CN117849043A - Urine test paper analysis device and detection method thereof - Google Patents

Urine test paper analysis device and detection method thereof Download PDF

Info

Publication number
CN117849043A
CN117849043A CN202410263825.6A CN202410263825A CN117849043A CN 117849043 A CN117849043 A CN 117849043A CN 202410263825 A CN202410263825 A CN 202410263825A CN 117849043 A CN117849043 A CN 117849043A
Authority
CN
China
Prior art keywords
image
test paper
color
strip
matrix
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
Application number
CN202410263825.6A
Other languages
Chinese (zh)
Inventor
黄建邦
王哲
陈启梦
于源华
宫平
庞春颖
张昊
孟祥凯
李欣悦
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Changchun University of Science and Technology
Original Assignee
Changchun University of Science and Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Changchun University of Science and Technology filed Critical Changchun University of Science and Technology
Priority to CN202410263825.6A priority Critical patent/CN117849043A/en
Publication of CN117849043A publication Critical patent/CN117849043A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/75—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated
    • G01N21/77—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated by observing the effect on a chemical indicator
    • G01N21/78—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated by observing the effect on a chemical indicator producing a change of colour
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Immunology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Urology & Nephrology (AREA)
  • Biomedical Technology (AREA)
  • Hematology (AREA)
  • Biotechnology (AREA)
  • Food Science & Technology (AREA)
  • Medicinal Chemistry (AREA)
  • Microbiology (AREA)
  • Cell Biology (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Plasma & Fusion (AREA)
  • Investigating Or Analysing Biological Materials (AREA)

Abstract

The invention discloses a urine test paper analysis device and a detection method thereof, relating to the field of test paper detection analysis, wherein the device comprises: the system comprises a control mechanism, a quantitative strip, a test paper transmission platform, an optical system, a video acquisition card, a computer and a display; the test paper strip is placed on the test paper transmission platform and is driven to move to different positions; the control mechanism controls the sample loading amount and the reaction time of the quantitative strip on the test strip; the optical system collects images on the test paper strip, sends the images to the computer through the video collection card, and displays the images through the display. The invention can more accurately quantify the sample, ensure the stability of the reaction between the sample and the test paper, and reduce errors caused by different sample amounts. The reaction time of the urine sample and the test paper is controlled, the influence of oxidation on the reaction result caused by insufficient reaction or overlong reaction time is prevented, and the accuracy of the reaction is ensured. Based on the image analysis method, the concentration of each component in the urine sample can be accurately judged.

Description

Urine test paper analysis device and detection method thereof
Technical Field
The invention relates to the field of test paper detection and analysis, in particular to a urine test paper analysis device and a detection method thereof.
Background
Urine analyzer is an important tool for detecting urinary system, and is also the first choice for pathological diagnosis, examination and later review. The change of the content of each component in urine produced by human body can reflect the change of health condition. The popular detection method in the current urine detector is to detect the color recognition concentration in the test strip image by adopting a computer vision technology, and has the following problems:
1. the user holds inaccurately to test time, and the reagent on the test paper piece begins to read the numerical value when reacting inadequately with the urine sample, leads to the result inaccurate.
2. Because urine sample is easy to be attached to the test paper block, the instrument light source is easy to form a highlight reflecting point in the image, and the calculation of the color value is influenced.
3. Granular pixel distribution may appear on the reacted test paper block, and the result is inaccurate due to direct color mean value identification.
4. The current color recognition algorithm has poor noise filtering effect.
5. The RGB color space-based method is easily affected by illumination intensity, and the recognition result is unstable.
6. Based on the HSV color space method, hue values cannot be accurately calculated when color blocks are close to black, white and gray, and a recognition result is unstable.
Disclosure of Invention
The invention provides a urine test paper analysis device and a detection method thereof, which solve the problems existing in the prior art.
The technical scheme of the invention is as follows:
a urine test paper analysis device, the device comprising: the system comprises a control mechanism, a quantitative strip, a test paper transmission platform, an optical system, a video acquisition card, a computer and a display; the test paper strip is placed on the test paper transmission platform and is driven to move to different positions; the control mechanism controls the sample loading amount and the reaction time of the quantitative strip on the test strip; the optical system collects images on the test paper strip, sends the images to the computer through the video collection card, and displays the images through the display.
Preferably, the control mechanism includes: the sample adding module and the reaction timing module; the sample adding module controls the sample adding amount of the quantitative strip to the test strip; the reaction timing module sets the reaction time of the test strip.
Preferably, the optical system includes: a white LED light source and a planar array CCD camera; and the test strip is irradiated by the white LED light source, and the area array CCD camera shoots an image of the test strip.
Preferably, the computer includes: the device comprises a test paper analysis image processing module, a test paper analysis image extraction module and a concentration calculation module; the test paper analysis image processing module removes the highlight of the image based on a bicubic interpolation method; the test paper analysis image extraction module finds out the place with the most sufficient reaction in the image, extracts the region of interest and obtains the color block diagram of each detection item; the concentration calculation module converts the image from the RGB color space to the HSV color space, takes Euclidean distance between the image to be detected and the image of the blank comparison module in the HSV color space as a characteristic value, and substitutes the value into a corresponding standard concentration gradient curve obtained by pre-experiment to obtain a concentration value of a detection item.
A method of detecting a urine test paper analysis device, the method comprising the steps of:
step 1: the sample adding module is used for adding samples on the test strip, and after the reaction is carried out for a set time, the image is shot by the area array CCD camera under the irradiation of the white LED light source;
step 2: the test paper analysis image processing module removes the highlight of the image based on a bicubic interpolation method and extracts the outline;
step 3: performing perspective transformation on the image, extracting a rectangular image with the same actual size as the test paper block, and identifying the detected type;
step 4: finding out the place with the most sufficient reaction in the perspective transformed image in the step 3 based on the thermodynamic diagram, extracting the region of interest, and obtaining a color block diagram of each detection item;
step 5: performing polynomial nonlinear color correction on the color block diagram of each detection item in the step 4 based on a matrix conversion method, analyzing a standard colorimetric card to obtain a gray level deviation curve, constructing a polynomial, and fitting a similar nonlinear relation to correct the color deviation;
step 6: and (3) converting the color block diagram obtained in the step (5) from an RGB color space to an HSV color space, taking Euclidean distance between an image to be detected and an image of a blank comparison module in the HSV color space as a characteristic value, and substituting the characteristic value into a corresponding standard concentration gradient curve obtained by a pre-experiment, so that the concentration value of the detection item can be obtained.
Preferably, the removing the highlight in step 2 includes:
step 201: dividing the image into blocks, wherein the average brightness of each sub-block forms a sub-block brightness matrix;
step 202: subtracting the average brightness of the sub-block from the average brightness of the full graph to obtain a brightness difference matrix, expanding the brightness difference matrix to the size of the full graph by using a bicubic interpolation method, and estimating the illumination distribution of the full graph;
step 203: subtracting the original gray level image from the calculated illumination distribution diagram to finish the highlight processing of the image.
Preferably, extracting the contour in the step 2 includes:
step 204: adopting a Gaussian smoothing filter to complete image filtering and remove Gaussian noise;
step 205: morphological processing is carried out on the filtered image, interference color blocks are eliminated through image opening operation, and a target color block area is filled through closing operation;
step 206: using adaptive threshold calculation to separate the background area from the foreground area;
step 207: and carrying out edge extraction on the images by adopting Canny operator edge detection to obtain the respective images of each detection item.
Preferably, the step 5 includes: step 501: the RGB value of the ith color block in the actual image is Ri, gi and Bi, and the standard value of the ith color block in the standard color card is R0i, G0i and B0i; matrix V [ J ]][I]A polynomial matrix composed of polynomials constructed for RGB values in an actual photographed image, each behavior R, G, B, RG, RB, BG, R, B, G, RG, RB, BG, BR, GR, GB pattern, R 3 ，G 3 ，B 3 RGB, where j=19-bit polynomial term, I is the number of color patches of the color chart;
step 502: x=a T ·V，X[3][I]A [ J ] is a matrix of standard RGB values for color chart color blocks][3]To the required mapping relation matrix, V [ J ]][I]A polynomial regression matrix;
step 503: the matrix A is optimized by a least square method to obtain A= (V.V) T ) -1 ·(V·X T )；
Step 504: the input image X processed by the steps in [3][M]Polynomial matrix V composed of RGB values in [19][M]Corrected output image X out [3][M]=A T ·V in 。
The invention has the beneficial effects that: the invention provides a simple and accurate quantitative strip device, which can more accurately quantify samples, ensure the stability of the reaction between the samples and test paper and reduce errors caused by different sample amounts. The reaction time of the urine sample and the test paper is controlled, the influence of oxidation on the reaction result caused by insufficient reaction or overlong reaction time is prevented, and the accuracy of the reaction is ensured. In the process of removing the highlight of the image, the matrix processing is carried out by adopting a bicubic interpolation method, so that the speed is high, and the time consumption is low. In the process of extracting the solid color block image, a thermodynamic diagram method is innovatively adopted to extract the area with the best reaction, and a polynomial nonlinear regression algorithm is adopted to correct the color based on a standard colorimetric card, so that the precise solid color block image of the optimal reaction area is obtained. Based on the image analysis method, the concentration of each component in the urine sample can be accurately judged.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a schematic diagram of a urine test paper analysis device;
FIG. 2 is a flow chart of an analysis method of the urine test paper analyzer.
In the figure: 1. the device comprises a control mechanism, 101, a sample adding module, 102, a reaction timing module, 2, a quantitative strip, 201, a sample tank, 3, a test strip, 4, a test strip transmission platform, 5, an optical system, 501, a white LED light source, 502, a planar array CCD camera, 6, a video acquisition card, 7, a computer, 701, a test strip analysis image processing module, 702, a test strip analysis image extraction module, 703, a concentration calculation module, 8 and a display.
Detailed Description
Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless it is specifically stated otherwise.
The following description of at least one exemplary embodiment is merely exemplary in nature and is in no way intended to limit the invention, its application, or uses.
Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any specific values should be construed as merely illustrative, and not a limitation. Thus, other examples of exemplary embodiments may have different values.
As shown in fig. 1, a urine test paper analysis device, the device comprising: the device comprises a control mechanism 1, a quantitative strip 2, a test paper transmission platform 4, an optical system 5, a video acquisition card 6, a computer 7 and a display 8. The test paper 3 is placed on the test paper transmission platform 4, and the test paper 3 is driven to move to different positions; the control mechanism 1 controls the sample adding amount and the reaction time of the quantitative strip 2 to the test strip 3; the optical system 5 collects the image on the test strip 3, sends the image to the computer 7 through the video collection card 6 and displays the image through the display 8; the control mechanism 1 mainly comprises a sample adding module 101 and a reaction timing module 102; the optical system 5 includes a white LED light source 501 and an area array CCD camera 502. In this embodiment, the urine sample is added into the sample tank 201 in the quantitative strip 2, the test strip 3 is placed at the designated position of the test strip transmission platform 4, and the stepper motor drives the deceleration strip to move according to the preset program of the test strip transmission platform 4, so as to move the test strip 3 to the marking position. The sample adding module 101 in the control mechanism 1 controls the quantitative strip 2 to drop the urine sample onto the test strip 3, the reaction timing module 102 ensures that the sample and the test strip 3 react completely, and the test strip 3 is brought to the area where the optical system 5 is located by the test strip transmission platform 4. The test strip 3 is irradiated by the white LED light source 501, the array CCD camera 502 shoots the image of the test strip 3, shot data are stored in the video acquisition card 6 and transmitted to the computer 7 through the PCI port, a series of processing is carried out on the obtained image, the computer 7 judges whether the image has an abnormal condition, and if the image has the abnormal condition, the subsequent steps are stopped.
The computer includes: the test paper analysis image processing module 701, the test paper analysis image extraction module 702 and the concentration calculation module 703. The test paper analysis image processing module 701 removes the highlight of the image based on a bicubic interpolation method; the test paper analysis image extraction module 702 finds the place with the most sufficient reaction in the image, extracts the region of interest and obtains the color block diagram of each detection item; the concentration calculation module 703 converts the image from RGB color space to HSV color space, and uses euclidean distance between the image to be measured and the image of the blank control module in HSV color space as a characteristic value, wherein the image to be measured refers to the image shot after the sample is dripped onto the test paper for reaction, and the image of the blank control module refers to the test paper image without the sample dripped; substituting the characteristic value into a corresponding standard concentration gradient curve obtained by a pre-experiment to obtain the concentration value of the detection item.
As shown in fig. 2, an analysis method of the urine test paper analysis device specifically comprises the following steps:
1) The urine test paper analyzes the image photographing.
Urine sample is added to the sample well 201 in the quantitative strip 2, and the test strip 3 is placed at a specified position. Pressing the power key starting device, after the initialization of the system is completed, the test paper transmission platform 4 drives the deceleration strip to move according to a preset program by the stepping motor, and the test paper strip 3 is moved to the marking position. The sample adding module 101 in the control mechanism 1 controls the quantitative strip 2 to drop the urine sample onto the test strip 3, the reaction timing module 102 ensures that the sample and the test strip 3 react completely, and the test strip 3 is moved to the area where the optical system 5 is located by the test strip transmission platform 4. The test strip 3 is irradiated by a white LED light source 501, and the array CCD camera 502 shoots images, and the shot images are stored in the video acquisition card 6 and transmitted to the computer 7 through the PCI port.
2) The test paper analysis image processing module 701 removes image highlights and contour extraction based on bicubic interpolation.
201 Firstly, the photographed image is required to be segmented, the average brightness of each sub-block is obtained to form a sub-block brightness matrix, and the segmentation standard only needs to meet the condition that the width and the height are integers.
202 And finally, expanding the brightness difference matrix into the size of the full graph by using a bicubic interpolation method to estimate the illumination distribution of the full graph.
203 The bi-cubic interpolation method is mainly different from the non-linear regression method based on wavelets, has no special requirements on the width and the height of the image, and takes time sequence and processing quality into comprehensive consideration optimally. And finally, subtracting the original image from the calculated illumination distribution map to finish the illumination treatment of the image.
204 Considering that in the image acquisition process, the area array CCD camera 502 introduces certain noise due to factors such as devices and the like, and usually takes Gaussian noise as a main factor, and an analysis algorithm adopts a Gaussian smoothing filter to complete the image filtering work.
205 The method comprises the steps of performing morphological processing on an image after filtering, firstly performing open operation on the image to eliminate some interference color blocks with smaller pixels, then filling a target color block area by using closed operation, wherein the main purpose of the morphological processing is to divide independent elements of the image, reduce the interference of small areas in the image and lay a foundation for threshold segmentation.
206 And (3) automatically acquiring an image threshold value by using an Ojin method and calculating and separating a background area and a foreground area by using the Ojin method to perform self-adaptive threshold value.
207 After the filtering, morphological processing and threshold segmentation image operation, the edge of the urine analysis test paper image is obvious and easy to position, and the edge detection of the Canny operator is directly adopted to extract the edge of the image, so that the respective image of each detection item is obtained.
3) The test paper analysis image processing module 701 performs perspective transformation processing on each image extracted in step 2), extracts a rectangular image of the same actual size as the test paper strip 3, and identifies the type detected.
301 The image processed in the step 2) is easy to locate, the coordinates of the upper left corner, the lower left corner, the upper right corner and the lower right corner of the image are obtained through coordinate analysis, perspective transformation is carried out, and the image is converted into a rectangular image with the same actual size as the test strip 3.
302 According to the sequence of shooting test paper, the types of detection are as follows: 0 is vitamin C, 1 is leucocyte, 2 is urobilinogen, 3 is bilirubin, 4 is occult blood, 5 is nitrite, 6 is pH value, 7 is protein, 8 is urine specific gravity, 9 is ketone body, 10 is glucose and 11 is microalbumin.
4) The test paper analysis image extraction module 702 finds the most fully reacted place in the image after the perspective transformation in step 3) based on the thermodynamic diagram, extracts the ROI (region of interest), and obtains a color block diagram for each test item.
401 Because the reaction process cannot ensure that each region of the test strip 3 completely reacts with the sample, and the color of pixel points in a plurality of regions is different due to various factors, the region with the deepest color or the shallowest color (different detection items) can be found out through a thermodynamic diagram image algorithm, and the region is the region with the best reaction, and the rectangular region of the part is extracted by utilizing an ROI algorithm.
5) The test paper analysis image extraction module 702 respectively carries out polynomial nonlinear color correction on each extracted image in the step 4), analyzes a standard colorimetric card to obtain a gray level deviation curve, constructs a polynomial, and fits a similar nonlinear relationship to correct the color deviation.
501 The RGB value of the ith color block in the actual rectangular image is Ri, gi and Bi, and the standard value of the ith color block in the standard color card is R0i, G0i and B0i.
502 Matrix V [ J ]][I]A polynomial matrix composed of polynomials constructed for RGB values in an actual photographed image, each behavior R, G, B, RG, RB, BG, R, B, G, RG, RB, BG, BR, GR, GB pattern, R 3 ，G 3 ，B 3 RGB, where j=19-bit polynomial term, I is the number of color patches of the color chart.
503 Mapping relation x=a) T ·V，A T Transpose of matrix A, X3][I]A [ J ] is a matrix of standard RGB values for color chart color blocks][3]To the required mapping relation matrix, V [ J ]][I]Is a polynomial regression matrix.
504 Defining a residual E as an RGB value matrix V of an actual photographed imageAnd the difference between the color card standard RGB value matrix X and the color card standard RGB value matrix X after mapping is carried out through the mapping relation A. The definition of the residual is as follows: e=x-a T V; the goal of the least squares method is to find a mapping a such that the sum of squares of the residuals is minimized: min E 2 =||X-A T ·V|| 2 The method comprises the steps of carrying out a first treatment on the surface of the By taking the partial derivative of the objective function, making the derivative equal to zero, the closed-form solution of the least squares method can be obtained: a= (v.v T ) -1 (V·X T ). Wherein, represents a matrix multiplication, -1 representing the inverse of the matrix, V T Representing the transpose of matrix V.
505 Input image X processed by the above five steps in [3][M]Polynomial matrix V composed of RGB values in [19][M]Corrected output image X out [3][M]=A T ·V in . M represents the number of pixels in the image.
6) The concentration calculation module 703 converts the obtained image from the RGB color space to the HSV color space, and takes EDs (euclidean distance) of the image to be measured and the image of the blank control module in the HSV color space as characteristic values, wherein the image to be measured refers to the image shot after the sample is dripped on the test paper for reaction, and the image of the blank control module refers to the test paper image without the sample dripped; substituting the characteristic value into a corresponding standard concentration gradient curve obtained by a pre-experiment, such as an EDs-ascorbic acid standard concentration curve, so as to obtain the concentration value of the detection item.
601 The specific calculation formula for converting the RGB color space into the HSV color space is as follows:
R’=R/255，
G’=G/255，
B’=B/255，
C max =max(R’,G’,B’)，
C min =min(R’,G’,B’)，
Δ=C max -C min ，
if Δ=0, H=0°，
if C max =R’, H=60°×[(G’-B’)/Δ+0]，
if C max =G’, H=60°×[(B’-R’)/Δ+2]，
if C max =B’, H=60°×[(R’-G’)/Δ+4]，
if C ma x=0, S=0，
if C max ≠0, S=Δ/C max ，
V=C max 。
602 The corresponding characteristic value of the color block to be measured is calculated and substituted into the standard curve to obtain the corresponding detection result, and the result is output on the display 8.
The invention discloses a computing device, which comprises a processor and a memory for storing a program executable by the processor, wherein the urine analysis detection method is realized when the processor executes the program stored by the memory.
The computing device of the invention can be a desktop computer, a notebook computer, a smart phone, a PDA hand-held terminal tablet computer, a programmable logic controller or other terminal devices with processor functions.
While certain specific embodiments of the invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the invention. It will be appreciated by those skilled in the art that modifications may be made to the above embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.

Claims (8)

1. A urine test paper analysis device, the device comprising: the system comprises a control mechanism, a quantitative strip, a test paper transmission platform, an optical system, a video acquisition card, a computer and a display; the test paper strip is placed on the test paper transmission platform and is driven to move to different positions; the control mechanism controls the sample loading amount and the reaction time of the quantitative strip on the test strip; the optical system collects images on the test paper strip, sends the images to the computer through the video collection card, and displays the images through the display.
2. The urine test strip analysis device of claim 1, wherein the control mechanism comprises: the sample adding module and the reaction timing module; the sample adding module controls the sample adding amount of the quantitative strip to the test strip; the reaction timing module sets the reaction time of the test strip.
3. The urine test strip analysis device of claim 1, wherein the optical system comprises: a white LED light source and a planar array CCD camera; and the test strip is irradiated by the white LED light source, and the area array CCD camera shoots an image of the test strip.
4. The urine test strip analysis device of claim 1, wherein said computer comprises: the device comprises a test paper analysis image processing module, a test paper analysis image extraction module and a concentration calculation module; the test paper analysis image processing module removes the highlight of the image based on a bicubic interpolation method; the test paper analysis image extraction module finds out the place with the most sufficient reaction in the image, extracts the region of interest and obtains the color block diagram of each detection item; the concentration calculation module converts the image from the RGB color space to the HSV color space, takes Euclidean distance between the image to be detected and the image of the blank comparison module in the HSV color space as a characteristic value, and substitutes the value into a corresponding standard concentration gradient curve obtained by pre-experiment to obtain a concentration value of a detection item.
5. A method for detecting a urine test paper analysis device according to any one of claims 1 to 4, comprising the steps of:
step 1: the sample adding module is used for adding samples on the test strip, and after the reaction is carried out for a set time, the image is shot by the area array CCD camera under the irradiation of the white LED light source;
step 2: the test paper analysis image processing module removes the highlight of the image based on a bicubic interpolation method and extracts the outline;
step 3: performing perspective transformation on the image, extracting a rectangular image with the same actual size as the test paper block, and identifying the detected type;
step 4: finding out the place with the most sufficient reaction in the perspective transformed image in the step 3 based on the thermodynamic diagram, extracting the region of interest, and obtaining a color block diagram of each detection item;
step 5: performing polynomial nonlinear color correction on the color block diagram of each detection item in the step 4 based on a matrix conversion method, analyzing a standard colorimetric card to obtain a gray level deviation curve, constructing a polynomial, and fitting a nonlinear relation to correct the color deviation;
step 6: and (3) converting the color block diagram obtained in the step (5) from an RGB color space to an HSV color space, taking Euclidean distance between an image to be detected and an image of a blank comparison module in the HSV color space as a characteristic value, and substituting the characteristic value into a corresponding standard concentration gradient curve obtained by a pre-experiment, so that the concentration value of the detection item can be obtained.
6. The method according to claim 5, wherein removing the highlight in the step 2 comprises:
step 201: dividing the image into blocks, wherein the average brightness of each sub-block forms a sub-block brightness matrix;
step 202: subtracting the average brightness of the sub-block from the average brightness of the full graph to obtain a brightness difference matrix, expanding the brightness difference matrix to the size of the full graph by using a bicubic interpolation method, and estimating the illumination distribution of the full graph;
step 203: subtracting the original gray level image from the calculated illumination distribution diagram to finish the highlight processing of the image.
7. The method according to claim 6, wherein extracting the contour in the step 2 includes:
step 204: adopting a Gaussian smoothing filter to complete image filtering and remove Gaussian noise;
step 205: morphological processing is carried out on the filtered image, interference color blocks are eliminated through image opening operation, and a target color block area is filled through closing operation;
step 206: using adaptive threshold calculation to separate the background area from the foreground area;
step 207: and carrying out edge extraction on the images by adopting Canny operator edge detection to obtain the respective images of each detection item.
8. The method according to claim 5, wherein the step 5 comprises: step 501: the RGB value of the ith color block in the actual image is Ri, gi and Bi, and the standard value of the ith color block in the standard color card is R0i, G0i and B0i; matrix V [ J ]][I]A polynomial matrix composed of polynomials constructed for RGB values in an actual photographed image, each behavior R, G, B, RG, RB, BG, R, B, G, RG, RB, BG, BR, GR, GB pattern, R 3 ，G 3 ，B 3 RGB, where j=19-bit polynomial term, I is the number of color patches of the color chart;
step 502: x=a T ·V，X[3][I]A [ J ] is a matrix of standard RGB values for color chart color blocks][3]To the required mapping relation matrix, V [ J ]][I]A polynomial regression matrix;
step 503: the matrix A is optimized by a least square method to obtain A= (V.V) T ) -1 ·(V·X T )；
Step 504: the input image X processed by the steps in [3][M]Polynomial matrix V composed of RGB values in [19][M]Corrected output image X out [3][M]=A T ·V in 。
CN202410263825.6A 2024-03-08 2024-03-08 Urine test paper analysis device and detection method thereof Pending CN117849043A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410263825.6A CN117849043A (en) 2024-03-08 2024-03-08 Urine test paper analysis device and detection method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410263825.6A CN117849043A (en) 2024-03-08 2024-03-08 Urine test paper analysis device and detection method thereof

Publications (1)

Publication Number Publication Date
CN117849043A true CN117849043A (en) 2024-04-09

Family

ID=90548448

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410263825.6A Pending CN117849043A (en) 2024-03-08 2024-03-08 Urine test paper analysis device and detection method thereof

Country Status (1)

Country Link
CN (1) CN117849043A (en)

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000180445A (en) * 1998-12-21 2000-06-30 Astec Corp:Kk Urinalysis reagent cell and urinalysis container
CN105891199A (en) * 2016-01-18 2016-08-24 南阳师范学院 Method for differentiating multiple types of metal ions through single indicator
CN106323926A (en) * 2016-08-16 2017-01-11 四川理工学院 Metallic iron ion measuring method based on Euclidean distances
CN109490289A (en) * 2018-11-15 2019-03-19 湖北德立森科技有限公司 The urinalysis device of pollution-free detection is carried out under sealing condition
CN110887960A (en) * 2019-12-02 2020-03-17 电子科技大学 Urine test strip quantitative detection system and method based on machine vision
CN113155814A (en) * 2021-02-07 2021-07-23 之江实验室 Portable colorimetric array image acquisition device based on optical fiber array and detection method
CN113658132A (en) * 2021-08-16 2021-11-16 沭阳九鼎钢铁有限公司 Computer vision-based structural part weld joint detection method
CN115201196A (en) * 2022-08-09 2022-10-18 广州健芯生物科技合伙企业(有限合伙) High-precision urine analysis method and system
CN116327152A (en) * 2022-12-14 2023-06-27 重庆理工大学 Remote non-contact heart rate detection system and method
CN117274295A (en) * 2023-09-21 2023-12-22 重庆邮电大学 Novel array type urine test paper instant detection and analysis method
CN117440160A (en) * 2022-07-13 2024-01-23 脸萌有限公司 Video processing method, device, equipment and storage medium

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000180445A (en) * 1998-12-21 2000-06-30 Astec Corp:Kk Urinalysis reagent cell and urinalysis container
CN105891199A (en) * 2016-01-18 2016-08-24 南阳师范学院 Method for differentiating multiple types of metal ions through single indicator
CN106323926A (en) * 2016-08-16 2017-01-11 四川理工学院 Metallic iron ion measuring method based on Euclidean distances
CN109490289A (en) * 2018-11-15 2019-03-19 湖北德立森科技有限公司 The urinalysis device of pollution-free detection is carried out under sealing condition
CN110887960A (en) * 2019-12-02 2020-03-17 电子科技大学 Urine test strip quantitative detection system and method based on machine vision
CN113155814A (en) * 2021-02-07 2021-07-23 之江实验室 Portable colorimetric array image acquisition device based on optical fiber array and detection method
CN113658132A (en) * 2021-08-16 2021-11-16 沭阳九鼎钢铁有限公司 Computer vision-based structural part weld joint detection method
CN117440160A (en) * 2022-07-13 2024-01-23 脸萌有限公司 Video processing method, device, equipment and storage medium
CN115201196A (en) * 2022-08-09 2022-10-18 广州健芯生物科技合伙企业(有限合伙) High-precision urine analysis method and system
CN116327152A (en) * 2022-12-14 2023-06-27 重庆理工大学 Remote non-contact heart rate detection system and method
CN117274295A (en) * 2023-09-21 2023-12-22 重庆邮电大学 Novel array type urine test paper instant detection and analysis method

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
姚海根: "《数字印刷技术》", 31 August 2001, 上海科学技术出版社 *
宋丽梅，朱新军: "《机器视觉与机器学习》", 31 May 2020, 机械工业出版社 *
张豪，彭煜民: "《发电厂机器视觉智能感知技术》", 31 December 2021, 广东科技出版社 *
杨帆: "《数字图像处理与分析 第4版》", 31 January 2019, 北京航空航天大学出版社 *
林晓辉: "《普通高等教育新工科机器人工程系列教材 工业机器人原理与应用》", 30 November 2022, 机械工业出版社 *
王向伟，荣先辉，钱海宁: "《首届伪装隐身专业委员会论文集》", 31 January 2020, 哈尔滨工程大学出版社 *

Similar Documents

Publication Publication Date Title
US11802839B2 (en) Quantifying color changes in chemical test pads induced by different concentrations of analytes under different lighting conditions
US9824441B2 (en) Method for estimating a quantity of a blood component in a fluid canister
AU2003236675B2 (en) Method for quantitative video-microscopy and associated system and computer software program product
US20200242809A1 (en) Methods and devices for performing an analytical measurement based on a color formation reaction
JP4071186B2 (en) Method and system for identifying an object of interest in a biological specimen
US11192100B2 (en) Multi-factor urine test system that adjusts for lighting and timing
JP6787076B2 (en) Color reaction detection system, color reaction detection method and program
AU2003236675A1 (en) Method for quantitative video-microscopy and associated system and computer software program product
AU2002334590A1 (en) Method quantitative video-microscopy and associated system and computer software program product
CN103839283A (en) Area and circumference nondestructive measurement method of small irregular object
JP7062926B2 (en) Color reaction detection system, color reaction detection method and program
CN111624203A (en) Relay contact alignment non-contact measurement method based on machine vision
CN117252875B (en) Medical image processing method, system, medium and equipment based on hyperspectral image
CN109030480B (en) Sample analysis method, sample analysis device, readable storage medium and computer equipment
CN117576121A (en) Automatic segmentation method, system, equipment and medium for microscope scanning area
CN117849043A (en) Urine test paper analysis device and detection method thereof
WO2018131091A1 (en) Image processing device, image processing method, and image processing program
Kibria et al. Smartphone-based point-of-care urinalysis assessment
CN114663481A (en) Multi-modal image acquisition device and registration method
CN115100273A (en) Immunochromatographic test strip quantitative analysis system and detection method based on image processing
CN114486895A (en) Method for detecting sample substance concentration based on pushing of urine drying test strip to identification
CN113450383A (en) Quantitative analysis method, device, equipment and medium for immunochromatographic test paper
US20240102934A1 (en) Test Strip Carrier, System and Method for Test Strip Detection
EP3954990B1 (en) Test strip fixation device for optical measurements of an analyte
CN116593452A (en) Food safety detection method, system and medium

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