CN109009132A - A kind of jaundice monitoring method and device - Google Patents

A kind of jaundice monitoring method and device Download PDF

Info

Publication number
CN109009132A
CN109009132A CN201810744772.4A CN201810744772A CN109009132A CN 109009132 A CN109009132 A CN 109009132A CN 201810744772 A CN201810744772 A CN 201810744772A CN 109009132 A CN109009132 A CN 109009132A
Authority
CN
China
Prior art keywords
jaundice
image
monitor value
sample
skin
Prior art date
Application number
CN201810744772.4A
Other languages
Chinese (zh)
Inventor
衣祝松
于越
Original Assignee
京东方科技集团股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 京东方科技集团股份有限公司 filed Critical 京东方科技集团股份有限公司
Priority to CN201810744772.4A priority Critical patent/CN109009132A/en
Publication of CN109009132A publication Critical patent/CN109009132A/en

Links

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/103Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/1032Determining colour for diagnostic purposes
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/0059Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
    • A61B5/0077Devices for viewing the surface of the body, e.g. camera, magnifying lens

Abstract

The present invention provides a kind of jaundice monitoring method and devices.Applied to server, which comprises receive the skin image of the uncalibrated image that Image Acquisition terminal is sent and monitoring object;Jaundice monitor value is determined according to the jaundice prediction model that the uncalibrated image, the skin image and preparatory training obtain;The jaundice monitor value is fed back into described image acquisition terminal.The embodiment of the present invention is that real-time monitoring icterus neonatorum symptom is provided convenience, and provides support for the real-time diagnosis decision of doctor, ensure that neonatal health and lives.

Description

A kind of jaundice monitoring method and device
Technical field
The present invention relates to field of computer technology, more particularly to a kind of jaundice monitoring method and device.
Background technique
Jaundice is neonatal common sympton and sign, causes bilirubin concentration liter in serum by bilirubin metabolism obstacle Caused by height.If be not treated in time, it will lead to Infection of Central Nervous System in Newborn Infants and be damaged, generate bilirubin encephalopathy, concurrent nuclear icterus Or brain tissue damage, seriously threaten Neonatal Health and life.
The method of existing monitoring jaundice has: 1) from infant femoral vein venous blood samples, this method is unable to real-time perfoming prison Control, and infant skin is had damage, increase the chance of bleeding and infection;2) Skin icterus tester, existing hand-held warp are used Beijing opera subcutaneous ulcer instrument needs manual operation when measuring, and cannot achieve for the jaundice infant for needing moment concern bilirubin concentration value dynamic State monitoring.
Summary of the invention
The present invention provides a kind of jaundice monitoring method and device, is unable to real-time monitoring to solve existing jaundice monitoring method Problem.
To solve the above-mentioned problems, the invention discloses a kind of jaundice monitoring methods, are applied to server, the method packet It includes:
Receive the skin image of the uncalibrated image that Image Acquisition terminal is sent and monitoring object;
Determine that jaundice monitors according to the jaundice prediction model that the uncalibrated image, the skin image and preparatory training obtain Value;
The jaundice monitor value is fed back into described image acquisition terminal.
Optionally, mould is predicted in the jaundice obtained according to the uncalibrated image, the skin image and preparatory training Before type determines jaundice monitor value, the method also includes:
Sample set is obtained, wherein each sample of the sample set is labelled with coloration, saturation degree, lightness and jaundice sample value;
The jaundice prediction model is obtained according to the sample set and regression algorithm training.
Optionally, mould is predicted in the jaundice obtained according to the uncalibrated image, the skin image and preparatory training After type determines jaundice monitor value, the method also includes:
New samples are generated according to the skin image and the jaundice monitor value;
The new samples are added in the sample set.
Optionally, the jaundice prediction model obtained according to the uncalibrated image, the skin image and preparatory training Determine jaundice monitor value, comprising:
Color gain is determined according to the uncalibrated image;
The standard color of the skin image is determined according to the color gain and the skin image;
The jaundice monitor value is determined according to the standard color and the jaundice prediction model.
The embodiment of the present invention also provides a kind of jaundice monitoring method, is applied to Image Acquisition terminal, which comprises
Acquire the skin image of uncalibrated image and monitoring object;
The uncalibrated image and the skin image are sent to server, so that the server is according to the calibration maps The jaundice prediction model that picture, the skin image and preparatory training obtain determines jaundice monitor value;
Receive the jaundice monitor value of the server feedback;
Show the jaundice monitor value.
The embodiment of the present invention also provides a kind of jaundice monitoring device, is deployed in server, and described device includes:
Image receiver module, for receiving the uncalibrated image of Image Acquisition terminal transmission and the skin image of monitoring object;
Jaundice monitor value determining module, for what is obtained according to the uncalibrated image, the skin image and training in advance Jaundice prediction model determines jaundice monitor value;
Jaundice detected value feedback module, for the jaundice monitor value to be fed back to described image acquisition terminal.
Optionally, before the jaundice monitor value determining module, described device further include:
Sample set obtains module, for obtaining sample set, wherein each sample of the sample set is labelled with coloration, saturation Degree, lightness and jaundice sample value;
Model training module, for obtaining the jaundice prediction model according to the sample set and regression algorithm training.
Optionally, after the jaundice monitor value determining module, described device further include:
Sample generation module, for generating new samples according to the skin image and the jaundice monitor value;
Swatch addition module, for the new samples to be added in the sample set.
Optionally, the jaundice monitor value determining module includes:
Color gain determines submodule, for determining color gain according to the uncalibrated image;
Standard color determines submodule, for determining the skin image according to the color gain and the skin image Standard color;
Jaundice monitor value determines submodule, for determining the Huang according to the standard color and the jaundice prediction model Subcutaneous ulcer monitor value.
The embodiment of the present invention also provides a kind of jaundice monitoring device, is deployed in Image Acquisition terminal, and described device includes:
Image capture module, for acquiring the skin image of uncalibrated image and monitoring object;
Image sending module, for the uncalibrated image and the skin image to be sent to server, so that the clothes Business device determines jaundice monitor value according to the jaundice prediction model that the uncalibrated image, the skin image and preparatory training obtain;
Jaundice monitor value receiving module, for receiving the jaundice monitor value of the server feedback;
Display module, for showing the jaundice monitor value.
Compared with prior art, the present invention includes the following advantages:
Server receives the skin image of the uncalibrated image that Image Acquisition terminal is sent and monitoring object;According to calibration maps The jaundice prediction model that picture, skin image and preparatory training obtain determines jaundice monitor value;Jaundice monitor value is fed back into image Acquisition terminal, so that Image Acquisition terminal can check jaundice monitor value.The embodiment of the present invention is real-time monitoring icterus neonatorum Symptom is provided convenience, and is provided support for the real-time diagnosis decision of doctor, be ensure that neonatal health and lives.
Detailed description of the invention
Fig. 1 shows a kind of step flow chart of jaundice monitoring method of the embodiment of the present invention one;
Fig. 2 shows a kind of step flow charts of jaundice monitoring method of the embodiment of the present invention two;
Fig. 3 shows a kind of structural block diagram of jaundice monitoring device of the embodiment of the present invention three;
Fig. 4 shows a kind of structural block diagram of jaundice monitoring device of the embodiment of the present invention four.
Specific embodiment
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, with reference to the accompanying drawing and specific real Applying mode, the present invention is described in further detail.
Embodiment one
Referring to Fig.1, a kind of step flow chart of jaundice monitoring method provided in an embodiment of the present invention is shown.Applied to clothes Business device, which comprises
Step 101, the skin image of the uncalibrated image that Image Acquisition terminal is sent and monitoring object is received.
In the present embodiment, by the skin image of Image Acquisition terminal acquisition uncalibrated image and monitoring object.For example, passing through shifting The local skin of camera shooting the white calibration card and infant of dynamic terminal, gets the skin figure of uncalibrated image and monitoring object Picture.Uncalibrated image and skin image are sent to server by Image Acquisition terminal, and server receives what Image Acquisition terminal was sent Uncalibrated image and skin image.The embodiment of the present invention does not make the sending method of Image Acquisition terminal and the reception mode of server It limits, can be configured according to the actual situation in detail.
Image Acquisition terminal due to sending uncalibrated image and skin image may have multiple, and server can be with centralized control The working condition of these Image Acquisition terminals and image acquisition period etc., convenient for the unified management of multiple images acquisition terminal.
Step 102, it is determined according to the jaundice prediction model that the uncalibrated image, the skin image and preparatory training obtain Jaundice monitor value.
In the present embodiment, server trains jaundice prediction model in advance, specifically may include steps of:
Sub-step one obtains sample set, wherein each sample of the sample set is labelled with coloration, saturation degree, lightness and Huang Subcutaneous ulcer sample value.Shown in sample set table specific as follows:
Constant Coloration (HUE) It is saturated (SATURATION) Lightness (VALUE) Jaundice sample value (μm ol/L)
1 60 100 100 80
1 65 110 170 200
1 70 120 166 154
1 61 109 142 222
1 90 130 129 154
1 86 102 143 111
Sub-step two obtains the jaundice prediction model according to the sample set and regression algorithm training.
Specifically, regression coefficient ω, ω=(X are determined using regression algorithmTX)-1XTY, wherein coloration, saturation degree, lightness For X, jaundice sample value is Y.It, can be true according to the Xp and regression coefficient ω of the skin image received after determining regression coefficient ω Determine jaundice monitor value Yp, Yp=Xp* ω.
Before determining jaundice monitor value according to skin image, need to carry out color correct to skin image.Specifically, according to The uncalibrated image determines color gain;The standard face of the skin image is determined according to the color gain and the skin image Color.For example, the uncalibrated image of Image Acquisition end acquisition white calibration card and the skin image of infant, choose 64* from uncalibrated image The RGB data of 64 pixels, (Rca, Gca, Bca) be by colour temperature influence uncalibrated image RGB actual value, (Rs Gs Bs) it is the mark influenced without colour temperature Determine the RGB theoretical value of image, therefore, it is R that color gain can be calculated according to RGB actual value and RGB theoretical valuegain=Rs/ Rca, Rgain=Rs/Rca, Rgain=Rs/Rca.The RGB data of 64*64 pixel is chosen from skin image, According to color gain The standard color that can determine skin image is (Rreal, Greal, Breal), wherein Rreal=Rta*Rgain, Rreal=Rta*Rgain, Rreal=Rta*Rgain.HSV (Hue, Saturation, Value, hexagonal pyramid model) is calculated according to the rgb value of standard color Value (Hreal, Sreal, Vreal).
Max=Max [R, G, B]
Min=Min [R, C, B]
V=max
Sub-step three determines the jaundice monitor value according to the standard color and the jaundice prediction model.
Specifically, [1 Hreal Sreal Vreal] vector is substituted into formula Yp=Xp* ω as Xp, obtains jaundice Monitor value Yp.
Optionally, new samples are generated according to the skin image and the jaundice monitor value;The new samples are added to In the sample set.
For example, obtaining Xp according to skin image, wherein Xp corresponds to vector [1 Hreal Sreal Vreal], by Xp and Huang Subcutaneous ulcer monitor value Yp generates new samples, and then new samples are added in sample set.When server receives a large amount of uncalibrated image When with skin image, a large amount of new samples can be generated according to the skin image received, on the one hand, can enrich in sample set Sample, and then for statistical analysis to jaundice phenomenon according to sample, finding out influences the influence factor that icterus neonatorum generates, such as Local climate influence, parent diet difference, inherent cause etc. provide some precautionary measures in advance.It on the other hand, can also be to skin After skin image and amendment the standard color of skin image is saved, by the image after preservation as stage Analysis decision according to According to, and the basic data of medical development is pushed in the future.
Step 103, the jaundice monitor value is fed back into described image acquisition terminal.
In the present embodiment, after server determines jaundice monitor value, jaundice monitor value is fed back into Image Acquisition terminal, so as to Image Acquisition terminal is shown or is inquired, and real-time monitoring icterus neonatorum symptom is realized, and is determined for the real-time diagnosis of doctor Plan provides support.
Server can also pre-establish the corresponding relationship of monitoring object and Image Acquisition terminal, according to the Huang of monitoring object The information inspection permission of Image Acquisition terminal is arranged in subcutaneous ulcer monitor value, feeds back Huang to Image Acquisition terminal further according to information inspection permission Subcutaneous ulcer monitor value.The period correspondence image acquisition terminal 1 and 2 for example, newborn A is hospitalized, when the jaundice monitor value of newborn A is beyond peace When full threshold value, the information inspection permission of Image Acquisition terminal 1 and 2 is disposed as allowing to check, server is by the Huang of newborn A Subcutaneous ulcer monitor value feeds back to Image Acquisition terminal 1 and 2.It is newborn when newborn A leaves hospital but jaundice monitor value still exceeds secure threshold Youngster A is only corresponding with Image Acquisition terminal 2, and the information inspection priority assignation of Image Acquisition terminal 2 is allowed to check by server, and The jaundice monitor value of newborn A is fed back into Image Acquisition terminal 2.When neonatal B discharge and jaundice monitor value is without departing from peace It is not allow to check by the information inspection priority assignation of Image Acquisition terminal 2, server is not to Image Acquisition terminal when full threshold value 2 feedback jaundice monitor values.The embodiment of the present invention does not limit information inspection permission in detail, can be set according to the actual situation It sets.
In conclusion server receives the uncalibrated image that Image Acquisition terminal is sent and monitoring pair in the embodiment of the present invention The skin image of elephant;Jaundice monitor value is determined according to the jaundice prediction model that uncalibrated image, skin image and preparatory training obtain; Jaundice monitor value is fed back into Image Acquisition terminal, Image Acquisition terminal can check jaundice monitor value.The embodiment of the present invention is Real-time monitoring icterus neonatorum symptom is provided convenience, and is provided support for the real-time diagnosis decision of doctor, be ensure that neonatal Health and lives.
Embodiment two
Referring to Fig. 3, shows the embodiment of the present invention and a kind of step flow chart of jaundice monitoring method is provided.Applied to image Acquisition terminal, which comprises
Step 201, the skin image of uncalibrated image and monitoring object is acquired.
In the present embodiment, Image Acquisition terminal be can be set on the infanette of hospital, also can be set in newborn family In infanette on, mobile terminal can also be used.When acquiring uncalibrated image, white calibration card can be shot by camera, White infanette can also be shot.When acquiring the skin image of monitoring object, the infant skin of designated position can be shot.Acquisition Two different cameras can be used in uncalibrated image and skin image, and same camera also can be used.Acquire uncalibrated image It can be controlled, can also be configured by the user of Image Acquisition terminal by server with the period of skin image.The present invention is real It applies example not limit the set-up mode of Image Acquisition terminal, Image Acquisition mode, image acquisition period etc. in detail, Ke Yigen It is configured according to actual conditions.
Step 202, the uncalibrated image and the skin image are sent to server, so that the server is according to institute It states uncalibrated image, the skin image and trains obtained jaundice prediction model to determine jaundice monitor value in advance.
In the present embodiment, after collecting uncalibrated image and skin image, uncalibrated image and skin image are sent to service Device.Specifically, WIFI (WIreless-FIdelity is wirelessly connected) module that can be used in Image Acquisition terminal sends mark Determine image and skin image.If Image Acquisition terminal is mobile terminal, it is yellow that monitoring can also be installed in advance in the terminal The APP (Application, application program) of subcutaneous ulcer, is uploaded to server for uncalibrated image and skin image by APP.Monitoring is yellow The APP of subcutaneous ulcer not only has image collecting function, can also have the function of that user management, information are shown, the embodiment of the present invention pair This is not limited in detail, can be configured according to the actual situation.
Step 203, the jaundice monitor value of the server feedback is received.
In the present embodiment, when server feedback jaundice monitor value, the jaundice monitor value of server feedback is received.The present invention Embodiment does not limit recipient's formula in detail, can be configured according to the actual situation.
Step 204, the jaundice monitor value is shown.
In the present embodiment, when Image Acquisition terminal is arranged within the hospital, jaundice monitoring can be shown using electronic ink screen Value.Electronic ink screen has the advantages that readable, flexible, easily cheap manufacture and low-power consumption.
Control module can also be set in Image Acquisition terminal, such as SOC (System on Chip, system level chip), CPU (Central Processing Unit, central processing unit), by SOC or CPU control image acquisition terminal acquire image, Send image, receive jaundice monitor value, display jaundice monitor value etc..The embodiment of the present invention does not limit this in detail, Ke Yigen It is configured according to actual conditions.
In conclusion Image Acquisition terminal acquires the skin image of uncalibrated image and monitoring object in the embodiment of the present invention; Uncalibrated image and skin image are sent to server, server is true according to uncalibrated image, skin image and jaundice prediction model Determine jaundice monitor value, Image Acquisition terminal receives the jaundice monitor value of server feedback and shown.The present invention is implemented Example is that real-time monitoring icterus neonatorum symptom is provided convenience, and provides support for the real-time diagnosis decision of doctor, ensure that new life The health and lives of youngster.
Embodiment three
Referring to Fig. 3, a kind of structural block diagram of jaundice monitoring device provided in an embodiment of the present invention is shown.It is deployed in service Device, described device include:
Image receiver module 301, for receiving the uncalibrated image of Image Acquisition terminal transmission and the skin figure of monitoring object Picture;
Jaundice monitor value determining module 302, for being obtained according to the uncalibrated image, the skin image and training in advance Jaundice prediction model determine jaundice monitor value;
Jaundice detected value feedback module 303, for the jaundice monitor value to be fed back to described image acquisition terminal.
Optionally, before the jaundice monitor value determining module 302, described device further include:
Sample set obtains module, for obtaining sample set, wherein each sample of the sample set is labelled with coloration, saturation Degree, lightness and jaundice sample value;
Model training module, for obtaining the jaundice prediction model according to the sample set and regression algorithm training.
Optionally, after the jaundice monitor value determining module 302, described device further include:
Sample generation module, for generating new samples according to the skin image and the jaundice monitor value;
Swatch addition module, for the new samples to be added in the sample set.
Optionally, the jaundice monitor value determining module 302 includes:
Color gain determines submodule, for determining color gain according to the uncalibrated image;
Standard color determines submodule, for determining the skin image according to the color gain and the skin image Standard color;
Jaundice monitor value determines submodule, for determining the Huang according to the standard color and the jaundice prediction model Subcutaneous ulcer monitor value.
In conclusion server receives the uncalibrated image that Image Acquisition terminal is sent and monitoring pair in the embodiment of the present invention The skin image of elephant;Jaundice monitor value is determined according to the jaundice prediction model that uncalibrated image, skin image and preparatory training obtain; Jaundice monitor value is fed back into Image Acquisition terminal, Image Acquisition terminal can check jaundice monitor value.The embodiment of the present invention is Real-time monitoring icterus neonatorum symptom is provided convenience, and is provided support for the real-time diagnosis decision of doctor, be ensure that neonatal Health and lives.
Example IV
Referring to Fig. 4, a kind of structural block diagram of jaundice monitoring device provided in an embodiment of the present invention is shown.It is deployed in image Acquisition terminal, described device include:
Image capture module 401, for acquiring the skin image of uncalibrated image and monitoring object;
Image sending module 402, for the uncalibrated image and the skin image to be sent to server, so that described Server determines that jaundice monitors according to the jaundice prediction model that the uncalibrated image, the skin image and preparatory training obtain Value;
Jaundice monitor value receiving module 403, for receiving the jaundice monitor value of the server feedback;
Display module 404, for showing the jaundice monitor value.
In conclusion Image Acquisition terminal acquires the skin image of uncalibrated image and monitoring object in the embodiment of the present invention; Uncalibrated image and skin image are sent to server, server is true according to uncalibrated image, skin image and jaundice prediction model Determine jaundice monitor value, Image Acquisition terminal receives the jaundice monitor value of server feedback and shown.The present invention is implemented Example is that real-time monitoring icterus neonatorum symptom is provided convenience, and provides support for the real-time diagnosis decision of doctor, ensure that new life The health and lives of youngster.
All the embodiments in this specification are described in a progressive manner, the highlights of each of the examples are with The difference of other embodiments, the same or similar parts between the embodiments can be referred to each other.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning Covering non-exclusive inclusion, so that the process, method, commodity or the equipment that include a series of elements not only include that A little elements, but also including other elements that are not explicitly listed, or further include for this process, method, commodity or The intrinsic element of equipment.In the absence of more restrictions, the element limited by sentence "including a ...", is not arranged Except there is also other identical elements in process, method, commodity or the equipment for including the element.
Above to a kind of jaundice monitoring method provided by the present invention and device, it is described in detail, it is used herein A specific example illustrates the principle and implementation of the invention, and the above embodiments are only used to help understand Method and its core concept of the invention;At the same time, for those skilled in the art is having according to the thought of the present invention There will be changes in body embodiment and application range, in conclusion the content of the present specification should not be construed as to the present invention Limitation.

Claims (10)

1. a kind of jaundice monitoring method, which is characterized in that be applied to server, which comprises
Receive the skin image of the uncalibrated image that Image Acquisition terminal is sent and monitoring object;
Jaundice monitor value is determined according to the jaundice prediction model that the uncalibrated image, the skin image and preparatory training obtain;
The jaundice monitor value is fed back into described image acquisition terminal.
2. the method according to claim 1, wherein described according to the uncalibrated image, the skin image Before the jaundice prediction model obtained with preparatory training determines jaundice monitor value, the method also includes:
Sample set is obtained, wherein each sample of the sample set is labelled with coloration, saturation degree, lightness and jaundice sample value;
The jaundice prediction model is obtained according to the sample set and regression algorithm training.
3. according to the method described in claim 2, it is characterized in that, described according to the uncalibrated image, the skin image After the jaundice prediction model obtained with preparatory training determines jaundice monitor value, the method also includes:
New samples are generated according to the skin image and the jaundice monitor value;
The new samples are added in the sample set.
4. the method according to claim 1, wherein it is described according to the uncalibrated image, the skin image and The jaundice prediction model that training obtains in advance determines jaundice monitor value, comprising:
Color gain is determined according to the uncalibrated image;
The standard color of the skin image is determined according to the color gain and the skin image;
The jaundice monitor value is determined according to the standard color and the jaundice prediction model.
5. a kind of jaundice monitoring method, which is characterized in that be applied to Image Acquisition terminal, which comprises
Acquire the skin image of uncalibrated image and monitoring object;
The uncalibrated image and the skin image are sent to server so that the server according to the uncalibrated image, The skin image and the jaundice prediction model that training obtains in advance determine jaundice monitor value;
Receive the jaundice monitor value of the server feedback;
Show the jaundice monitor value.
6. a kind of jaundice monitoring device, which is characterized in that be deployed in server, described device includes:
Image receiver module, for receiving the uncalibrated image of Image Acquisition terminal transmission and the skin image of monitoring object;
Jaundice monitor value determining module, the jaundice for being obtained according to the uncalibrated image, the skin image and preparatory training Prediction model determines jaundice monitor value;
Jaundice detected value feedback module, for the jaundice monitor value to be fed back to described image acquisition terminal.
7. device according to claim 6, which is characterized in that before the jaundice monitor value determining module, the dress It sets further include:
Sample set obtains module, for obtaining sample set, wherein each sample of the sample set is labelled with coloration, saturation degree, bright Degree and jaundice sample value;
Model training module, for obtaining the jaundice prediction model according to the sample set and regression algorithm training.
8. device according to claim 7, which is characterized in that after the jaundice monitor value determining module, the dress It sets further include:
Sample generation module, for generating new samples according to the skin image and the jaundice monitor value;
Swatch addition module, for the new samples to be added in the sample set.
9. device according to claim 6, which is characterized in that the jaundice monitor value determining module includes:
Color gain determines submodule, for determining color gain according to the uncalibrated image;
Standard color determines submodule, for determining the mark of the skin image according to the color gain and the skin image Quasi- color;
Jaundice monitor value determines submodule, for determining that the jaundice is supervised according to the standard color and the jaundice prediction model Measured value.
10. a kind of jaundice monitoring device, which is characterized in that be deployed in Image Acquisition terminal, described device includes:
Image capture module, for acquiring the skin image of uncalibrated image and monitoring object;
Image sending module, for the uncalibrated image and the skin image to be sent to server, so that the server Jaundice monitor value is determined according to the jaundice prediction model that the uncalibrated image, the skin image and preparatory training obtain;
Jaundice monitor value receiving module, for receiving the jaundice monitor value of the server feedback;
Display module, for showing the jaundice monitor value.
CN201810744772.4A 2018-07-09 2018-07-09 A kind of jaundice monitoring method and device CN109009132A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810744772.4A CN109009132A (en) 2018-07-09 2018-07-09 A kind of jaundice monitoring method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810744772.4A CN109009132A (en) 2018-07-09 2018-07-09 A kind of jaundice monitoring method and device

Publications (1)

Publication Number Publication Date
CN109009132A true CN109009132A (en) 2018-12-18

Family

ID=64641202

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810744772.4A CN109009132A (en) 2018-07-09 2018-07-09 A kind of jaundice monitoring method and device

Country Status (1)

Country Link
CN (1) CN109009132A (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201939330U (en) * 2011-01-07 2011-08-24 郝天羽 Network monitoring system for icterus neonatorum
CN104856680A (en) * 2015-05-11 2015-08-26 深圳贝申医疗技术有限公司 Automatic detection method and system for neonatal jaundice

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201939330U (en) * 2011-01-07 2011-08-24 郝天羽 Network monitoring system for icterus neonatorum
CN104856680A (en) * 2015-05-11 2015-08-26 深圳贝申医疗技术有限公司 Automatic detection method and system for neonatal jaundice

Similar Documents

Publication Publication Date Title
Harvey et al. Topographic representations of object size and relationships with numerosity reveal generalized quantity processing in human parietal cortex
US10755411B2 (en) Method and apparatus for annotating medical image
US9824441B2 (en) Method for estimating a quantity of a blood component in a fluid canister
US20170186139A1 (en) Image processing method for detail enhancement and noise reduction
WO2017076105A1 (en) Fault identification system for use in direct current transmission line
Çukur et al. Attention during natural vision warps semantic representation across the human brain
Lazar et al. Estimation of the orientation distribution function from diffusional kurtosis imaging
DE102010030859B4 (en) A method of inspecting a target mounted on a substrate
Chen et al. Individual variability and test-retest reliability revealed by ten repeated resting-state brain scans over one month
KR20170048558A (en) Automatic configuration of a low field magnetic resonance imaging system
US4365873A (en) Spatial frequency and contrast sensitivity test chart
WO2019001354A1 (en) Display panel gray scale adjustment method and device
Curby et al. Face to face with emotion: Holistic face processing is modulated by emotional state
US9332252B2 (en) Automatic test system for digital display systems
Newton et al. Task demand modulation of steady‐state functional connectivity to primary motor cortex
DE60036995T2 (en) Calibration system for a color generating device
US8655068B1 (en) Color correction system
EP0940996B1 (en) A method, an arrangement, an ASIC and their use for objective assessment of video quality
US20040151379A1 (en) 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
US20150243041A1 (en) Systems and methods for image and video signal measurement
Koppelmans et al. Brain structural plasticity with spaceflight
US20090136102A1 (en) Image processing of medical images
Martini et al. Image quality assessment based on edge preservation
US20070103551A1 (en) Method and system for measuring video quality
JP2004528566A (en) Chromaticity coordinate measuring device

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