CN109946290A - A kind of portable urine detector and method - Google Patents
A kind of portable urine detector and method Download PDFInfo
- Publication number
- CN109946290A CN109946290A CN201910258489.5A CN201910258489A CN109946290A CN 109946290 A CN109946290 A CN 109946290A CN 201910258489 A CN201910258489 A CN 201910258489A CN 109946290 A CN109946290 A CN 109946290A
- Authority
- CN
- China
- Prior art keywords
- paper
- test
- shell
- module
- value
- 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
- 210000002700 urine Anatomy 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 title claims abstract description 14
- 238000001514 detection method Methods 0.000 claims abstract description 75
- 239000011324 bead Substances 0.000 claims abstract description 16
- 238000012360 testing method Methods 0.000 claims description 58
- 238000012937 correction Methods 0.000 claims description 18
- 238000001914 filtration Methods 0.000 claims description 17
- 239000003086 colorant Substances 0.000 claims description 9
- 238000003780 insertion Methods 0.000 claims description 9
- 230000037431 insertion Effects 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 7
- 239000000758 substrate Substances 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 5
- 239000003153 chemical reaction reagent Substances 0.000 claims description 4
- 238000005530 etching Methods 0.000 claims description 4
- 230000007812 deficiency Effects 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 239000007787 solid Substances 0.000 claims 1
- 238000013461 design Methods 0.000 abstract description 2
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 239000008103 glucose Substances 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 7
- 238000005286 illumination Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 239000000463 material Substances 0.000 description 4
- 238000009603 uroscopy Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000001360 synchronised effect Effects 0.000 description 3
- 239000011800 void material Substances 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 235000005911 diet Nutrition 0.000 description 2
- 230000037213 diet Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 230000004438 eyesight Effects 0.000 description 2
- 238000011049 filling Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000011900 installation process Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 241000252794 Sphinx Species 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- GZCGUPFRVQAUEE-VANKVMQKSA-N aldehydo-L-glucose Chemical compound OC[C@H](O)[C@H](O)[C@@H](O)[C@H](O)C=O GZCGUPFRVQAUEE-VANKVMQKSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000009535 clinical urine test Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 206010012601 diabetes mellitus Diseases 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000001727 in vivo Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
Landscapes
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a kind of portable urine detector and methods, are related to urine detection technical field.The present invention includes detection device and cloud background system, detection device includes shell, slot component, fixation kit and several detection paper slips, a circuit board is fixed in shell, one surface of circuit board is fixed with several LED lamp beads, a camera module, the first algoritic module, the second algoritic module, third algorithm module and the 4th algoritic module, circuit board side is equipped with USB interface, shell side is run through in USB interface side, shell offers an opening with respect to the other side, shell side is connected with smart phone by USB interface and OTG data line, and fixation kit includes bottom plate.The present invention designs the corresponding algoritic module used, and be connected with cloud by designing novel urine detection structure, solves the problems, such as that existing urine detector volume is excessive, can not generally use and higher cost.
Description
Technical field
The invention belongs to urine detection technical fields, more particularly to a kind of portable urine detector and method.
Background technique
Urine Indexs measure is a kind of very common medicine detection mode.Currently, had already appeared both at home and abroad it is some just
Take the urine Indexs measure equipment of formula.But they still have the drawback that the convenience wretched insufficiency of 1, urine examination equipment: setting
It is standby oversized or excessively heavy, it has not been convenient to carry, also be inconvenient to place and be detected at home.2, urine examination equipment cost
Excessively high, be not suitable for a large amount of universal: detection device is a completely self-contained equipment, acquisition unit, computing unit comprising information,
Mechanical driving device, output or print module, this causes the cost of equipment high, and average family is difficult afford to consume, serious shadow
The universalness of equipment is rung.And excessively complicated internal structure is also unfavorable for the technology upgrading replacement.In terms of user experience, deposit
In problems: urine examination equipment aesthetics is inadequate, influences the vision perception of user.3, software and hardware is complicated for operation, and gerontal patient is difficult
To grasp.In use process, prompt information is inadequate, and user is needed to guess trial and error repeatedly.Detection time lack of wisdom is reminded, may
Lead to miss the best testing time.Automatic monitoring is lacked to test strips installation process, test strips insertion is not in place, upper and lower lane is anti-
, front and back it is anti-or no insertion test strips or deflection, beyond abnormal cases such as slot positions, can not all carry out
Early warning and prompt.Network module configuration is complicated, and gerontal patient can not complete independently configuration.Also, it is set due to being completely dependent on urine examination
Standby upper network module, the outlying district equipment that will lead in not network are not available.Data do not store, or can only be
It is locally stored.It can not be exchanged with doctor, ward mate, also be unable to get beneficial associated treatment information.4, the inspection of urine index
Survey unstable result: light durability is insufficient, uneven illumination, does not shield the interference of ambient light photograph, causes shadow to detection process
It rings.Be inconvenient to clean, be easy to cause testing result to change because of urine retention, and lead to peculiar smell, influence user
Experience.Designed on device structure it is unreasonable, be easy be physically contacted with urine test paper item, so as to cause between each indicator paper block
It pollutes, influences result.Testing result precision is inadequate, has difference with practical index.It, will if the above problem cannot solve
Application of the urine detection instrument in general patient daily life is seriously affected, so that uroscopy instrument can not become a popular production
Product.
Summary of the invention
The purpose of the present invention is to provide a kind of portable urine detector and methods, are examined by designing novel urine
Geodesic structure, and the corresponding algoritic module used is designed, and be connected with cloud, solve existing urine detector volume mistake
Greatly, it can not generally use and the problem of higher cost.
In order to solve the above technical problems, the present invention is achieved by the following technical solutions:
The present invention is a kind of portable urine detector, including detection device and cloud background system, the detection dress
It sets including shell, slot component, fixation kit and several detection paper slips;
A circuit board is fixed in the shell, one surface of circuit board is fixed with several LED lamp beads, a camera mould
Group, the first algoritic module, the second algoritic module, third algorithm module and the 4th algoritic module, the circuit board side are equipped with USB
Shell side is run through in interface, the USB interface side, and the shell offers an opening, the shell side with respect to the other side
Smart phone is connected with by USB interface and OTG data line;
The fixation kit includes bottom plate, and the bottom plate is fixedly connected by bolt with one surface of bottom in shell, described
One surface of bottom plate is fixed with position gates, one group of side buckle, one group of column-shaped projection and baffle buckle, the position gates and is located at shell
In vivo close to the side of detection box opening, the column-shaped projection is equipped with movable circlip, and the buckle of side described in one group and cylindricality are convex
Rise and be symmetricly set on one surface of bottom plate, the side buckle and baffle buckle are inverted L shape structure, described activity circlip one end with
Side buckle side is fixedly connected, and the baffle wedge be located in bottom plate far from opening side;
The slot component includes main board, and main board week side is equipped with enclosing, and one opposite side of enclosing is opened
Equipped with one group of symmetrical U-lag, the U-lag and column-shaped projection clearance fit, the enclosing top are fixed with the rich knot of packet
Structure, the main board middle part offer strip recess, and strip recess middle part offers circular recess.
Further, the detection paper slip includes test-paper and thin substrate, and the thin substrate includes rectangular panel portion and handle
Portion, the test-paper are fixed on rectangular panel portion, and the test-paper is equipped with several small indicator paper blocks, one surface of rectangular panel portion
And be located at the position outside small indicator paper block and be equipped with black outline border, indication wire, prompt icon and patch are equipped in the middle part of the test-paper
Piece.
Further, the quantity of the LED lamp bead is four, and four LED lamp beads are rectangular to be distributed in circuit board
It is opposite on four corners, the camera module and slot component medium position.
Further, the shell is cube structure, and shell week side is equipped with frosted layer, at the housing corners
It is provided with fillet, the case top is fixed with a switch, and the switch is electrically connected with circuit board.
Further, the cloud background system includes cloud database, doctor terminal software module, patient end software mould
Block, kith and kin end software module, social module and customer service subsystem.
A kind of portable urine detection method, comprising the following steps:
SS01 determines the positive and negative of test-paper by observation prompt icon and patch, and test-paper is soaked urine, is placed on master
On body plate, by forming suction between the suction-operated and slot component of moisture content;
The opening for the slot component alignment shell side for installing test-paper is inserted into shell by SS02, and slot component passes through positioning
Door is fallen between side buckle and baffle buckle, while U-lag can be stuck in and column-shaped projection side, at this time movable circlip sending
The sound, then slot component installs;
SS03 takes out OTG data line, is connected smart phone with the USB interface on circuit board by OTG data line, intelligence
Mobile phone can power for circuit board, at this time camera module and LED lamp bead starting;
SS04 positions each small indicator paper block on test-paper in image by the first algoritic module, passes through second
Algoritic module test-paper is positioned and judge direction of insertion whether deflection, can be to test-paper by third algorithm module
Each pixel carries out color correction in image, can be identified the color in test-paper to obtain by the 4th algoritic module
To final urine Indexs measure result;
SS05 can be transferred data to inside smart phone by OTG data line, can observe inspection by smart phone
It surveys result and is transferred to cloud database.
Further, specific step is as follows for the first algoritic module in the SS04:
SS0411: binaryzation is carried out to image using threshold value;
SS0412: using the largest connected domain in binary map as test paper panel region;
SS0413: the black outline border of test-paper is obtained using binaryzation in test paper panel region;
SS0414: the early warning if black outline border number deficiency 16;
SS0415: binaryzation is carried out inside each black outline border and obtains test paper panel region;
SS0416: test paper panel region is further refined using etching operation.
Further, specific step is as follows for the second algoritic module in the SS04:
SS0421: the part being overlapped with image border is filtered out from test-paper exterior contour, obtains outer profile and image
The intersection point on boundary, the lower left corner, the lower right corner as test strips;
The angle for the profile point that SS0422: calculating each profile point and longitudinal separation is N;
SS0423: using the smallest two profile points of angle value in all profile points as the upper left corner of test-paper, the upper right corner;
SS0424: whether the lower left corner, the upper left corner, the upper right corner, the lower right corner successively line judge to meet between each lines flat
Row, vertical relation;
SS0425: judge whether test-paper is to be disposed vertically.
Further, specific step is as follows for third algorithm module in the SS04:
20 figures are continuously captured using urine examination device in SS0431:1 minutes;
SS0432: the average value in tri- channels RGB of each figure is calculated;
SS0433: the intermediate value of each channel average value in 20 figures is found;
SS0434: by average value and the biggish image filtering of intermediate value difference;
SS0435: the average image of residual image is calculated;
SS0436: chromatic noise is filtered in the average image;
SS0437: reflective spot is highlighted caused by filtering light source;
SS0438: filtering shadows pixels and low brightness pixel;
SS0439: big gradient value pixel is filtered;
SS04310: all ash point pixels on test strips bottom plate are detected;
SS04311: average value is calculated to all ash point pixels, obtains the target value for color correction;
SS04312: using target value to each pixel, while color correction is carried out in tri- channels RGB;
SS04313: the pixel to color value after correction higher than 255 carries out average filter.
Further, specific step is as follows for the 4th algoritic module in the SS04:
SS0441: test-paper sample is acquired by human configuration various concentration reagent;
SS0442: the true detection sample of user is acquired by network;
SS0443: the region of 0.5mm wide is cut to each test-paper surrounding;
SS0444: simultaneous selection HSV, RGB, normalization tri- kinds of color spaces of RGB are as feature;
SS0445: from the color similarity of three kinds of color space COMPREHENSIVE CALCULATINGs, two pixels;
SS0446: subset of colours is established for each detection, and completes the poly- of color value using mean shift algorithm
Class establishes Gauss model for each color subclass;
SS0447: analyzing each pixel on current test-paper, judges that it belongs to the probability of each color subclass;
SS0448: carrying out noise filtering using Gauss model, if residual pixel number is lower than 10%, early warning;
SS0449: using repeatedly capturing, the image change amount of relatively corresponding test-paper, determine for identification most accurately
Moment;
SS04410: all pixels on comprehensive current test-paper obtain test-paper and belong to the general of each reference class
Rate obtains final recognition result.
The invention has the following advantages:
1, size of the present invention is no more than 10cm*10cm*10cm, and weight is no more than 200 grams, is well suited for patient and carries out at home
Test, is not take up excessive space, and be convenient for carrying, also can be used on the road.
2, the present invention controls the cost of urine examination equipment, retains image acquisition units, lighting unit in a device, then sharp
Be connected with OTG data line with smart phone, thus can computing unit, display unit by means of smart phone, while by machine
Tool transmission device is changed to hand slot, and the complexity of equipment is greatly lowered, and cost is also greatly lowered, and has completely general
The condition that logical masses can consume.
3, configuration design of the present invention is beautiful, promotion user visual perception, simple to operation, step extreme facility, and data are all same
When be stored in mobile phone local and cloud, user can easily see testing result, can also check on mobile phone or on web
All testing results in history, furthermore the matched cloud system of detection device also supports the society between patient Yu doctor, ward mate
It hands over, cloud system can send highly relevant feedback information and medical information according to the physical condition of patient.
4, urine examination equipment of the present invention has closure, can shield ambient light according to interference.Tray interior utilizes
White LED light source is illuminated, illumination stable and uniform, and the slot for installing test paper can be dismantled, independent to clean, and equipment and test paper are not
There are physical contacts, therefore not will cause urine pollution, and professional equipment in hospital is fully achieved in the testing result of each index item
Detection accuracy.
Certainly, it implements any of the products of the present invention and does not necessarily require achieving all the advantages described above at the same time.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, will be described below to embodiment required
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is a kind of structural schematic diagram of portable urine detector of the invention;
Fig. 2 is that Fig. 1 removes the structural schematic diagram after housing base;
Fig. 3 is the structure top view of fixation kit;
Fig. 4 is the structural schematic diagram of slot component;
Fig. 5 is the structural schematic diagram of fixation kit;
Fig. 6 is the structural schematic diagram for detecting paper slip;
In attached drawing, parts list represented by the reference numerals are as follows:
1- shell, 2- slot component, 3- fixation kit, 4- detection paper slip, 101- circuit board, 102-LED lamp bead, 103- take the photograph
As head mould group, 104-USB interface, 105- is open, 106- switch, 201- main board, 202- enclosing, 203-U shape slot, and 204- packet is rich
Structure, 205- strip recess, 206- circular recess, 301- bottom plate, 302- position gates, the side 303- buckle, 304- column-shaped projection,
305- baffle buckle, 306- activity circlip, 401- test-paper, 402- thin substrate, 403- rectangular panel portion, 404- handle portion, 405-
Small indicator paper block, 406- black outline border, 407- indication wire, 408- prompt icon, 409- patch.
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 all other
Embodiment shall fall within the protection scope of the present invention.
It please refers to shown in Fig. 1-6, the present invention is a kind of portable urine detector, including detection device and cloud backstage
System, detection device include shell 1, slot component 2, fixation kit 3 and several detection paper slips 4;
A circuit board 101 is fixed in shell 1,101 1 surface of circuit board is fixed with several LED lamp beads 102, a camera
Mould group 103, the first algoritic module, the second algoritic module, third algorithm module and the 4th algoritic module, 101 side of circuit board are set
There is usb 1 04,1 side of shell is run through in 04 side of usb 1, and shell 1 offers an opening 105, shell 1 with respect to the other side
Side is connected with smart phone by usb 1 04 and OTG data line, the model JYJH5-2835D082 of LED lamp bead 102,
LED lamp bead 102 is parallel with circuit board 101, guarantees that direction of illumination is the vertical direction of shell 1, camera module 103 includes optics
Camera lens and sensitive chip, sensitive chip are CCD sensitive chip or CMOS sensitive chip, and the chip model used is taken the photograph for HM2057
As the resolution ratio of head image is ten thousand pixel of 30-1000;When stressing speed, the resolution ratio of 300,000 pixels can be used;Stress precision, then
The resolution ratio of 10,000,000 pixels can be used, camera module 103 is communicated using UVC agreement with smart phone;
Fixation kit 3 includes bottom plate 301, and bottom plate 301 is fixedly connected by bolt with one surface of bottom in shell 1, bottom plate
301 1 surfaces are fixed with 302, one groups of sides of position gates and buckle 303, one groups of column-shaped projections 304 and baffle buckle 305, positioning
Door 302 is located at close to the side of detection box opening 105 in shell 1, and column-shaped projection 304 is equipped with movable circlip 306, one group of side
Buckle 303 and column-shaped projection 304 are symmetricly set on 301 1 surface of bottom plate, and side buckle 303 and baffle buckle 305 are inverted L shape
Structure, movable 306 one end of circlip buckle 303 sides with side and are fixedly connected, and baffle buckle 305 is located at bottom plate 301 far from opening
105 sides, position gates 302 are used to be oriented to slot component 2 and fixed, the stability of raising slot component 2;
Slot component 2 includes main board 201, and 201 weeks sides of main board are equipped with enclosing 202, and 202 1 opposite side of enclosing is opened
Equipped with one group of symmetrical U-lag 203, U-lag 203 and 304 clearance fit of column-shaped projection are fixed with packet at the top of enclosing 202
Rich structure 204 offers strip recess 205 in the middle part of main board 201, and 205 middle part of strip recess offers circular recess 206, encloses
Gear 202 is higher by 2-5mm than main board 201, enclosing 202 with a thickness of 0.5-1.5mm, enclosing 202 makes 2 four sides quilt of slot component
It surrounds, can be good at preventing detection paper slip 4 from skidding off, and can guarantee to detect paper slip 4 in insertion and installation process, Bu Huifa
Raw deflection, plays fixed function.
Wherein, detection paper slip 4 includes test-paper 401 and thin substrate 402, and thin substrate 402 includes rectangular panel portion 403 and handle
Portion 404, test-paper 401 are fixed on rectangular panel portion 403, and test-paper 401 is equipped with several small indicator paper blocks 405, small indicator paper block 405
Be 16, be distributed in a manner of 4*4,403 1 surface of rectangular panel portion and be located at small indicator paper block 405 outside position be equipped with black
Outline border 406 is equipped with indication wire 407, prompt icon 408 and patch 409, the line thickness of black outline border 406 in the middle part of test-paper 401
For 0.5mm, the spacing between two neighboring black outline border 406 is 1mm, and automatic checkout equipment by detecting outside black in the picture
The position of frame 406, so that it may obtain the exact position of each small indicator paper block 405.
Wherein, the quantity of LED lamp bead 102 is four, and four LED lamp beads 102 are rectangular to be distributed in circuit board 101 4
It is opposite on corner, camera module 103 and 2 medium position of slot component.
Wherein, shell 1 is cube structure, and shell 1 is made of light-proof material, all round closure, and isolation exterior light is according to dry
It disturbs, 1 week side of shell is equipped with frosted layer, and 1 corner of shell is provided with fillet, a switch 106, switch 106 are fixed at the top of shell 1
It is electrically connected with circuit board 101, carrying out fillet processing is the abrasion of shell 1 in order to prevent, and 1 surfacing of shell carries out frosted processing
For improving user's feel.
Wherein, cloud background system includes cloud database, doctor terminal software module, patient end software module, Qin Youduan
Software module, social module and customer service subsystem;
1, cloud database module, particular content and effect are as follows: (1) all previous testing results of all users exist
Preservation in cloud database.(2) artificial treatment to testing result each time is supported: to the part number of certain detection record
According to or total data modify;The completely new detection record of artificial addition one;Delete certain the detection note for being considered wrong
Record.(3) when user replaces mobile phone, system can automatically update the history detection record of mobile phone terminal, keep mobile phone terminal and cloud
The consistency of end data: user logs in the account of oneself on new mobile phone, then cloud database detects the corresponding hand of the account
All historical datas in the user beyond the clouds database are retrieved packing if being currently new cell-phone number by machine number
Compression, then downloads in mobile phone and synchronizes update.(4) user account manages submodule: beyond the clouds in database, establishing account
Number management data list;For the account of each user, a record is established;In the corresponding record of the account, the account is stored
Any phone number having used;When each user logs in, all cloud can be sent together by phone number.Cloud program
By judging whether the phone number is to occur for the first time in the record of the user, to decide whether to carry out data
It is synchronous;If this is new phone number for the user, then need the phone number being saved in the account corresponding
In record.
2, doctor terminal software module: (1) system is specially equipped with for each patient and instructs doctor: cloud system can be automatically to trouble
Person's distribution instructs doctor or user oneself to instruct doctor.Each doctor can instruct several patients.System automatically according to
Score height of the doctor in grading module is ranked up, the high first distribution of score.(2) when patient has new detection message,
Doctor terminal is reminded in a manner of sending message.(3) doctor checks the historical data of patient, provides hints and tips.
3, patient end software module: (1) mobile phone of patient under offline scenario, can will test result locally save with
Editor.(2) it is automatic to realize that local data is synchronous with cloud: after mobile phone offline a period of time when mobile phone is in online situation
Again line again then needs automatically to update emerging detection record to cloud;The detection note that patient edits in mobile phone terminal
Record needs to update to cloud;Patient has updated detection record in web browser, it is also desirable to automatically update cloud database
With mobile phone terminal;After patient replaces mobile phone, all detections record in cloud needs to be synchronized to new mobile phone terminal, while new cell-phone
On off-line data, also to automatically update cloud database.(3) patient can check any one detection in mobile phone local side
All history of index item detect record, and all index results detected each time.(4) patient end software is carved when detecting
Near when, patient is reminded automatically in a manner of voice, figure etc., so that the effect of urine Indexs measure be allowed to reach most
It is good.(5) automatic information broadcast function of the patient end software module to patient.(6) management of multiple accounts on the same mobile phone:
It can easily be switched under the account of oneself;After obtaining testing result, newest the one of all users can be traversed automatically
Secondary testing result, the most matched user that will be found remind whether user needs to automatically switch account;Record can be will test to turn
Move on to the mode under correct account.(7) management of a variety of test strips and a variety of Detection tasks: in back-end data base, to patient
The type of the type of test strips used and their Detection task, carries out necessary recording and storage.(8) conditions of patients information
Submodule is fed back, according to each single item Testing index of patient as a result, corresponding provide ready feedback word content in advance,
And the information such as corresponding message, drug, treatment recommendations, health care product.(9) e-commerce submodule: user can easily purchase
The consumptive materials such as test strips are bought, and can be paid by network payment.
4, kith and kin end software module: each step for facilitating young man that gerontal patient is instructed to operate uroscopy instrument: (1) kith and kin exist
Line supports function: during patient detects, on the software interface at kith and kin end, two pictures can be seen in real time:
Content of shooting, the content of mobile phone screen of mobile phone camera;After line supports function starting, kith and kin can carry out between patient
Real-time speech communicating is instructed;Kith and kin instruct patient to complete opening for detector by the real time content of viewing camera in real time
The operation such as the dynamic, installation of test strips, the connection of cellular phone data line, installation of test paper slot;Kith and kin can direct point in software
Detection button is hit, is operated instead of user;It can also be instructed by observation patient using the situation of software.(2) patient
There is new detection message then to remind kith and kin in time;(3) kith and kin check the history detection data of patient.
5, social module: for realizing mutual exchange (1), Huan Zheyu between the roles such as doctor, patient, kith and kin, ward mate
Doctor exchange social functions submodule: the content that can be transmitted include text, voice, picture, video, real-time voice, in real time
Video is made a phone call etc..(2) for patient to the appraisement system of doctor, content includes following several respects: the guidance of doctor whether and
When;Whether the instruction of doctor has strong specific aim, and whether improvement is obvious;The attitude good or not of doctor;Marking
As a result for 1-5/;Other patients can be according to the score and total score of each single item of the doctor, so that it may know the doctor
Raw service quality, to be judged.(3) the automatic recommendation and selection function of doctor: patient oneself setting and doctor are instructed
Distance, more than the distance doctor without selection;Default distance is 60km;Doctor in the distance range of patient set,
It is ranked up from high to low according to evaluation score;Doctor is good at field, with the degree of agreement of the most concerned Testing index of patient into
Row sequence;For example some patient concerns urine sugar level, then the doctor's sequence for being good at diabetes is forward;Doctor is investigated to have referred to
The quantity of the patient led.If the patient instructed is more than restriction number (such as 30 people), guidance not can be carried out.
6, customer service subsystem: (1) voice messaging using open source speech recognition software CMU Sphinx patient sent into
Row identification;Developer and contact staff gather the common high frequency problem of user in advance;Various problems are sorted out, are guaranteed
They are attributed to the same problem, establish among text subset S_text, and carry out real-time update to them;(2) from high frequency
Keyword is manually extracted in problem, builds up lists of keywords.Count between each keyword and the problem be associated with it is general
Rate: it is directed to current key word, all candidate problems is traversed, counts its total degree occurred in the text of the problem;It calculates
Probability of occurrence of the current key word in current candidate problem;(3) answer of each high frequency problem has editted, intelligence
Algorithm can call at any time, as answer feedback to user;(4) after user submits a question, intelligent algorithm passes through text one by one
The method of comparison, extracts keyword from text information;It tables look-up to obtain the probability that the keyword belongs to each problem, is all
Candidate problem establishes probability histogram;The probability of all keywords, is all overlapped in histogram;It is selected in histogram general
That maximum candidate problem of rate is as analysis result.(5) by the correspondence answer feedback of selected problem to patient.(6) user
It is still dissatisfied to answer, then it transfers to manually to be answered.
7, ward mate's chat and group management function submodule, improve the a-c cycle between patient.
8, patient population content of the discussions hot spot automatically analyzes function: research staff is by manually maintaining a hot keyword column
Table saves the frequency of each word appearance in 1 month, is ranked up from high to low according to frequency;It also needs to maintain one
Non-hot word list;When having new chat content every time, intelligent algorithm first calls viterbi algorithm to segment text;
Highest 100 words of the frequency of occurrences in same day chat content are extracted;It is analyzed by word, if current word is hot spot word,
Then update the frequency of occurrences for changing hot spot word;Else if being non-hot word, then without processing;Otherwise, manually the word is carried out
Analysis, decides whether to be added in hot spot word list;Highest preceding 20 words of frequency in hot spot word list are fed back into research and development
Personnel help it to grasp newest industrial hot spot.
9, wechat is checked card, and circle of friends is shown: be will test result and is published to circle of friends automatically in the form of a graph, allows good friend
The physical condition of oneself is known in time.
10, cloud intelligent analysis module detects patient's urine sugar level results abnormity situation, specific as follows: algorithm is certainly
The index result of 3 days nearly to patient dynamic (test 4 times, in total 12 times daily) carries out discriminatory analysis (by taking urine sugar level value as an example):
(1) glucose in urine normal value threshold value T=2.8mmol/L is set;(2) if this detection data X < 2.8mmol/L, then prompt glucose in urine
Normally;(3) otherwise, this history detection data of the glucose in urine of the user in the database is transferred.Such as no record before this, this
It is detected as detecting for the first time, is then stored in current record and exports prompt result;(4) otherwise, nearly 3 days indexs in called data library
As a result, seeking achievement data average value(5) ifIt is abnormal then to prompt glucose in urine, but trend is relatively stable, builds
View is careful in one's diet, and keeps continuing to monitor.(6) otherwise, then glucose in urine is prompted unusual fluctuations occur, it is proposed that further to test blood glucose and adjust
Whole diet is seen a doctor in time when necessary depending on blood glucose test result.
A kind of portable urine detection method, comprising the following steps:
SS01 determines the positive and negative of test-paper 401 by observation prompt icon 408 and patch 409, and test-paper 401 is soaked urine
Liquid is placed on main board 201, by forming suction between the suction-operated and slot component 2 of moisture content;
The opening 105 that the slot component 2 for installing test-paper 401 is directed at 1 side of shell is inserted into shell 1, groups of slots by SS02
Part 2 across position gates 302 fall in side buckle 303 and baffle buckle 305, while U-lag 203 can be stuck in it is convex with cylindricality
304 sides are played, movable circlip 306 issues the sound at this time, then slot component 2 installs;
SS03 takes out OTG data line, is connected the usb 1 04 on smart phone and circuit board 101 by OTG data line
It connects, smart phone can power for circuit board 101, and camera module 103 and LED lamp bead 102 start at this time;
SS04 positions each small indicator paper block 405 in image on test-paper 401 by the first algoritic module, leads to
Cross the second algoritic module test-paper 401 is positioned and judge direction of insertion whether deflection, pass through third algorithm module energy
It is enough that color correction is carried out to each pixel in 401 image of test-paper, it can be in test-paper 401 by the 4th algoritic module
Color is identified to obtain final urine Indexs measure result;
SS05 can be transferred data to inside smart phone by OTG data line, can observe inspection by smart phone
It surveys result and is transferred to cloud database.
Wherein, specific step is as follows for the first algoritic module in SS04:
SS0411: binaryzation is carried out to image using threshold value;
SS0412: using the largest connected domain in binary map as 401 region of test-paper;
SS0413: the black outline border 406 of test-paper 401 is obtained using binaryzation in 401 region of test-paper;
SS0414: the early warning if 406 number deficiency of black outline border 16;
SS0415: binaryzation is carried out inside each black outline border 406 and obtains 401 region of test-paper;
SS0416: 401 region of test-paper is further refined using etching operation.
Detailed step is as follows: 1, shooting image using urine examination device, then convert gray scale for color image Img_color
Image Img_gray;2, test strips are set and detect binaryzation empirical value Th_strip as 100;3, two-value is carried out to Img_gray
Change, obtains foreground image Img_fore: each of traversal Img_gray pixel, if the brightness value of the pixel is greater than
Th_strip, then the brightness value that the pixel of Img_fore corresponding position is arranged is 255, otherwise, is set as 0;4, indicator paper block outline border
Positioning, obtains test strips area-of-interest figure Img_ROI, the specific steps are as follows: (1) be connected to foreground image Img_fore
Domain analysis;(2) if there is no connected domain, it is basic just without test strips in field of view to illustrate, urine detection instrument algorithm stops;
(3) inner void filling is carried out to the connected domain detected;(4) area of each connected domain is calculated;By the maximum company of area
Logical domain, as the corresponding region of test strips;(5) area value in largest connected domain is if it is less than area lowest threshold Th_area_
Bound (is defaulted as 10000), then user is reminded in early warning;(6) it is located in Img_ROI, on position every inside test strips outline border
One pixel is both configured to 255, rest of pixels 0;5, setting indicator paper block black outline border detects binaryzation empirical value Th_
Bound is 150;6, binaryzation is carried out in conjunction with Img_gray and Img_ROI, obtains foreground image Img_fore2:(1) traversal
Each of Img_gray pixel is not handled if the brightness value in the corresponding Img_ROI figure of the location of pixels is 0;
Otherwise, if the pixel brightness value is lower than Th_bound in Img_gray, the respective pixel brightness value in Img_fore2 is set
255 are set to, if being higher than Th_bound, is set as 0;7, in conjunction with Img_color and Img_ROI, detection obtains foreground image
Img_fore3:(1 each of Img_color pixel) is traversed;If the corresponding Img_ROI figure of the location of pixels is bright
Angle value is 0, then does not handle;Otherwise, if as long as tri- values of RGB of the position pixel have one to be less than threshold value in Img_color
Th_bound then sets 255 for the respective pixel value brightness in Img_fore3, unless RGB tri- values are both less than Th_
Bound is just set as 0;(4) by image or operation, carry out Img_fore2 and Img_fore3 to be fused to foreground image
Img_fore4;8, carry out connected domain analysis to Img_fore4: if (1) connected domain number is less than 16, early warning, which is reminded, to be used
Family;(2) inner void of each connected domain is filled;(3) area of all connected domains is calculated;(4) area maximum 16 are extracted
Connected domain;If the area of this 16 connected domains is both greater than Th_area_patch, subsequent step is carried out;Otherwise, early warning is reminded
User;(5) the area-of-interest figure Bound_ROI_i of each connected domain is calculated, connected domain internal pixel values are set as
255;9, indicator paper block interior zone detection threshold value Th_bound_inner is set as 50;10, the more smart of each indicator paper block is obtained
Quasi- area-of-interest figure Bound_ROI_fine_i:(1) traverse the picture that each of Bound_ROI_i brightness value is 255
Element;(2) if the brightness value of the respective pixel in Img_gray is higher than Th_bound_inner, by Bound_ROI_fine_i
In respective pixel brightness value be set as 255;Otherwise, if RGB tri- of position pixel values in Img_color, as long as having
One is higher than Th_bound_inner, also sets 255 for the respective pixel brightness value in Bound_ROI_fine_i;Otherwise,
0 is set by the respective pixel brightness value in Bound_ROI_fine_i;(4) connected domain is carried out in Bound_ROI_fine_i
Analysis, if user is reminded in early warning without connected domain;(5) inner void filling is carried out to the connected domain that detection obtains;11,
The corresponding foreground area of connected domain on area-of-interest figure Bound_ROI_fine_i accurate to indicator paper block carries out etching operation,
The side length of morphological operation is 5 pixels, square operator.
Wherein, specific step is as follows for the second algoritic module in SS04:
SS0421: filtering out the part being overlapped with image border from 401 exterior contour of test-paper, obtains outer profile and figure
The lower left corner, the lower right corner as the intersection point on boundary, as test strips;
The angle for the profile point that SS0422: calculating each profile point and longitudinal separation is NN=20;
SS0423: using the smallest two profile points of angle value in all profile points as the upper left corner of test-paper 401, upper right
Angle;
SS0424: whether the lower left corner, the upper left corner, the upper right corner, the lower right corner successively line judge to meet between each lines flat
Row, vertical relation;
SS0425: judge whether test-paper 401 is to be disposed vertically.
Detailed step is following 1, from the point sequence of an outline of obtained test strips outline border, guarantees it according to the inverse of test strips outline border
Clockwise is configured.Remove the part being overlapped in point sequence of an outline with image boundary: a, along image boundary from left to right
Scanning finds first distance to image boundary less than the profile point of 5 pixels, is denoted as Pt1;B, equally along image boundary
It turns left scanning from the right side, obtains first distance to image boundary less than the profile point of 5 pixels, be denoted as Pt2;C, by test strips
All removing between point Pt1 and point Pt2 with the profile point of image boundary lap in outline border profile sequence;D, again whole
Test paper profile sequence is managed, makes its sequence counterclockwise, and guarantees that starting point is Pt2, emphasis Pt1;
2, since point Pt2, traverse each profile point Pti according to sequence counter-clockwise, calculate profile point angle ci:a,
Spacing N is set as 20;B, according to sequence n-th pixel after profile point Pti counterclockwise, is found, it is denoted as Pt_next;
C, n-th pixel of the sequence before profile point Pti is found, Pt_pre is denoted as;D, Pti and Pt_next is connected, is obtained
Straight line L1;E, Pti and Pt_pre is connected, obtains straight line L2;F, the angle between L1 and L2 is calculated, angle ci is obtained,
That angle that angle ci takes angle to be less than or equal to 180 °;G, point sequence of an outline length is Len;If the serial number of profile point Pti is small
In N, or it is greater than Len_N, then the angle value of profile point Pti is directly recorded as 180 °;
3, it finds in all profile points, the smallest two profile points of angle value are denoted as profile point Corner1, profile respectively
Point Corner2. is using the two profile points as the upper left corner of test strips and the upper right corner;Utilize profile point Corner1, profile point
Corner2, point Pt1, point Pt2, are divided into three sections for test strips profile;They are left margin Line_left, coboundary respectively
Line_top, right margin Line_right;
4, three boundaries are directed to, its straightness: three boundaries are analyzed, as long as wherein there is one straightness V_line to be less than
Threshold value 0.9 then illustrates that test strips are problematic, early warning;The calculation method of straightness are as follows: the head and the tail two o'clock of a, fillet are constituted
Straight line L0;B, in the profile point of statistical boundary, to straight line distance be less than threshold value point number, threshold value is defaulted as 5 pixels, remembers
For N_near_line;C, the profile number on boundary is N_contour;D, straightness
If 5, left margin, right margin are greater than 5 ° with the angle of vertical direction respectively, illustrate that test strips direction of insertion is inclined
Tiltedly, early warning is needed;If coboundary and horizontal angle are greater than 5 °, illustrate that test strips direction of insertion tilts, need early warning;
If the angle that left margin and right margin are constituted, is less than threshold value Th_Angle (5 °), illustrates that right boundary is parallel;Otherwise, it needs
Early warning;The angle value in the upper left corner and the upper right corner is calculated, if there is any one less than 85 ° among them, or is greater than 95 °,
Then illustrate that the angle is not right angle, needs early warning.
Wherein, specific step is as follows for third algorithm module in SS04:
20 figures are continuously captured using urine examination device in SS0431:1 minutes;
SS0432: the average value in tri- channels RGB of each figure is calculated;
SS0433: the intermediate value of each channel average value in 20 figures is found;
SS0434: by average value and the biggish image filtering of intermediate value difference;
SS0435: the average image of residual image is calculated;
SS0436: chromatic noise is filtered in the average image;
SS0437: reflective spot is highlighted caused by filtering light source;
SS0438: filtering shadows pixels and low brightness pixel;
SS0439: big gradient value pixel is filtered;
SS04310: all ash point pixels on test strips bottom plate 301 are detected;
SS04311: average value is calculated to all ash point pixels, obtains the target value for color correction;
SS04312: using target value to each pixel, while color correction is carried out in tri- channels RGB;
SS04313: the pixel to color value after correction higher than 255 carries out average filter.
Detailed step is as follows: 1, urine detector automatically continuously captures N=20 images, and each time interval is 2 seconds
Clock.
2, the average light intensity for calculating N images, filters the image of low light image and overexposure, specific steps are such as
Under:
(1) it is directed to every piece image, calculates the average value in tri- channels figure RGB:
Wherein, NpixelIt is image
Total number-of-pixels.(2) it is directed to the R_aver of N width image, sequence from big to small is carried out, then obtains intermediate value R_median.
(3) each R_aver is traversed, if the difference of the absolute value of the value and R_median is greater than 10, then it is assumed that the figure has exception, needs
Filter out the figure.(4) for two Color Channels of G and B, same method is also used, calculates intermediate value, and Exception Filter figure
Picture.(5) still remaining normal picture total number is N at this time2IfIt then needs to re-shoot.Otherwise, residue is utilized
N2Width image calculates the average image:
3, the chromatic noise in mean chart is filtered using median filtering.
4, the detection of the light reflector point in mean chart: each pixel of img_mean is traversed, if met simultaneously such as
Lower three conditions, then be set as 0. wherein for the pixel value of same position in img_GLINT_ROI, Th_G be 250:R (x, y) >=
Th_GLINT&&G(x,y)≥Th_GLINT&&B(x,y)≥Th_GLINT。
5, in the average image shadows pixels and low brightness pixel detection and filtering: each pixel, if met simultaneously
The pixel value of same position in shadows pixels ROI image img_shadow_ROI is then set as 0. by following three condition
R(x,y)≤Th_shadow&&G(x,y)≤Th_shadow&&B(x,y)≤Th_shadow
Wherein, Th_shadow is empirical value (being defaulted as 20).
6, the filtering of the big gradient value pixel on indicator paper block periphery: (1) gradation conversion is carried out to img_mean, obtains img_
Mean_gray. (2) calculate gradient magnitude using Sobel operator in img_mean_gray:
Gx(i, j)=I (i, j)-I (i, j-1), Gy(i, j)=I (i, j)-I (i-1, j), G (i, j)=Gx(i,j)+Gy
(i,j)
Wherein, GxThe gradient magnitude that (i, j) is horizontally oriented, GyThe gradient magnitude that (i, j) is vertically oriented, I (i, j) table
Show that the pixel brightness value of the position (i, j), G (i, j) are the gradient magnitudes for the pixel that position is (i, j).(3) current mean chart is traversed
As each pixel of img_mean, if meeting following condition G (i, j) >=Th_gradien, t if, schemes edge pixel ROI
As the pixel value of same position in img_gradient_ROI is set as 0. wherein, Th_gradient is that empirical value (is defaulted as
40)。
7, the detection of the ash point pixel (rgb value difference is not more than 20) on test paper bottom plate: abovementioned steps have obtained each
The position of a indicator paper block, therefore the position in img_mean other than indicator paper block is only needed to traverse each pixel, as long as meeting
Following three condition, it just adds it in set S:
Img_GLINT_ROI (x, y)==255&&img_shadow_ROI (x, y)==255&&img_grdient_
ROI (x, y)==
8, to the average image img_mean carry out color correction: in set S it is all ash put pixels, calculate they
R, the respective average value on tri- channels G, B.Then maximum value therein is chosen, is used for color correction as target value:
Val_max=max (R_aver, G_aver, B_aver)
Calculate tri- respective correction coefficient in channel of R, G, B:
Each of img_mean pixel is traversed, its color-values is corrected:
Wherein, R、、G、、B、For current pixel, the numerical value in tri- channels R, G, B after correction.
9, after color correction, pixel value is more than the processing of 255 situation: utilizing 8 in 8 neighborhoods on the pixel periphery
The average value of the rgb value of pixel, the rgb value as the pixel.Then Gaussian smoothing is carried out to result images, to eliminate face
The indisposed sense of the vision that may cause in color correction course.
Wherein, specific step is as follows for the 4th algoritic module in SS04:
SS0441: 401 sample of test-paper is acquired by human configuration various concentration reagent;
SS0442: the true detection sample of user is acquired by network;
SS0443: the region of 0.5mm wide is cut to each 401 surrounding of test-paper;
SS0444: simultaneous selection HSV, RGB, normalization tri- kinds of color spaces of RGB are as feature;
SS0445: from the color similarity of three kinds of color space COMPREHENSIVE CALCULATINGs, two pixels;
SS0446: subset of colours is established for each detection, and completes the poly- of color value using mean shift algorithm
Class establishes Gauss model for each color subclass;
SS0447: analyzing each pixel on current test-paper 401, judges that it belongs to the general of each color subclass
Rate;
SS0448: carrying out noise filtering using Gauss model, if residual pixel number is lower than 10%, early warning;
SS0449: using repeatedly capturing, the image change amount of relatively corresponding test-paper 401 determines for identification most smart
At the time of quasi-;
SS04410: all pixels on comprehensive current test-paper 401 obtain test-paper 401 and belong to each reference class
Probability, obtain final recognition result.
Detailed step is as follows: 1, the high-volume of indicator paper block test sample is collected: (1) passing through the various various concentrations of human configuration
Correspondence reagent, then test strips are impregnated wherein, obtain corresponding sample subgraph (such as the corresponding subgraph of each indicator paper block
As more than 1000).(2) collection of user's authentic testing sample.After uroscopy instrument puts goods on the market true use, examined in user
During surveying urine index, the image captured when can also detect each time user is stored in cloud database.
2, in indicator paper block subgraph peripheral light areas processing: each up and down in the corresponding subgraph of indicator paper block is cut out
Cut the fillet of 0.5mm width, the in this way central area eventually for the indicator paper block of color identification, actual size 4mm*4mm.
3, the selection of color space: (1) defect of HSV color space: by taking this situation of R==max as an example, work as max-
When this value very little of min (for example being lower than 20), it is easy to the unstable phenomenon of hue value occur.This is because denominator is very at this time
It is small, and the variation of the very little of molecule, so that it may so that biggish variation occurs for entire fractional value.When max==min, H value
Be it is imponderable, at this time denominator be 0.Hue value is very also unstable at this time.In order to make up this defect of hue value, the present invention
Introduce normalization rgb space.(2) rgb color space is normalized: in rgb color space, the correlation of tri- color values of R, G, B
Property is very high, and is highly susceptible to the interference of illumination.They can not steadily describe the reflectivity of body surface.In order to disappear
Except illumination variation bring is interfered, rgb color space is normalized using the summation in tri- channels RGB as illumination value, is then calculated
The ratio of each Color Channel obtains three normalized color characteristics: r, g, b:But
It is that normalization rgb color space is still defective.When being such as lower than 40 when the value very little of R+G+B, r, g two
The calculating of value is still unstable.It needs directly to state color using rgb color space at this time.(3) three kinds of color spaces it is comprehensive
It closes and uses: (a) extracting form and aspect feature h in HSV color space;If (b) h feature is unstable, in normalization rgb space
Extract r, g feature;If (c) feature r, g is unstable, R, G, B feature are extracted directly in rgb space;
4, the calculating of the color similarity of two pixels: (1) judge whether form and aspect feature h is stable, i.e. the difference of max and min
Value is greater than 50 situation: if stablized, directly utilizing the hue value h of two colors1、h2It makes the difference.Difference is bigger, and similarity is got over
It is low.The calculating of color difference is as follows: dist=| h1-h2|.(2) form and aspect feature is unstable, then compares the difference of r, g of two pixels
Value.The difference is smaller, illustrates that the color of two pixels is closer.Dist=| r1-r2|+|g1-g2|.(3) r, g are unstable, i.e. R,
G, situation of the summation of B less than 20.Directly compare the difference of R, G, B at this time.The difference is smaller, illustrates that two color values more connect
Closely.Dist=| R1-R2|+|G1-G2|+|B1-B2|;
5, for each detection (a line on colorimetric card, including multiple with reference to color lump), candidate color collection is carried out
It establishes: the sample of the current detection item corresponding concentration in step 1 is belonged in sample set S.It analyzes in sample set S
All subimage blocks, extract subgraph in all pixels, obtain subset of colours S_patch;The subset of colours contains this
All possible color in term of reference corresponding to reference block, and each color can be calculated and belong to the reference block
Probability.Using certain type colorimetric card as example, for this detection of glucose, a total of 5 refer to color lump on colorimetric card.That
This detection for glucose is just needed to establish 5 subset of colours.One of subset of colours S_patch_sugar_i's builds
Vertical process is as follows: (1) from colorimetric card, the index value range of current reference color lump being extracted.Relevant information is all recorded in
On colorimetric card;(2) all image patterns for belonging to the concentration range collected in step 1 are belonged into sample image
Collect S_image_i;(3) for every piece image in sample image subset S_image_i, the detection and mistake of reflective spot are carried out
Filter;(4) all pixels in every piece image in sample image subset S_image_i are extracted, its color feature value is calculated;
(5) mean shift clustering method is utilized, is clustered for all colours characteristic value in image subset S_image_i.Each subset
Subclass numbers be set as 10:(a) at random setting 10 classes initial center position;(b) size of search window is set;(c)
Iterative search finds the maximum position of sample rate in window, as new window center every time;(d) iteration, directly
Until the center of any one class all no longer changes;(e) according to the final center of 10 classes, to all pictures
Element is classified, and 10 subclasses are obtained.(6) color characteristic for utilizing classification results and all pixels is established each subclass high
This probabilistic model.To establish gaussian probability model in six features of slave R, G, B, Hue, r, g of current subclass.
6, identify to the color of current indicator paper block to be detected: (1) each traversed on colorimetric card refers to color lump,
Obtain its standard color feature R, G, B, Hue, r, g;(2) each pixel on current indicator paper block is traversed, its color spy is extracted
Sign: R, G, B, Hue, r, g;(3) whether the method for utilizing probability, be that noise judges to each pixel on indicator paper block: (a)
Using cluster result obtained in color characteristic and step 5 and gaussian probability model, calculates current pixel and belong to each ginseng
Examine the probability of class;If (b) probability that the pixel belongs to any one reference class is below 0.001, uses the pixel as and make an uproar
Sound is filtered.(4) probability that current pixel is classified as each corresponding reference class on colorimetric card is calculated.Select probability is maximum
Reference class as classification results: (a) using cluster result and gaussian probability model obtained in color characteristic and step 5,
Calculate the probability that current pixel belongs to each reference class;(b) probability of more all reference classes, by that maximum probability value
Classification results of the serial number of corresponding reference block as the pixel;(c) the maximum reference class of select probability is as the pixel
Classification results.(5) classification results of entire indicator paper block are calculated: (a) counting the classification results of each pixel, obtain classification histogram
Figure;(b) according to classification histogram, the probability that the indicator paper block belongs to each reference class is calculated.Calculation method are as follows:
Wherein Pi indicator paper block belongs to the probability of i-th of reference class.And ciIt is the pixel number that i-th of reference class is classified as in indicator paper block image
Mesh.N is the total number of all pixels in image.(c) in all reference class probability PsiIn, the maximum reference class of select probability,
The color recognition result final as indicator paper block:(d) the corresponding index value of current indicator paper block is calculated.
It weights to obtain the result using the index value of each reference block.Wherein, resiIt is each reference class
Corresponding index value.PiFor reference class probability.N is the number of reference class.
If 7, for current indicator paper block after completing various noise filterings, it is true to account for the indicator paper block by remaining sum of all pixels mesh N
Real image prime number purpose ratio is lower than 10%, then illustrates that the indicator paper block has exception to need early warning that user is reminded to re-start detection.
8, by uroscopy instrument carry out multiple video capture in the way of it is whether abundant to detect chemical reaction: (1) using step
The seven 20 width images captured are analyzed.(2) it is directed to some detection, analyzes the situation of change of this 20 width sub-picture content.It will
Each width subgraph all respectively makes the difference with corresponding subgraph in forward and backward two frame, counts the sum of all pixels mesh changed.
It is specific as follows: compared with (a) current figure carries out pixel-by-pixel with former frame subgraph, to judge that how many pixel is different, record
The total number of different pixel.Two pixels, meeting following condition, to be considered as them inconsistent:
|R1(x,y)-R2(x, y) | > Th_diff | | | G1(x,y)-G2(x, y) | > Th_diff | | | B1(x,y)-B2(x,
Y) | > Th_diff wherein, R1(x, y) indicates the R value of the position present frame (x, y), R2The R of (x, y) expression position former frame (x, y)
Value .G1(x, y) indicates the G value of the position present frame (x, y), G2The G value of (x, y) expression position former frame (x, y).B1(x, y) is indicated
The B value of the position present frame (x, y), B2The B value of (x, y) expression position former frame (x, y).Some picture of current figure and former frame figure
Element, as long as any one channel color data error in tri- channels RGB is excessive, so that it may think that the pixel is changed.
Wherein, Th_diff is empirical value, is set as the number N of 10. (b) statistics current figure and the different pixel of former frame figure1.
The number N of statistics current figure and the different pixel of a later frame figure2The unstable sum of all pixels mesh of current figure is counted, formula is such as
Under: N=N1+N2(4) are directed to current detection item, its corresponding all subgraph are traversed, by number of pixels change minimum (N value
It is minimum) that width subgraph detected as the most stable of moment.
In the description of this specification, the description of reference term " one embodiment ", " example ", " specific example " etc. means
Particular features, structures, materials, or characteristics described in conjunction with this embodiment or example are contained at least one implementation of the invention
In example or example.In the present specification, schematic expression of the above terms may not refer to the same embodiment or example.
Moreover, particular features, structures, materials, or characteristics described can be in any one or more of the embodiments or examples to close
Suitable mode combines.
Present invention disclosed above preferred embodiment is only intended to help to illustrate the present invention.There is no detailed for preferred embodiment
All details are described, are not limited the invention to the specific embodiments described.Obviously, according to the content of this specification,
It can make many modifications and variations.These embodiments are chosen and specifically described to this specification, is in order to better explain the present invention
Principle and practical application, so that skilled artisan be enable to better understand and utilize the present invention.The present invention is only
It is limited by claims and its full scope and equivalent.
Claims (10)
1. a kind of portable urine detector, it is characterised in that: including detection device and cloud background system, the detection dress
It sets including shell (1), slot component (2), fixation kit (3) and several detection paper slips (4);
It is fixed with a circuit board (101) in the shell (1), (101) one surface of circuit board is fixed with several LED lamp beads
(102) and a camera module (103), circuit board (101) side are equipped with USB interface (104), the USB interface (104)
Shell (1) side is run through in side, and the shell (1) offers an opening (105) with respect to the other side, and shell (1) side is logical
It crosses USB interface (104) and OTG data line is connected with smart phone;
The fixation kit (3) includes bottom plate (301), and the bottom plate (301) is solid by bolt and shell (1) interior one surface of bottom
Fixed connection, (301) one surface of bottom plate are fixed with position gates (302), one group of side buckle (303), one group of column-shaped projection
(304) it is located in shell (1) with baffle buckle (305), the position gates (302) close to the side of detection box opening (105),
The column-shaped projection (304) is equipped with movable circlip (306), and side described in one group buckles (303) and column-shaped projection (304) is symmetrical
On (301) one surface of bottom plate, the side buckle (303) and baffle buckle (305) are inverted L shape structure, the activity for setting
Circlip (306) one end is fixedly connected with side buckle (303) side, and the baffle buckle (305) is located at bottom plate (301) and keeps away from
Mouth (105) side;
The slot component (2) includes main board (201), and all sides of the main board (201) are equipped with enclosing (202), described to enclose
(202) one opposite sides of gear offer one group of symmetrical U-lag (203), the U-lag (203) and column-shaped projection (304)
Clearance fit, enclosing (202) top are fixed with packet and have mercy on structure (204), and it is recessed to offer strip in the middle part of the main board (201)
It falls into (205), offers circular recess (206) in the middle part of the strip recess (205).
2. a kind of portable urine detector according to claim 1, which is characterized in that detection paper slip (4) packet
Include test-paper (401) and thin substrate (402), the thin substrate (402) includes rectangular panel portion (403) and handle portion (404), described
Test-paper (401) is fixed on rectangular panel portion (403), and the test-paper (401) is equipped with several small indicator paper blocks (405), described
(403) one surface of rectangular panel portion and it is located at small indicator paper block (405) external position and is equipped with black outline border (406), the test paper
Indication wire (407), prompt icon (408) and patch (409) are equipped in the middle part of piece (401).
3. a kind of portable urine detector according to claim 1, which is characterized in that the LED lamp bead (102)
Quantity is four, and four LED lamp beads (102) are rectangular to be distributed in (101) four corners of circuit board, the camera mould
It is opposite in group (103) and slot component (2) medium position.
4. a kind of portable urine detector according to claim 1, which is characterized in that the shell (1) is pros
Body structure, all sides of the shell (1) are equipped with frosted layer, and shell (1) corner is provided with fillet, shell (1) top
It is fixed with a switch (106), the switch (106) and circuit board (101) are electrically connected.
5. a kind of portable urine detector according to claim 1, which is characterized in that the cloud background system packet
Include cloud database, doctor terminal software module, patient end software module, kith and kin end software module, social module and customer service subsystem
System.
6. -5 any one a kind of portable urine detection method according to claim 1, which is characterized in that including following step
It is rapid:
SS01 determines the positive and negative of test-paper (401) by observation prompt icon (408) and patch (409), and test-paper (401) are soaked
Wet urine is placed on main board (201), by forming suction between the suction-operated of moisture content and slot component (2);
SS02 will install opening (105) insertion shell (1) of slot component (2) alignment shell (1) side of test-paper (401),
Slot component (2) is fallen in side buckle (303) and baffle buckle (305) across position gates (302), while U-lag (203)
Can be stuck in column-shaped projection (304) side, movable circlip (306) issues the sound at this time, then slot component (2) installs;
SS03 takes out OTG data line, is connected the USB interface (104) on smart phone and circuit board (101) by OTG data line
It connects, smart phone can power for circuit board (101), at this time camera module (103) and LED lamp bead (102) starting;
SS04 positions each small indicator paper block (405) on test-paper in image (401) by the first algoritic module, leads to
Cross the second algoritic module test-paper (401) is positioned and judge direction of insertion whether deflection, pass through third algorithm module
Color correction can be carried out to each pixel in test-paper (401) image, it can be to test-paper by the 4th algoritic module
(401) color in is identified to obtain final urine Indexs measure result;
SS05 can be transferred data to inside smart phone by OTG data line, can observe detection knot by smart phone
Fruit is simultaneously transferred to cloud database.
7. a kind of portable urine detection method according to claim 6, which is characterized in that the first algorithm in the SS04
Specific step is as follows for module:
SS0411: binaryzation is carried out to image using threshold value;
SS0412: using the largest connected domain in binary map as test-paper (401) region;
SS0413: the black outline border (406) of test-paper (401) is obtained using binaryzation in test-paper (401) region;
SS0414: the early warning if black outline border (406) number deficiency 16;
SS0415: binaryzation is carried out inside each black outline border (406) and obtains test-paper (401) region;
SS0416: test-paper (401) region is further refined using etching operation.
8. a kind of portable urine detection method according to claim 6, which is characterized in that the second algorithm in the SS04
Specific step is as follows for module:
SS0421: the part being overlapped with image border is filtered out from test-paper (401) exterior contour, obtains outer profile and image
The intersection point on boundary, the lower left corner, the lower right corner as test strips;
SS0422: each profile point and longitudinal separation are calculated as the angle of the profile point of N (N=20);
SS0423: using the smallest two profile points of angle value in all profile points as the upper left corner of test-paper (401), upper right
Angle;
SS0424: by the lower left corner, the upper left corner, the upper right corner, the lower right corner successively line, judge whether to meet between each lines it is parallel,
Vertical relation;
SS0425: judge whether test-paper (401) is to be disposed vertically.
9. a kind of portable urine detection method according to claim 6, which is characterized in that third algorithm in the SS04
Specific step is as follows for module:
20 figures are continuously captured using urine examination device in SS0431:1 minutes;
SS0432: the average value in tri- channels RGB of each figure is calculated;
SS0433: the intermediate value of each channel average value in 20 figures is found;
SS0434: by average value and the biggish image filtering of intermediate value difference;
SS0435: the average image of residual image is calculated;
SS0436: chromatic noise is filtered in the average image;
SS0437: reflective spot is highlighted caused by filtering light source;
SS0438: filtering shadows pixels and low brightness pixel;
SS0439: big gradient value pixel is filtered;
SS04310: all ash point pixels on test strips bottom plate (301) are detected;
SS04311: average value is calculated to all ash point pixels, obtains the target value for color correction;
SS04312: using target value to each pixel, while color correction is carried out in tri- channels RGB;
SS04313: the pixel to color value after correction higher than 255 carries out average filter.
10. a kind of portable urine detection method according to claim 6, which is characterized in that the 4th calculates in the SS04
Specific step is as follows for method module:
SS0441: test-paper (401) sample is acquired by human configuration various concentration reagent;
SS0442: the true detection sample of user is acquired by network;
SS0443: the region of 0.5mm wide is cut to each test-paper (401) surrounding;
SS0444: simultaneous selection HSV, RGB, normalization tri- kinds of color spaces of RGB are as feature;
SS0445: from the color similarity of three kinds of color space COMPREHENSIVE CALCULATINGs, two pixels;
SS0446: subset of colours is established for each detection, and completes the cluster of color value using mean shift algorithm, is
Each color subclass establishes Gauss model;
SS0447: analyzing each pixel on current test-paper (401), judges that it belongs to the probability of each color subclass;
SS0448: carrying out noise filtering using Gauss model, if residual pixel number is lower than 10%, early warning;
SS0449: using repeatedly capturing, the image change amount of relatively corresponding test-paper (401), determine for identification most precisely
At the time of;
SS04410: all pixels on comprehensive current test-paper (401) obtain test-paper (401) and belong to each reference class
Probability, obtain final recognition result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910258489.5A CN109946290A (en) | 2019-04-01 | 2019-04-01 | A kind of portable urine detector and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910258489.5A CN109946290A (en) | 2019-04-01 | 2019-04-01 | A kind of portable urine detector and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109946290A true CN109946290A (en) | 2019-06-28 |
Family
ID=67013264
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910258489.5A Pending CN109946290A (en) | 2019-04-01 | 2019-04-01 | A kind of portable urine detector and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109946290A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113567429A (en) * | 2021-09-24 | 2021-10-29 | 深圳市云创精密医疗科技有限公司 | Portable urine test device and online medical system using same |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20110038456A (en) * | 2009-10-08 | 2011-04-14 | (주) 지비테크 | Urine analyzer |
JP2012088232A (en) * | 2010-10-21 | 2012-05-10 | Sutakku System:Kk | Water quality inspection test paper measurement apparatus |
CN104359899A (en) * | 2014-11-04 | 2015-02-18 | 康泰医学系统(秦皇岛)股份有限公司 | Handheld urine analyzer |
CN206223791U (en) * | 2016-12-07 | 2017-06-06 | 厦门科牧智能技术有限公司 | A kind of automatic urine checking device and toilet |
CN206411017U (en) * | 2017-01-11 | 2017-08-15 | 深圳市莱康宁医用科技股份有限公司 | A kind of Urine Analyzer and urine analysis system |
CN107121542A (en) * | 2017-04-28 | 2017-09-01 | 厦门大学 | A kind of immunity-chromatography test strip quantitative detection system and method based on mobile phone |
CN107426483A (en) * | 2016-05-24 | 2017-12-01 | 鸿富锦精密工业(深圳)有限公司 | Wearable biological information of human body detection means, system and detection method |
CN108107196A (en) * | 2018-01-16 | 2018-06-01 | 中科院合肥技术创新工程院 | A kind of intelligent domestic type urine dry chemical method detecting system and method |
CN108613971A (en) * | 2016-12-11 | 2018-10-02 | 芦守珍 | A kind of minitype portable Urine test paper analyzer and urine dry chemical scrip |
-
2019
- 2019-04-01 CN CN201910258489.5A patent/CN109946290A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20110038456A (en) * | 2009-10-08 | 2011-04-14 | (주) 지비테크 | Urine analyzer |
JP2012088232A (en) * | 2010-10-21 | 2012-05-10 | Sutakku System:Kk | Water quality inspection test paper measurement apparatus |
CN104359899A (en) * | 2014-11-04 | 2015-02-18 | 康泰医学系统(秦皇岛)股份有限公司 | Handheld urine analyzer |
CN107426483A (en) * | 2016-05-24 | 2017-12-01 | 鸿富锦精密工业(深圳)有限公司 | Wearable biological information of human body detection means, system and detection method |
CN206223791U (en) * | 2016-12-07 | 2017-06-06 | 厦门科牧智能技术有限公司 | A kind of automatic urine checking device and toilet |
CN108613971A (en) * | 2016-12-11 | 2018-10-02 | 芦守珍 | A kind of minitype portable Urine test paper analyzer and urine dry chemical scrip |
CN206411017U (en) * | 2017-01-11 | 2017-08-15 | 深圳市莱康宁医用科技股份有限公司 | A kind of Urine Analyzer and urine analysis system |
CN107121542A (en) * | 2017-04-28 | 2017-09-01 | 厦门大学 | A kind of immunity-chromatography test strip quantitative detection system and method based on mobile phone |
CN108107196A (en) * | 2018-01-16 | 2018-06-01 | 中科院合肥技术创新工程院 | A kind of intelligent domestic type urine dry chemical method detecting system and method |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113567429A (en) * | 2021-09-24 | 2021-10-29 | 深圳市云创精密医疗科技有限公司 | Portable urine test device and online medical system using same |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Fraser et al. | Reaction time measures of feature saliency in schematic faces | |
CN101685060B (en) | Sample imaging apparatus | |
CN108898579A (en) | A kind of image definition recognition methods, device and storage medium | |
CN105388147A (en) | Detection method for body fluid based on special test paper | |
CN106778695A (en) | A kind of many people's examing heartbeat fastly methods based on video | |
EP2720030B1 (en) | Medicine management system and method using the same | |
CN109697719A (en) | A kind of image quality measure method, apparatus and computer readable storage medium | |
CN209029110U (en) | Chinese medicine facial diagnosis is health management system arranged | |
CN106340000A (en) | Bone age assessment method | |
CN113421230A (en) | Vehicle-mounted liquid crystal display light guide plate defect visual detection method based on target detection network | |
US20200376491A1 (en) | Portable urine detection device and method | |
CN107066779A (en) | Self-service body parameter inspection method and system based on biological specimen color | |
CN109241948A (en) | A kind of NC cutting tool visual identity method and device | |
CN109946290A (en) | A kind of portable urine detector and method | |
CN108287161A (en) | A kind of Intelligent tea organoleptic evaluation method and system | |
CN109991216A (en) | A kind of uroscopy instrument test strips color identification method | |
US7837327B2 (en) | Contact lens user support system and support method | |
CN111795919B (en) | Automatic bone marrow cell morphology detection system and working method thereof | |
CN109406506B (en) | Shared self-testing health terminal and testing method | |
CN105550668A (en) | Apparatus for collecting biological features of living body and method for identifying biological features of living body | |
CN107300360A (en) | A kind of shaft size fast algorithm of detecting of rain fed crops seed three | |
CN114486902A (en) | Quality detection system and method | |
CN115343279A (en) | Test paper-based skin oil evaluation method | |
EP0545348A1 (en) | Blood cell analyzer | |
CN110960194B (en) | Ear phase acquisition device and acquisition method |
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 |