CN102496026B - Tongue picture drawing method mixed with color and space information - Google Patents
Tongue picture drawing method mixed with color and space information Download PDFInfo
- Publication number
- CN102496026B CN102496026B CN 201110410830 CN201110410830A CN102496026B CN 102496026 B CN102496026 B CN 102496026B CN 201110410830 CN201110410830 CN 201110410830 CN 201110410830 A CN201110410830 A CN 201110410830A CN 102496026 B CN102496026 B CN 102496026B
- Authority
- CN
- China
- Prior art keywords
- tongue
- pixel
- target area
- color
- tongue picture
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
A tongue picture drawing method mixed with color and space information includes 1 utilizing a digital camera to right face the face, the teeth, the lips and the tongue body of a patient for photograph; 2 searching any starting pixel close to color harmony and brightness of a tongue picture in the pictures, enabling the starting pixel to serve as a target area and ordering the color harmony of adjacent pixels in the target area according to similarity; 3 selecting pixel having smallest color harmony characteristic difference with the target area according to above ordering results and adding the pixel into a data structure of the target area; and 4 repeating the above process till all the adjacent pixels satisfying the above constraint condition into the target area to achieve the effect that the final target area is an extracted tongue picture area. The method is high in accuracy, good in reliability, strong in practicability, low in cost and capable of quickly extracting furred tongue pictures and non-furred tongue pictures.
Description
Technical field
The present invention relates to a kind of Fusion of Color that can be automatically the tongue image be extracted from face, lip and tooth regions and the tongue picture extracting method of spatial information.
Background technology
Lingual diagnosis is the main research contents of observation of hoping in the traditional Chinese medical science four methods of diagnosis, hear, ask, hit, and is a kind of characteristic diagnostic method of the traditional Chinese medical science.Thereby the various features that traditional lingual diagnosis mainly relies on traditional Chinese medical science doctor to observe tongue picture are made judgement to patient's the state of an illness.Traditional lingual diagnosis not only relies on traditional Chinese medical science doctor's knowledge and experience, and the diagnostic result of lingual diagnosis also can be subjected to the interference of environmental factor, thereby has stronger subjectivity.Some researchers take the tongue image with digital camera, utilize computer image processing technology the feature of tongue picture to be carried out the detection of quantification.For tongue picture is detected, at first an important job extracts tongue picture exactly from face, lip and tooth regions, provides accurately, analyzes reliably foundation for follow-up quantification detects.At present, because the diversity of tongue picture, some tongue picture extracting method have the limitation of himself, can not well coated tongue be extracted.
Summary of the invention
Purpose of the present invention just provide a kind of accuracy height, good reliability, practical, cost is low, can extract the Fusion of Color of tongue and no tongue tongue picture and the tongue picture extracting method of spatial information.
The tongue picture extracting method of Fusion of Color of the present invention and spatial information, be a kind of employing color image processing, utilize color and the spatial information in tongue picture zone, under the guidance of greed rule, the maximum tongue body zone that search has the tongue picture feature in entire image the steps include:
1, utilizes digital camera to comprise that over against patient the tongue picture of face, tooth, lip and tongue body takes, be transferred on the computer taking the tongue image that comes out with data line then; 2, in image, seek any one initial pixel approaching with the hue and luminance feature of tongue picture, as the target area, then the tone with the target area adjacent pixels is sorted according to similarity, the method of ordering can adopt selects ordering, Straight Insertion Sort, bubble sorting or quicksort, recommends to adopt quicksort; 3, according to the pixel of result's selection of sorting previously with target area tone characteristics difference minimum, if this pixel satisfies the color constraint condition similar to the tone of target area, be that tone difference is less than setting threshold, perhaps satisfy the space constraints that tongue fur is surrounded by tongue nature, be the tongue fur pixel in that there are the tongue nature pixel in both sides or the left and right sides up and down, and this pixel satisfies the bigger brightness constraint condition of brightness, the brightness that is pixel exceeds preset threshold, then this pixel is joined in the target area and go, be about to this pixel and join in the data structure of target area; 4, repeat said process at last and all join in the target area up to all neighbors that satisfies above-mentioned constraint condition, the final objective zone is the tongue picture zone that extracts.
The tongue picture extracting method of Fusion of Color of the present invention and spatial information compared with prior art has following advantage:
1, this method can successfully extract tongue picture from the image that has tongue fur, has overcome the shortcoming that tongue picture extracting method in the past can not extract coated tongue;
2, this method is extracted the process of tongue picture, need not manual intervention, and whole leaching process is automatically finished, and is better than manual or semi-automatic method in the past;
3, this method can directly be handled colored tongue image, and the applicability of method is stronger, is better than the method for in the past extracting at gray level image;
4, this method utilizes human eye to the principle of color-aware, and color and spatial information in the comprehensive utilization original image extract tongue picture, and methodological science is reasonable, and result more accurately and reliably;
5, the software and hardware of this method employing is simple and reliable, has cost advantage.
Description of drawings
Fig. 1 is structure composition frame chart of the present invention;
Fig. 2 is system of the present invention main program flow chart.
Embodiment
The tongue picture extracting method of a kind of Fusion of Color and spatial information, the system that adopts comprises digital camera 1, data line 2, PC 3, take over against the tongue body that patient stretches out with digital camera, after original tongue picture is transferred to PC by data line, then extracting software by traditional Chinese medical science tongue picture calls original tongue picture file, and handle and to extract tongue body zone, i.e. tongue picture.
Hardware requirement is as follows in the system: digital camera adopts the above digital camera of 5,000,000 pixels, guarantees to have certain sharpness; PC adopts the above processor of PentiumIV 1.7G, more than the internal memory 256M, and the above free disk space of 2G at least.Software requirement in the system is as follows: operating system is Windows XP, and Software Development Platform is Visual C++ 6.0.Under the situation of above-mentioned minimalist configuration, the original image size of calling in the suggestion software is no more than 800 * 600.
The specific algorithm of the tongue picture extracting method of Fusion of Color and spatial information (adopting the SPARKS language description) is as follows:
procedure?GREEDY-TONGUE-EXTRACTION(S,?x)
// S is the target area, is initially sky.X represent the pixel that begins to search for //
Bool MeetConstraint // pixel satisfy the mark of constraint condition //
S←Φ;
If x brightness is higher, and tone and tongue nature approximate // brightness in tongue body zone must be in normal range //
then
S ← x} // initialization S//
end?if
S ' ← { x
i| Adjacent (x
i, S)=True} //S ' be S the set in abutting connection with pixel //
loop
MeetConstraint←False
While S ' is not empty and MeetConstraint=False
In S ', find one make HueSimilarity (x ', S) get peaked pixel x ' //HueSimilarity be used for to judge the tone similarity //
If (x ' to the comparatively similar or of S tone (x ' the approximate tongue fur pixel and x ' of tone be similar to the encirclement of tongue nature pixel)) and x ' brightness is higher // this pixel must satisfy tone, brightness and locus constraint condition //
then
MeetConstraint ← True; //x ' for satisfy the pixel of constraint condition //
S ← S ∪ { x ' } // with x ' add the target area //
S ' ← S '-{ x ' } // with x ' deletion from the set of pixel on every side //
S ' ← S ' ∪ { x
i| Adjacent (x
i, x ' })=True and x
i S} // x ' pixel is on every side joined among the S '
The current circulation of exit // withdraw from //
else
S ' ← S '-{ x ' } // with x ' deletion from pixel collection on every side //
end?if
repeat
until?MeetConstraint=False?repeat
end?GREEDY-TONGUE-EXTRACTION。
Claims (2)
1. the tongue picture extracting method of a Fusion of Color and spatial information, it is characterized in that: it may further comprise the steps:
(1), utilize digital camera to comprise that over against patient the tongue picture of face, tooth, lip and tongue body takes, be transferred on the computer taking the tongue image that comes out with data line then;
(2), in image, seek any one initial pixel approaching with the hue and luminance feature of tongue picture, as the target area, then the tone with the target area adjacent pixels is sorted according to similarity;
(3), according to the pixel of result's selection of sorting previously with target area tone characteristics difference minimum, if this pixel satisfies the color constraint condition similar to the tone of target area, be that tone difference is less than setting threshold, perhaps satisfy the space constraints that tongue fur is surrounded by tongue nature, be the tongue fur pixel in that there are the tongue nature pixel in both sides or the left and right sides up and down, and this pixel satisfies the bigger brightness constraint condition of brightness, the brightness that is pixel exceeds preset threshold, then this pixel is joined in the target area and go, be about to this pixel and join in the data structure of target area;
(4), at last repeat said process and all join in the target area up to all neighbors that satisfies above-mentioned constraint condition, the final objective zone is the tongue picture zone that extracts.
2. the tongue picture extracting method of a kind of Fusion of Color according to claim 1 and spatial information is characterized in that: the method for described ordering adopts selects a kind of in ordering, Straight Insertion Sort, bubble sorting, the quicksort, preferred quicksort.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201110410830 CN102496026B (en) | 2011-12-12 | 2011-12-12 | Tongue picture drawing method mixed with color and space information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201110410830 CN102496026B (en) | 2011-12-12 | 2011-12-12 | Tongue picture drawing method mixed with color and space information |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102496026A CN102496026A (en) | 2012-06-13 |
CN102496026B true CN102496026B (en) | 2013-07-17 |
Family
ID=46187851
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN 201110410830 Expired - Fee Related CN102496026B (en) | 2011-12-12 | 2011-12-12 | Tongue picture drawing method mixed with color and space information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102496026B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109615628B (en) * | 2018-12-24 | 2023-06-02 | 上海合参智能医疗科技有限公司 | Tongue picture image evaluation method |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1759804A (en) * | 2005-11-02 | 2006-04-19 | 浙江大学 | Intelligent analyzing and differentiating method of herbalist doctor through integrated references form four parts of diagnosis |
CN1804867A (en) * | 2006-01-19 | 2006-07-19 | 上海交通大学 | Method for extracting tongue body from tongue images |
-
2011
- 2011-12-12 CN CN 201110410830 patent/CN102496026B/en not_active Expired - Fee Related
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1759804A (en) * | 2005-11-02 | 2006-04-19 | 浙江大学 | Intelligent analyzing and differentiating method of herbalist doctor through integrated references form four parts of diagnosis |
CN1804867A (en) * | 2006-01-19 | 2006-07-19 | 上海交通大学 | Method for extracting tongue body from tongue images |
Also Published As
Publication number | Publication date |
---|---|
CN102496026A (en) | 2012-06-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6312714B2 (en) | Multispectral imaging system for shadow detection and attenuation | |
CN103020585B (en) | A kind of immuning tissue's positive cell and negative cells recognition methods | |
US9014467B2 (en) | Image processing method and image processing device | |
JP5988119B2 (en) | Backlight detection method and device | |
CN110276366A (en) | Carry out test object using Weakly supervised model | |
CN107832677A (en) | Face identification method and system based on In vivo detection | |
CN105103189A (en) | Near infrared guided image denoising | |
CN101601287A (en) | Produce the equipment and the method for photorealistic image thumbnails | |
WO2012122682A1 (en) | Method for calculating image visual saliency based on color histogram and overall contrast | |
Rossi et al. | FishAPP: A mobile App to detect fish falsification through image processing and machine learning techniques | |
CN112307853A (en) | Detection method of aerial image, storage medium and electronic device | |
CN107622497A (en) | Image cropping method, apparatus, computer-readable recording medium and computer equipment | |
Wang et al. | Towards a kinect-based behavior recognition and analysis system for small animals | |
CN115147936A (en) | Living body detection method, electronic device, storage medium, and program product | |
CN111666911A (en) | Micro-expression data expansion method and device | |
KR101344851B1 (en) | Device and Method for Processing Image | |
EP2904546B1 (en) | Method and apparatus for ambient lighting color determination | |
CN102496026B (en) | Tongue picture drawing method mixed with color and space information | |
CN109191398A (en) | Image processing method, device, computer readable storage medium and electronic equipment | |
CN108682021A (en) | Rapid hand tracking, device, terminal and storage medium | |
CN110852172B (en) | Method for expanding crowd counting data set based on Cycle Gan picture collage and enhancement | |
JP7375901B2 (en) | Display device, display method, program and image projection system | |
US20060010582A1 (en) | Chin detecting method, chin detecting system and chin detecting program for a chin of a human face | |
Lanillos et al. | Multisensory 3D saliency for artficial attention systems | |
US8538142B2 (en) | Face-detection processing methods, image processing devices, and articles of manufacture |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20130717 Termination date: 20171212 |
|
CF01 | Termination of patent right due to non-payment of annual fee |