tongue body in the tongue image by adopting a U-Net deep learning network, and positioning and performing edge segmentation to obtain a tongue body image;
s3, processing the tongue body image in a blocking mode to obtain a blocking image P 1 ,P 2 ,......,P n And carrying out normalization processing to obtain image block pixel p x (i,j)；
S4, image block pixel p x (i, j) carrying out histogram information statistics, and recording the frequency of occurrence of each pixel value as F x ；
And S5, judging granularity according to the counted times, and analyzing the tongue coating quality.
The invention has the beneficial effects that: the concept of granularity is provided, local information of a tongue body image acquired by a tongue image instrument based on constant illumination intensity is mapped into the granularity, whether the tongue body is in a normal coating, a rotten coating and a greasy coating state or not is evaluated, compared with other methods, the method combines the whole and local information of the tongue body image to carry out comprehensive evaluation, and has higher universality and adaptability to external factors such as environmental illumination change and the like and the specificity of the tongue body.
Drawings
FIG. 1 is a schematic flow chart of the method for evaluating tongue coating quality based on artificial intelligence according to the present invention;
FIG. 2 is a schematic view of a captured tongue image;
FIG. 3 is a schematic view of a captured tongue image;
FIG. 4 is a schematic flow chart of the granularity judgment of the tongue coating quality assessment method based on artificial intelligence.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
In the description of the present invention, it is to be understood that the terms "upper", "lower", "inside", "outside", "left", "right", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, or the orientations or positional relationships that the products of the present invention are conventionally placed in use, or the orientations or positional relationships that are conventionally understood by those skilled in the art, and are used for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention.
Furthermore, the terms "first," "second," and the like are used solely to distinguish one from another, and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it is also to be noted that, unless otherwise explicitly stated or limited, the terms "disposed" and "connected" are to be interpreted broadly, and for example, "connected" may be a fixed connection, a detachable connection, or an integral connection; can be mechanically or electrically connected; the connection may be direct or indirect via an intermediate medium, and may be a communication between the two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
The following detailed description of embodiments of the invention refers to the accompanying drawings.
As shown in figure 1, the tongue body coating quality evaluation method based on artificial intelligence comprises the following steps:
s1, acquiring a tongue image to be analyzed, as shown in figure 2;
s2, detecting a tongue body in the tongue image by adopting a U-Net deep learning network, and positioning and performing edge segmentation to obtain a tongue body image, as shown in FIG. 3;
s3, processing the tongue body image in a blocking mode to obtain a blocking image P 1 ,P 2 ,......,P n And carrying out normalization processing to obtain image block pixel p x (i, j) is represented by
N =255; the method specifically comprises the following steps: the tongue image is divided into a plurality of detailed regions, so that a region of interest (ROI) sensitive to an algorithm can be better searched, and therefore the tongue image is effectively divided based on a template method; dividing the collected image with the resolution of 1024 × 1024 into 512 blocks, wherein the calculation formula of the boundary pixel length of each block is as follows: (i/512) × (j/512), where i represents the pixel length of the input image and j represents the pixel width of the original image. Obtaining a block image P after the image block processing 1 ,P 2 ,......,P n ，n=512；
S4, image block pixel p x (i, j) carrying out histogram information statistics, and recording the frequency of occurrence of each pixel value as F X ；
S5, judging granularity according to the counted times, and analyzing the tongue coating quality; the method specifically comprises the following steps:
s51, calculating the probability P (x) of each pixel value, and expressing the probability P (x) as
Wherein, F x Indicates the number of pixels with a pixel value of x, F 1 、F 2 ...F n Respectively representing the number of the pixel values of 1 and 2.. N;
s52, calculating the entropy of the probability P (x), and expressing the probability P (x) as
Obtaining a tongue image block P 1 ,P 2 ,......,P n Corresponding histogram entropy value H 1 ,H 2 ,......,H n ；
S53, counting all entropy values, then judging the granularity, judging whether the total number of the entropy values larger than 3 is smaller than n/2, and if so, judging that the moss quality is normal moss; otherwise, go to S54, as shown in fig. 4;
s54, judging whether the total quantity of the entropy values which are more than or equal to 5 is less than n/4, if so, judging that the tongue proper is a rotten tongue; otherwise, the tongue proper is greasy.
According to the characteristic that entropy values of image histograms are remarkably different when tongue bodies are greasy, the concept of granularity is provided, local information of the tongue body images acquired by a tongue image instrument based on constant illumination intensity is mapped into the granularity, and then the overall information of the tongue body images is represented based on the distribution of the granularity to carry out comprehensive judgment by combining the overall information and the local information of the tongue body images.
Compared with other methods, the method for evaluating whether the tongue body is in a normal coating, rotten coating and greasy coating state combines the whole and local information of the tongue body image to carry out comprehensive evaluation, and has higher universality and adaptability to external factors such as environmental illumination change and the like and the specificity of the tongue body.
The technical solution of the present invention is not limited to the above-mentioned specific embodiments, and all technical modifications made according to the technical solution of the present invention fall within the protection scope of the present invention.
Claims (3)
1. The tongue body coating quality evaluation method based on artificial intelligence is characterized by comprising the following steps:
s1, acquiring a tongue image to be analyzed;
s2, detecting a tongue body in the tongue image by adopting a U-Net deep learning network, and positioning and performing edge segmentation to obtain a tongue body image;
s3, processing the tongue body image in a blocking mode to obtain a blocking image P 1 ,P 2 ,......,P n And carrying out normalization processing to obtain image block pixel p x (i,j)；
S4, image block pixel p x (i, j) intoAnd (4) counting row histogram information, and counting the occurrence frequency of each pixel value and recording the occurrence frequency as F x ；
And S5, judging granularity according to the counted times, and analyzing the tongue coating quality.
2. The artificial intelligence based tongue coating quality assessment method according to claim 1, wherein in S5 comprises:
s51, calculating the probability P (x) of each pixel value, and expressing the probability P (x) as
Wherein F is x Indicates the number of pixels with a pixel value of x, F 1 、F 2 ...F n Respectively representing the number of the pixel values of 1 and 2.. N;
s52, calculating the entropy of the probability P (x), and expressing the probability P (x) as
Obtaining a tongue image block P 1 ,P 2 ,......,P n Corresponding histogram entropy value H 1 ,H 2 ,......,H n ；
S53, counting all entropy values, then judging the granularity, judging whether the total number of the entropy values larger than 3 is smaller than n/2, and if so, judging that the moss quality is normal moss; otherwise, entering S54;
s54, judging whether the total quantity of the entropy values which are more than or equal to 5 is less than n/4, if so, judging that the tongue proper is a rotten tongue; otherwise, the tongue proper is greasy.
3. The artificial intelligence based tongue coating quality assessment method according to claim 1, wherein in S3, the pixels p of the processed body image block are normalized x (i, j) is represented by
，n=512，N=255。/>
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310223940.6A CN115953392B (en) | 2023-03-09 | 2023-03-09 | Tongue body tongue fur quality assessment method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310223940.6A CN115953392B (en) | 2023-03-09 | 2023-03-09 | Tongue body tongue fur quality assessment method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115953392A true CN115953392A (en) | 2023-04-11 |
| CN115953392B CN115953392B (en) | 2023-05-16 |
Family
ID=85906867
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310223940.6A Active CN115953392B (en) | 2023-03-09 | 2023-03-09 | Tongue body tongue fur quality assessment method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115953392B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1512451A (en) * | 2002-12-28 | 2004-07-14 | ���ǵ�����ʽ���� | Method for extracting concerned area from tongue image and relative health monitoring method and device |
| CN1931087A (en) * | 2006-10-11 | 2007-03-21 | 哈尔滨工业大学 | Automatic tongue picture grain analysis method |
| CN103946868A (en) * | 2013-05-13 | 2014-07-23 | 黄勃 | Processing method and system for medical images |
| CN103985113A (en) * | 2014-03-12 | 2014-08-13 | 浙江工商大学 | Tongue image segmentation method |
| CN106510636A (en) * | 2016-11-29 | 2017-03-22 | 深圳市易特科信息技术有限公司 | Automatic detection system and method for tongue image in traditional Chinese medicine technology |
| CN112633301A (en) * | 2021-01-14 | 2021-04-09 | 北京工业大学 | Traditional Chinese medicine tongue image greasy feature classification method based on depth metric learning |
| CN113506266A (en) * | 2021-07-09 | 2021-10-15 | 平安科技（深圳）有限公司 | Method, device and equipment for detecting tongue greasy coating and storage medium |
| CN113657449A (en) * | 2021-07-15 | 2021-11-16 | 北京工业大学 | Traditional Chinese medicine tongue picture greasy classification method containing noise labeling data |
| CN114511884A (en) * | 2022-01-29 | 2022-05-17 | 上海国民集团健康科技有限公司 | Tongue image definition recognition method, device, equipment and medium based on contrast learning |
| CN115375690A (en) * | 2022-10-26 | 2022-11-22 | 合肥云诊信息科技有限公司 | Tongue picture putrefaction classification and identification method |
-
2023
- 2023-03-09 CN CN202310223940.6A patent/CN115953392B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1512451A (en) * | 2002-12-28 | 2004-07-14 | ���ǵ�����ʽ���� | Method for extracting concerned area from tongue image and relative health monitoring method and device |
| US20040151379A1 (en) * | 2002-12-28 | 2004-08-05 | Samsung Electronics Co., Ltd. | Method of digital image analysis for isolating a region of interest within a tongue image and health monitoring method and apparatus using the tongue image |
| CN1931087A (en) * | 2006-10-11 | 2007-03-21 | 哈尔滨工业大学 | Automatic tongue picture grain analysis method |
| CN103946868A (en) * | 2013-05-13 | 2014-07-23 | 黄勃 | Processing method and system for medical images |
| WO2014183246A1 (en) * | 2013-05-13 | 2014-11-20 | Huang Bo | Medical image processing method and system |
| CN103985113A (en) * | 2014-03-12 | 2014-08-13 | 浙江工商大学 | Tongue image segmentation method |
| CN106510636A (en) * | 2016-11-29 | 2017-03-22 | 深圳市易特科信息技术有限公司 | Automatic detection system and method for tongue image in traditional Chinese medicine technology |
| CN112633301A (en) * | 2021-01-14 | 2021-04-09 | 北京工业大学 | Traditional Chinese medicine tongue image greasy feature classification method based on depth metric learning |
| CN113506266A (en) * | 2021-07-09 | 2021-10-15 | 平安科技（深圳）有限公司 | Method, device and equipment for detecting tongue greasy coating and storage medium |
| CN113657449A (en) * | 2021-07-15 | 2021-11-16 | 北京工业大学 | Traditional Chinese medicine tongue picture greasy classification method containing noise labeling data |
| CN114511884A (en) * | 2022-01-29 | 2022-05-17 | 上海国民集团健康科技有限公司 | Tongue image definition recognition method, device, equipment and medium based on contrast learning |
| CN115375690A (en) * | 2022-10-26 | 2022-11-22 | 合肥云诊信息科技有限公司 | Tongue picture putrefaction classification and identification method |
Non-Patent Citations (4)
| Title |
|---|
| XINFENG ZHANG: "An improved tongue image segmentation algorithm based on Deeplabv3+ framework", 《IET IMAGE PROCESSING》 * |
| 杜建强: "基于图像分析的中医舌象分割与识别方法研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
| 杨刚: "典型缺陷局部放电超声信号的特征与模式识别方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 涂帅: "基于舌象分析的中医体质检测研究与实现", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115953392B (en) | 2023-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111985536B (en) | Based on weak supervised learning gastroscopic pathology image Classification method | |
| US10504624B2 (en) | System and method for segmentation and automated measurement of chronic wound images | |
| Jiang et al. | An automatic detection system of lung nodule based on multigroup patch-based deep learning network | |
| Gatos et al. | Temporal stability assessment in shear wave elasticity images validated by deep learning neural network for chronic liver disease fibrosis stage assessment | |
| Sameti et al. | Image feature extraction in the last screening mammograms prior to detection of breast cancer | |
| Pogorelov et al. | Bleeding detection in wireless capsule endoscopy videos—Color versus texture features | |
| JP2004209245A (en) | Method for extracting region of interest from image of tongue and method and apparatus for monitoring health using image of tongue | |
| Chatterjee et al. | Optimal selection of features using wavelet fractal descriptors and automatic correlation bias reduction for classifying skin lesions | |
| Kong et al. | Automated maxillofacial segmentation in panoramic dental x-ray images using an efficient encoder-decoder network | |
| CN112071418B (en) | Gastric cancer peritoneal metastasis prediction system and method based on enhanced CT image histology | |
| Biniaz et al. | Automatic reduction of wireless capsule endoscopy reviewing time based on factorization analysis | |
| Chakraborty et al. | Chronic wound characterization using bayesian classifier under telemedicine framework | |
| Mathew et al. | Transform based bleeding detection technique for endoscopic images | |
| Wang et al. | Reduction of bubble-like frames using a RSS filter in wireless capsule endoscopy video | |
| Gómez-Flores et al. | Texture analysis based on auto-mutual information for classifying breast lesions with ultrasound | |
| US20210209755A1 (en) | Automatic lesion border selection based on morphology and color features | |
| CN112419246A (en) | Depth detection network for quantifying esophageal mucosa IPCLs blood vessel morphological distribution | |
| CN115953392A (en) | Tongue body coating quality evaluation method based on artificial intelligence | |
| Arnold et al. | Indistinct frame detection in colonoscopy videos | |
| Zhuo et al. | Fine-needle aspiration biopsy evaluation-oriented thyroid carcinoma auxiliary diagnosis | |
| Li et al. | Contourlet-based features for computerized tumor detection in capsule endoscopy images | |
| CN113920071A (en) | New coronavirus image identification method based on convolutional neural network algorithm | |
| CN115937215A (en) | Body fluid analysis lichen texture method based on artificial intelligence | |
| Lynn et al. | Segmentation of skin lesion towards melanoma skin cancer classification | |
| Vijayalakshmi et al. | METHODOLOGY FOR IMPROVING DEEP LEARNING-BASED CLASSIFICATION FOR CT SCAN COVID-19 IMAGES |
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 |