CN110473191A - A kind of erythema recognition methods - Google Patents
A kind of erythema recognition methods Download PDFInfo
- Publication number
- CN110473191A CN110473191A CN201910735417.5A CN201910735417A CN110473191A CN 110473191 A CN110473191 A CN 110473191A CN 201910735417 A CN201910735417 A CN 201910735417A CN 110473191 A CN110473191 A CN 110473191A
- Authority
- CN
- China
- Prior art keywords
- image
- erythema
- recognition methods
- component
- obtains
- 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
- 206010015150 Erythema Diseases 0.000 title claims abstract description 33
- 231100000321 erythema Toxicity 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000001514 detection method Methods 0.000 claims abstract description 5
- 230000003628 erosive effect Effects 0.000 claims abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000007689 inspection Methods 0.000 abstract description 4
- 208000020061 Hand, Foot and Mouth Disease Diseases 0.000 description 5
- 208000025713 Hand-foot-and-mouth disease Diseases 0.000 description 5
- 206010011409 Cross infection Diseases 0.000 description 2
- 206010029803 Nosocomial infection Diseases 0.000 description 2
- 239000012141 concentrate Substances 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 208000035473 Communicable disease Diseases 0.000 description 1
- 241000709661 Enterovirus Species 0.000 description 1
- 208000009525 Myocarditis Diseases 0.000 description 1
- 206010037423 Pulmonary oedema Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 206010014599 encephalitis Diseases 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 201000011475 meningoencephalitis Diseases 0.000 description 1
- 210000000214 mouth Anatomy 0.000 description 1
- 208000005333 pulmonary edema Diseases 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30088—Skin; Dermal
Abstract
The invention discloses a kind of erythema recognition methods comprising the steps of: A, obtains image；B, hand region detection is carried out to image, obtains hand region；C, the hand region rgb image data collected is converted into HSV image data；D, the threshold value of chrominance component H and saturation degree component S are set；E, according to the threshold process image pixel of setting, the binary image in doubtful erythema region is obtained；F, denoising is carried out to binary image, then carries out erosion operation, obtains new binary image；G, Connected area disposal$ is done to new binary image, obtains multiple connected domains；H, non-erythema connected domain is filtered according to connected component, to obtain erythema region, the present invention utilizes image recognition technology, inspection, judgement by image to garden, the children's progress hand erythema for entering school is entered, avoid the period for entering garden in children, entering school, it is difficult to and garden is entered to each, enters the problem of children in school go through, are easy to appear careless omission.
Description
Technical field
The present invention relates to medical detection technology, specifically a kind of erythema recognition methods.
Background technique
Hand-foot-and-mouth disease is the infectious disease being caused by enterovirus, and mostly occurs in 5 years old or less children, can cause hand, foot, oral cavity
The erythema at equal positions, a small number of infants can cause the complication such as myocarditis, pulmonary edema, aseptic meningoencephalitis.Individual children with serious disease
If progression of the disease is fast, lead to death.Hand-foot-and-mouth disease has infectiousness, in places such as kindergarten, the schools that children concentrate, is easy
Cross-infection, therefore children's progress hand-foot-and-mouth disease inspection and preliminary judgement to entering garden, entering school occurs, prevents doubtful hand-foot-and-mouth disease
Children enter garden, enter school and just become the main means to guard against cross infection.
Since an obvious characteristic at hand-foot-and-mouth disease initial stage is exactly long erythema on hand, fields such as kindergarten, school at present
Generallyd use manual type, arrange school physician and teacher according on hand whether long erythema, brothers are carried out to the children for entering garden, entering school
Stomatosis inspection and preliminary judgement, but there is low efficiency in the mode for manually checking and judging, can greatly increase school physician and religion
The workload of teacher, in the period that children enter garden, enter school, due to more than children and parent's number and personnel concentrate, kindergarten and school
Be difficult to garden is entered to each, the children that enter school go through, be extremely easy to appear careless omission.
Summary of the invention
The purpose of the present invention is to provide a kind of erythema recognition methods, to solve the problems mentioned in the above background technology.
To achieve the above object, the invention provides the following technical scheme:
A kind of erythema recognition methods comprising the steps of:
A, image is obtained；
B, hand region detection is carried out to image, obtains hand region；
C, the hand region rgb image data collected is converted into HSV image data；
D, the threshold value of chrominance component H and saturation degree component S are set；
E, according to the threshold process image pixel of setting, the binary image in doubtful erythema region is obtained；
F, denoising is carried out to binary image, then carries out erosion operation, obtains new binary image；
G, Connected area disposal$ is done to new binary image, obtains multiple connected domains；
H, non-erythema connected domain is filtered according to connected component, to obtain erythema region.
As further technical solution of the present invention: the mode that image is obtained in the step A is set by image capture
Standby acquisition, or transmitted by data and receive or read from storage device.
As further technical solution of the present invention: the step A also needs to carry out image drop to image after obtaining image
It makes an uproar pretreatment.
As further technical solution of the present invention: the denoising of the step F uses opening operation method.
As further technical solution of the present invention: the connected component of the step H includes size, extensibility
And/or circle.
As further technical solution of the present invention: the step D is specifically included: the max-thresholds of setting chrominance component H
The max-thresholds Smax and minimum threshold Smin of Hmax and minimum threshold Hmin and saturation degree component S.
As further technical solution of the present invention: according to the mark of the threshold process image pixel of setting in the step E
It is quasi- as follows: if the chrominance component H' of image pixel meets Hmin < H' < Hmax, and saturation degree component S' meet Smin < H' <
Smax then makes the pixel value of the image pixel be equal to 255；Otherwise, it is equal to the pixel value of the image pixel.
Compared with prior art, the beneficial effects of the present invention are: erythema recognition methods of the present invention utilizes image recognition technology,
Inspection, judgement by image to garden, the children's progress hand erythema for entering school is entered, identify children on hand with erythema, phase
Than greatly improving the efficiency in manual type, the workload of school physician and teacher are reduced, is avoided and is entered garden in children, enters school
Period, it is difficult to accomplish to enter each garden, enter the problem of children in school go through, are easy to appear careless omission.
Detailed description of the invention
Fig. 1 is flow chart of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Embodiment 1: referring to Fig. 1, a kind of erythema recognition methods comprising the steps of:
A, it is acquired by image capture device, or is transmitted data and receive or obtained by way of being read in storage device
Take image；And image noise reduction pretreatment is carried out to image；
B, hand region detection is carried out to image, obtains hand region；
C, the hand region rgb image data collected is converted into HSV image data；
D, the threshold value of chrominance component H and saturation degree component S are set；The max-thresholds Hmax and minimum of chrominance component H are set
The max-thresholds Smax and minimum threshold Smin of threshold value Hmin and saturation degree component S.
E, according to the threshold process image pixel of setting, the binary image in doubtful erythema region is obtained；
F, denoising is carried out to binary image using opening operation method, then carries out erosion operation, obtains new two-value
Change image；
G, Connected area disposal$ is done to new binary image, obtains multiple connected domains；
H, non-erythema connected domain is filtered according to connected component, to obtain erythema region.Wherein, connected component includes
Size, extensibility and/or circle.
Embodiment 2, on the basis of embodiment 1, in step E such as according to the standard of the threshold process image pixel of setting
Under: if the chrominance component H' of image pixel meets Hmin < H' < Hmax, and saturation degree component S' meets Smin < H' < Smax, then
The pixel value of the image pixel is set to be equal to 255；Otherwise, it is equal to the pixel value of the image pixel.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included within the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiments being understood that.
Claims (7)
1. a kind of erythema recognition methods, which is characterized in that comprise the steps of:
A, image is obtained；
B, hand region detection is carried out to image, obtains hand region；
C, the hand region rgb image data collected is converted into HSV image data；
D, the threshold value of chrominance component H and saturation degree component S are set；
E, according to the threshold process image pixel of setting, the binary image in doubtful erythema region is obtained；
F, denoising is carried out to binary image, then carries out erosion operation, obtains new binary image；
G, Connected area disposal$ is done to new binary image, obtains multiple connected domains；
H, non-erythema connected domain is filtered according to connected component, to obtain erythema region.
2. a kind of erythema recognition methods according to claim 1, which is characterized in that obtain the side of image in the step A
Formula is to be acquired by image capture device, or transmitted by data and receive or read from storage device.
3. a kind of erythema recognition methods according to claim 1, which is characterized in that the step A is also needed after obtaining image
Image noise reduction pretreatment is carried out to image.
4. a kind of erythema recognition methods according to claim 1, which is characterized in that the denoising of the step F uses
Opening operation method.
5. a kind of erythema recognition methods according to claim 1, which is characterized in that the connected component packet of the step H
Include size, extensibility and/or circle.
6. a kind of erythema recognition methods according to claim 1, which is characterized in that the step D is specifically included: setting color
Adjust the max-thresholds Hmax and minimum threshold Hmin of component H and the max-thresholds Smax and minimum threshold of saturation degree component S
Smin。
7. -6 any a kind of erythema recognition methods according to claim 1, which is characterized in that basis is set in the step E
The standard for the threshold process image pixel set is as follows: if the chrominance component H' of image pixel meets Hmin < H' < Hmax, and satisfying
Meet Smin < H' < Smax with degree component S', then the pixel value of the image pixel is made to be equal to 255；Otherwise, make the image pixel
Pixel value is equal to 0.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910735417.5A CN110473191A (en) | 2019-08-09 | 2019-08-09 | A kind of erythema recognition methods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910735417.5A CN110473191A (en) | 2019-08-09 | 2019-08-09 | A kind of erythema recognition methods |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110473191A true CN110473191A (en) | 2019-11-19 |
Family
ID=68510434
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910735417.5A Pending CN110473191A (en) | 2019-08-09 | 2019-08-09 | A kind of erythema recognition methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110473191A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111242936A (en) * | 2020-01-17 | 2020-06-05 | 苏州瓴图智能科技有限公司 | Non-contact palm herpes detection device and method based on image |
| CN111986378A (en) * | 2020-07-30 | 2020-11-24 | 湖南长城信息金融设备有限责任公司 | Bill color fiber yarn detection method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100158363A1 (en) * | 2008-12-19 | 2010-06-24 | Qualcomm Incorporated | System and method to detect skin color in an image |
| WO2017092431A1 (en) * | 2015-12-01 | 2017-06-08 | 乐视控股（北京）有限公司 | Human hand detection method and device based on skin colour |
| CN110097510A (en) * | 2019-04-11 | 2019-08-06 | 平安科技（深圳）有限公司 | A kind of pure color flower recognition methods, device and storage medium |
-
2019
- 2019-08-09 CN CN201910735417.5A patent/CN110473191A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100158363A1 (en) * | 2008-12-19 | 2010-06-24 | Qualcomm Incorporated | System and method to detect skin color in an image |
| WO2017092431A1 (en) * | 2015-12-01 | 2017-06-08 | 乐视控股（北京）有限公司 | Human hand detection method and device based on skin colour |
| CN110097510A (en) * | 2019-04-11 | 2019-08-06 | 平安科技（深圳）有限公司 | A kind of pure color flower recognition methods, device and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111242936A (en) * | 2020-01-17 | 2020-06-05 | 苏州瓴图智能科技有限公司 | Non-contact palm herpes detection device and method based on image |
| CN111986378A (en) * | 2020-07-30 | 2020-11-24 | 湖南长城信息金融设备有限责任公司 | Bill color fiber yarn detection method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110473191A (en) | A kind of erythema recognition methods | |
| WO2022110712A1 (en) | Image enhancement method and apparatus, electronic device and computer readable storage medium | |
| NO20082843L (en) | Procedure for the detection of head degenerative disease, and corresponding seeding program and detector | |
| TW201101842A (en) | Dynamic image compression method for human face detection | |
| CN103402117A (en) | Method for detecting color cast of video image based on Lab chrominance space | |
| CN103808265A (en) | Method, device and system for measuring oilseed rape laminae and forms of sclerotium scabs synchronously | |
| US20200320743A1 (en) | Method and apparatus for processing image | |
| CN106022205A (en) | Image processing apparatus and image processing method | |
| CN113537057A (en) | Facial acupuncture point automatic positioning detection system and method based on improved cycleGAN | |
| CN108416782A (en) | View-based access control model identifies and the tobacco leaf ranking method and system of illumination correction | |
| CN206558009U (en) | A kind of instructional device of English Translation | |
| CN104036459A (en) | Local tone mapping method capable of reproducing sense of reality of image | |
| CN204392394U (en) | A kind of amplification processor for camera high definition picture | |
| CN108198156B (en) | Crop leaf image enhancement method and device | |
| CN104102901B (en) | High-precision fingerprint identification system | |
| CN106447627A (en) | Image processing method and apparatus | |
| CN103020910A (en) | Retina feature point enhancing method based on anisotropy and isotropy | |
| CN107736868A (en) | A kind of method for aiding in understanding patient's Er Nei state of an illness | |
| US20230363644A1 (en) | Oral cavity detection method, oral cavity detection device, and computer-readable storage medium | |
| CN108230405A (en) | Image white balancing treatment method based on gray processing | |
| Bellina et al. | The first description of how to take a picture from the microscope with an m-phone | |
| CN204189175U (en) | Based on the fingerprint recognition system of the asymmetric trigger circuit of emitter-base bandgap grading manifold type | |
| Mattson | Constructing the computer-rated Face Stimulus Assessment-Revised (FSA-R) to assess formal elements of Major Depressive Disorder (MDD) | |
| DI MAIO | Ode laica per Chibok e Leah | |
| Dongsheng et al. | Differences between Sidney Shapiro and Howard Goldblatt: A Perspective of Institutionalized Translator’s Behavior |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200515 Address after: Room 2803, building T2, Shenye Shangcheng (South District), No. 5001, Huanggang Road, Lianhua village, Huafu street, Futian District, Shenzhen City, Guangdong Province Applicant after: Shenzhen Sanbao innovation robot Co.,Ltd. Address before: 518055 Guangdong 28, Shenzhen, Futian District, Huafu street, No. 5001 Huanggang Road, Shenzhen Industrial upper city (two phase of the Southern District) Applicant before: Shenzhen Sanbao Innovation Intelligence Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191119 |