CN110007068B - Urine leakage detection method - Google Patents
Urine leakage detection method Download PDFInfo
- Publication number
- CN110007068B CN110007068B CN201910226761.1A CN201910226761A CN110007068B CN 110007068 B CN110007068 B CN 110007068B CN 201910226761 A CN201910226761 A CN 201910226761A CN 110007068 B CN110007068 B CN 110007068B
- Authority
- CN
- China
- Prior art keywords
- sample
- block
- image
- medicine
- dripping
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
- G01N33/52—Use of compounds or compositions for colorimetric, spectrophotometric or fluorometric investigation, e.g. use of reagent paper and including single- and multilayer analytical elements
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N35/00—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor
- G01N35/00584—Control arrangements for automatic analysers
- G01N35/00594—Quality control, including calibration or testing of components of the analyser
- G01N35/00613—Quality control
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Immunology (AREA)
- Hematology (AREA)
- Chemical & Material Sciences (AREA)
- Urology & Nephrology (AREA)
- Analytical Chemistry (AREA)
- Quality & Reliability (AREA)
- Molecular Biology (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Biochemistry (AREA)
- Cell Biology (AREA)
- Medicinal Chemistry (AREA)
- Food Science & Technology (AREA)
- Biotechnology (AREA)
- Microbiology (AREA)
- Image Analysis (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention provides a urine leakage detection method, which comprises the steps of carrying out dripping sample on each medicine block of a detection test paper, wherein an original image of the detection test paper is obtained, and edge recognition is carried out to obtain a detection image; determining the central position of each medicine block in the detection image according to the actual size of the detection test paper; cutting the detection image according to the central position of each medicine block in the detection image and the actual size of each medicine block on the detection test paper to obtain a segmentation image corresponding to a single medicine block; processing and calculating the segmentation images corresponding to the dripping sample blocks by using an adjusted cosine similarity algorithm or a high-frequency signal distribution statistical algorithm to obtain characteristic parameters of the segmentation images; and judging whether each drop sample medicine block leaks according to the characteristic parameters of each segmented image through image comparison.
Description
Technical Field
The invention relates to the technical field of medical instruments, in particular to a method for detecting leakage and dripping of urine.
Background
Urine tests are one of three general items in clinical tests in modern medicine and play an important role in the diagnosis of diseases. The full-automatic urine analyzer consists of a liquid path system, a sample introduction system, a strip selection system, a detection system, an electronic system and a software system. The liquid path system is responsible for dripping the sample on the test paper to let the urine sample react with the dropping sample medicine piece on the test paper, realize the detection and analysis of urine composition through detecting system. However, the liquid path system has many pipelines and pump valves, and there may be phenomena of aging of the pipelines, residual urine components and the like after long use, which may cause the liquid path system to be blocked or have poor air tightness, resulting in the possibility of leakage of the liquid path system during sample dropping.
Disclosure of Invention
The invention aims to provide a method for detecting leakage of urine and a method for detecting whether leakage of a sample dropping block on test paper occurs.
In order to achieve the above object, the present invention provides a method for detecting urine leakage, which is used for detecting whether a urine sample is dropped on each block of a test strip, and the method comprises the following steps:
dropping samples on the medicine blocks of the detection test paper;
acquiring an original image of the test paper and performing edge recognition to acquire a detection image;
determining the central position of each medicine block in the detection image according to the actual size of the detection test paper;
cutting the detection image according to the central position of each medicine block in the detection image and the actual size of each medicine block on the detection test paper to obtain a segmentation image corresponding to each medicine block;
processing and calculating the segmentation image corresponding to each dripping sample medicine block by utilizing a cosine similarity adjustment algorithm or a high-frequency signal distribution statistical algorithm to obtain characteristic parameters of the segmentation image corresponding to each dripping sample medicine block;
and judging whether each dripping sample medicine block leaks or not and the position of the dripping sample medicine block according to the characteristic parameters of each segmented image.
The step of obtaining the characteristic parameters of each segmented image by using the adjusted cosine similarity algorithm comprises the following steps:
under the HSV color space, extracting the image characteristics of the segmented image corresponding to each sample dropping block, and fitting the image characteristics into a one-dimensional characteristic vector to obtain the one-dimensional characteristic vector of the segmented image corresponding to each sample dropping block;
acquiring an image feature vector of the non-dripping sample medicine block;
and performing cosine similarity adjustment calculation on the one-dimensional characteristic vector corresponding to each sample dripping block and the image characteristic vector of the sample dripping block to obtain characteristic parameters of each segmented image, wherein the characteristic parameters are cosine similarity contrast parameters.
Optionally, when the cosine similarity contrast parameter corresponding to the sample dropping block is within a first set range, it is determined that the sample dropping block has dropped; and when the cosine similarity contrast parameter corresponding to the sample dropping block is out of the first set range, judging that the sample dropping block does not drop.
Optionally, image feature vectors corresponding to the plurality of non-dripping sample drug blocks are collected and adjusted for cosine similarity calculation in a circulating manner, so as to obtain a fluctuation interval of cosine similarity contrast parameters of the non-dripping sample drug blocks, and the first set range is the fluctuation interval of the cosine similarity contrast parameters.
Optionally, the step of obtaining the feature parameters of each segmented image by using a high-frequency signal distribution statistical algorithm includes:
under the RGB color space, acquiring the position distribution and the quantity of high-frequency signals of the segmented image corresponding to each sample drop block, and acquiring the characteristic parameters of the segmented image corresponding to each sample drop block, wherein the characteristic parameters are high-frequency information parameters.
Optionally, when the high-frequency information parameter corresponding to the sample dropping block is within a second set range, it is determined that the sample dropping block has dropped; and when the high-frequency information parameter corresponding to the sample dropping medicine block is out of the second set range, judging that the sample dropping medicine block does not leak.
Optionally, the position distribution and the number of the high-frequency signals corresponding to the plurality of non-dripping sample blocks are collected to obtain a fluctuation interval of the high-frequency information parameters of the non-dripping sample blocks, and the second set range is the fluctuation interval of the high-frequency information parameters.
The invention has the following beneficial effects:
1. acquiring characteristic parameters of a segmented image corresponding to the dripping sample dripping block in an image comparison mode, and acquiring information of whether the dripping sample dripping block leaks or not in the image comparison mode;
2. through adding the missing drop recognition function, remind the user to take place the position of the dropping sample medicine piece of the missing drop and the dropping sample medicine piece of the missing drop, avoid not dropping the sample dropping sample medicine piece and produce the inaccurate result of test, make the detection precision higher.
Drawings
Fig. 1 is a flowchart of a urine leakage detection method according to an embodiment of the present invention.
Detailed Description
The following describes in more detail embodiments of the present invention with reference to the schematic drawings. Advantages and features of the present invention will become apparent from the following description and claims. It is to be noted that the drawings are in a very simplified form and are not to precise scale, which is provided for the purpose of facilitating and clearly illustrating embodiments of the present invention.
As shown in fig. 1, the present embodiment provides a method for detecting leakage of urine, which is used to detect whether a urine sample is dropped on each block of a test strip, and includes:
step S1: and carrying out dropping sample on each medicine block of the detection test paper.
Step S2: and acquiring an original image of the detection test paper, performing edge recognition to acquire an edge coordinate, determining the actual position of the edge coordinate in the original image, and acquiring a detection image which only contains image information of the detection test paper.
Step S3: and determining the central position of each medicine block in the detection image from the transverse direction and the longitudinal direction according to the ratio between the actual size and the edge coordinate of the detection test paper.
Step S4: and cutting the detection image according to the central position of each medicine block in the detection image and the actual size of each medicine block on the detection test paper to obtain a segmentation image corresponding to a single medicine block, so that the segmentation image of each medicine block is conveniently processed, and the dripping sample medicine blocks and the non-dripping sample medicine blocks are conveniently distinguished.
Step S5: processing and calculating the segmentation images corresponding to the dripping medicine blocks by utilizing a cosine similarity adjustment algorithm or a high-frequency signal distribution statistical algorithm to obtain characteristic parameters of the segmentation images;
specifically, the step of obtaining the feature parameters of each segmented image by using the adjusted cosine similarity algorithm includes:
step S51: under the HSV color space, extracting the image characteristics of the segmented image corresponding to each sample dropping block, and fitting the image characteristics into a one-dimensional characteristic vector to obtain the one-dimensional characteristic vector of the segmented image corresponding to each sample dropping block;
step S52: acquiring image feature vectors of the non-dripping sample medicine blocks (the image feature vectors of the non-dripping sample medicine blocks are calibrated before delivery);
step S53: and performing cosine similarity adjustment calculation on the one-dimensional characteristic vector of the segmented image corresponding to each dripping sample medicine block and the image characteristic vector of the medicine block not dripping the sample to obtain the characteristic parameter of each segmented image, wherein the characteristic parameter is a cosine similarity contrast parameter X1.
Step S6: when the cosine similarity contrast parameter X1 corresponding to the sample dropping block is within a first set range X2, judging that the sample dropping block has no dropping; and when the cosine similarity contrast parameter X1 corresponding to the sample dropping block is out of the first set range X2, judging that the sample dropping block does not drop. The method comprises the steps of collecting image feature vectors corresponding to a plurality of non-dripping sample medicine blocks (large sample data) and circularly adjusting cosine similarity calculation to obtain a fluctuation interval of cosine similarity contrast parameters of the non-dripping sample medicine blocks, and setting a first set range X2 as the fluctuation interval of the cosine similarity contrast parameters. And judging whether the dripping sample medicine block leaks or not according to the correspondence between each segmentation image and the dripping sample medicine block, and then finding the position of the dripping sample medicine block according to the segmentation image.
The step of acquiring the characteristic parameters of each segmented image by using a high-frequency signal distribution statistical algorithm comprises the following steps:
step S51': under an RGB color space, acquiring the position distribution and the quantity of high-frequency signals of the segmented image corresponding to each sample drop block, and acquiring the characteristic parameters of the segmented image corresponding to each sample drop block, wherein the characteristic parameters are high-frequency information parameters Y1. Because the distribution range of the high-frequency signals of the detection images of the dripping sample medicine blocks is narrow and the distribution quantity is obviously reduced (the high-frequency signals of the medicine blocks which are not dripped are calibrated before leaving the factory), the high-frequency signals of the detection images of the medicine blocks which are not dripped are wide in distribution and large in quantity, and can be distinguished based on the distribution.
Step S6': when the high-frequency information parameter Y1 corresponding to the sample dripping block is within a second set range Y2, judging that the sample dripping block has no dripping; and when the high-frequency information parameter Y1 corresponding to the medicine block is out of the second set range Y2, judging that the medicine block does not leak. The position distribution and the number of the high-frequency signals corresponding to a plurality of non-dripping sample blocks (large sample data) are collected to obtain the fluctuation interval of the high-frequency information parameters of the non-dripping sample blocks, and the second setting range Y2 is set as the fluctuation interval of the high-frequency information parameters.
The above description is only a preferred embodiment of the present invention, and does not limit the present invention in any way. It will be understood by those skilled in the art that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (2)
1. A urine leakage detection method is used for detecting whether a urine sample is dripped on each medicine block of a detection test paper, and is characterized by comprising the following steps:
dropping samples of the medicine blocks of the detection test paper;
acquiring an original image of the test paper, performing edge identification to acquire an edge coordinate, and determining the actual position of the edge coordinate in the original image to obtain a detection image;
determining the central position of each medicine block in the detection image according to the actual size of the detection test paper; the method comprises the following specific steps: determining the central position of each medicine block in the detection image from the transverse direction and the longitudinal direction according to the proportion between the actual size and the edge coordinate of the detection test paper;
cutting the detection image according to the central position of each medicine block in the detection image and the actual size of each medicine block on the detection test paper to obtain a segmentation image corresponding to each medicine block;
processing and calculating the segmentation image corresponding to each sample drop medicine block by using an adjusted cosine similarity algorithm to obtain the characteristic parameters of the segmentation image corresponding to each sample drop medicine block;
judging whether each dripping sample medicine block leaks or not and the position of the dripping sample medicine block according to the characteristic parameters of each segmented image;
specifically, the step of obtaining the feature parameters of each segmented image by using the adjusted cosine similarity algorithm includes:
under the HSV color space, extracting the image characteristics of the segmented image corresponding to each sample dropping block, and fitting the image characteristics into a one-dimensional characteristic vector to obtain the one-dimensional characteristic vector of the segmented image corresponding to each sample dropping block;
acquiring an image feature vector of the non-dripping sample medicine block;
performing cosine similarity adjustment calculation on the one-dimensional characteristic vector corresponding to each sample dripping block and the image characteristic vector of the sample dripping block to obtain characteristic parameters of each segmented image, wherein the characteristic parameters are cosine similarity contrast parameters;
specifically, the step of judging whether each sample drop block is dropped and the position of the dropped sample block according to the characteristic parameters of each segmented image comprises the following steps:
collecting image characteristic vectors corresponding to a plurality of non-dripping sample medicine blocks and circularly adjusting cosine similarity calculation to obtain a fluctuation interval of cosine similarity contrast parameters of the non-dripping sample medicine blocks, wherein a first set range is the fluctuation interval of the cosine similarity contrast parameters; when the cosine similarity contrast parameter corresponding to the sample dripping block is in a first set range, judging that the sample dripping block has no dripping; and when the cosine similarity contrast parameter corresponding to the sample dropping block is out of the first set range, judging that the sample dropping block does not drop, judging whether the sample dropping block drops according to the corresponding segmented image and the sample dropping block, and finding the position of the sample dropping block according to the segmented image.
2. The method for detecting the leakage of urine according to claim 1, wherein when the high frequency information parameter corresponding to the sample block is within a second set range, the sample block is determined to be leaked; and when the high-frequency information parameter corresponding to the sample dropping medicine block is out of the second set range, judging that the sample dropping medicine block does not drop.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910226761.1A CN110007068B (en) | 2019-03-25 | 2019-03-25 | Urine leakage detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910226761.1A CN110007068B (en) | 2019-03-25 | 2019-03-25 | Urine leakage detection method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110007068A CN110007068A (en) | 2019-07-12 |
CN110007068B true CN110007068B (en) | 2022-07-08 |
Family
ID=67167985
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910226761.1A Active CN110007068B (en) | 2019-03-25 | 2019-03-25 | Urine leakage detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110007068B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110412257B (en) * | 2019-07-22 | 2022-05-03 | 深圳市预防宝科技有限公司 | Test paper block positioning method combining manual calibration and star ray algorithm |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1948603A (en) * | 2006-11-10 | 2007-04-18 | 苏州大学 | Method of identifying woven fabric defect |
CN101400297A (en) * | 2006-03-10 | 2009-04-01 | 哈达斯·莱维 | Method and system for automated sampling and analysis using a personal sampler device |
CN103745219A (en) * | 2014-01-28 | 2014-04-23 | 爱威科技股份有限公司 | Method and device for classifying urine casts |
CN104200239A (en) * | 2014-09-09 | 2014-12-10 | 河海大学常州校区 | Image feature fusion identification based signature authentic identification system and method |
CN105335658A (en) * | 2014-08-15 | 2016-02-17 | 张钰昕 | Application system for performing urine analysis by using camera function of intelligent mobile device |
CN106546581A (en) * | 2016-11-02 | 2017-03-29 | 长沙云知检信息科技有限公司 | Detection paper card intelligent checking system and detection paper card intelligent analysis method |
CN107862350A (en) * | 2016-09-29 | 2018-03-30 | 网易(杭州)网络有限公司 | Test paper detecting method, apparatus and system |
CN108152278A (en) * | 2017-11-22 | 2018-06-12 | 沈阳普泽众康医药科技有限公司 | A kind of urine detection method and device |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1997005574A1 (en) * | 1995-07-27 | 1997-02-13 | Imperial Cancer Research Technology Limited | Raw data segmentation and analysis in image tomography |
US9239281B2 (en) * | 2008-04-07 | 2016-01-19 | Hitachi High-Technologies Corporation | Method and device for dividing area of image of particle in urine |
JP5463269B2 (en) * | 2010-11-24 | 2014-04-09 | 日本電信電話株式会社 | Feature figure addition method, feature figure detection method, feature figure addition device, feature figure detection device, and program |
CN105096293B (en) * | 2014-04-30 | 2018-12-07 | 西门子医疗保健诊断公司 | Method and apparatus for handling the block to be processed of sediment urinalysis image |
CN107392849B (en) * | 2017-06-27 | 2021-02-05 | 中国航空工业集团公司北京长城航空测控技术研究所 | Target identification and positioning method based on image subdivision |
-
2019
- 2019-03-25 CN CN201910226761.1A patent/CN110007068B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101400297A (en) * | 2006-03-10 | 2009-04-01 | 哈达斯·莱维 | Method and system for automated sampling and analysis using a personal sampler device |
CN1948603A (en) * | 2006-11-10 | 2007-04-18 | 苏州大学 | Method of identifying woven fabric defect |
CN103745219A (en) * | 2014-01-28 | 2014-04-23 | 爱威科技股份有限公司 | Method and device for classifying urine casts |
CN105335658A (en) * | 2014-08-15 | 2016-02-17 | 张钰昕 | Application system for performing urine analysis by using camera function of intelligent mobile device |
CN104200239A (en) * | 2014-09-09 | 2014-12-10 | 河海大学常州校区 | Image feature fusion identification based signature authentic identification system and method |
CN107862350A (en) * | 2016-09-29 | 2018-03-30 | 网易(杭州)网络有限公司 | Test paper detecting method, apparatus and system |
CN106546581A (en) * | 2016-11-02 | 2017-03-29 | 长沙云知检信息科技有限公司 | Detection paper card intelligent checking system and detection paper card intelligent analysis method |
CN108152278A (en) * | 2017-11-22 | 2018-06-12 | 沈阳普泽众康医药科技有限公司 | A kind of urine detection method and device |
Also Published As
Publication number | Publication date |
---|---|
CN110007068A (en) | 2019-07-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106546581B (en) | Test paper detection card intelligent detection system and test paper detection card intelligent analysis method | |
JP7228585B2 (en) | Method and apparatus for making analytical measurements | |
JP7278276B2 (en) | Methods and apparatus for making analytical measurements based on chromogenic reactions | |
CN112818988B (en) | Automatic identification reading method and system for pointer instrument | |
CN112257676B (en) | Pointer type instrument reading method and system and inspection robot | |
US6697509B2 (en) | Method and apparatus for scoring the uptake of markers in cells | |
CN101324452A (en) | Method for automatically detecting pointer instrument | |
CN113065538A (en) | Pressure sensor detection method, device and equipment based on image recognition | |
CN110007068B (en) | Urine leakage detection method | |
CN106204523A (en) | A kind of image quality evaluation method and device | |
CN111950553A (en) | Automatic alignment method and device for pointer instrument | |
CN116228776A (en) | Electromechanical equipment welding defect identification method and system | |
CN110174711A (en) | Terminal device and its foreign bodies detection evaluation of result method, computer storage medium | |
CN113554688B (en) | O-shaped sealing ring size measurement method based on monocular vision | |
CN114694128A (en) | Pointer instrument detection method and system based on abstract metric learning | |
CN113989513A (en) | Method for recognizing reading of square pointer type instrument | |
CN112115896A (en) | Instrument panel pointer reading prediction method and device, computer equipment and storage medium | |
CN109215068B (en) | Image magnification measuring method and device | |
JP3745075B2 (en) | Film thickness measuring device | |
CN107389677B (en) | Method and device for detecting quality of flannelette fluff | |
Chen et al. | A robust and automated cell counting method in quantification of digital breast cancer immunohistochemistry images | |
CN115908429B (en) | Method and system for detecting grinding precision of foot soaking powder | |
CN114264407B (en) | Method for detecting measurement accuracy of pointer type pressure gauge, computer medium and computer | |
CN113447381B (en) | Brinell hardness detection method and detection system | |
CN118172328A (en) | Image analysis method, system and device based on portable concentration meter |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |