CN115096878A - A kind of detection method and system of stool test paper - Google Patents

Abstract

The invention discloses a method and a system for detecting a stool inspection test paper. The method includes: acquiring an image of the stool inspection test paper, wherein the image of the stool inspection test paper includes a flag position of at least one test paper; using a first preset algorithm to generate a stool inspection test paper Correcting the image of the test paper image; extracting the color development result area of the test paper by using the sign of each test paper in the correction image; identifying and judging the color development result area of each test paper respectively, and generating the corresponding detection result of each test paper. The detection method proposed by the invention can accurately identify the color development result of the test paper in the image. It has good recognition effect in the detection of different stool test strip images, the algorithm has strong adaptability, simple parameter structure, and low linear computational complexity.

Description

A kind of detection method and system of stool test paper

technical field

The invention relates to the technical field of stool inspection, in particular to a detection method and system for stool inspection test paper.

Background technique

The traditional fecal test method needs to use a fecal collection stick to sample the feces after each defecation, and then use the fecal sample diluent to dissolve, take the corresponding test paper for testing, and observe the reaction results. This method requires manual intervention, and there are The detection process is cumbersome, easy to infect the bacteria in the feces, and the risk of low accuracy of linear calculation.

SUMMARY OF THE INVENTION

Therefore, the detection method and system for a stool test paper provided by the present invention overcome the defects of the prior art that the detection process is cumbersome, the bacteria in the feces are easily infected, and the linear calculation accuracy is low.

To achieve the above object, the present invention provides the following technical solutions:

In a first aspect, an embodiment of the present invention provides a method for detecting a stool test paper, including:

acquiring an image of a stool test strip, where the image of the stool test strip includes at least one sign of the test strip;

Using the first preset algorithm to generate a corrected image of the stool test strip image;

Extract the color development result area of the test strip by using the mark position of each test strip in the corrected image;

Identify and judge the color development result area of each test strip respectively, and generate the corresponding detection result of each test strip.

Optionally, the step of generating a corrected image of the stool test strip image using the first preset algorithm includes:

Convert the image of the stool test paper into a grayscale image, and use the Gaussian filter with preset parameters to remove the noise of the grayscale image;

Extract the contour of the denoised grayscale image through a preset edge detection algorithm, and fill the edge-detected image through image expansion;

Use the Hough transform algorithm to detect the edge lines in the filled edge detection image, and calculate the rotation angle of the filled edge detection image to be corrected;

Taking the center of the edge detection image after filling as the rotation center, combined with the rotation angle to be corrected, a first preset algorithm is used to generate a corrected image of the test strip image.

Optionally, the step of using the Hough transform algorithm to detect the edge line in the edge detection image after filling, and calculating the rotation angle to be corrected in the edge detection image after filling, includes:

Use the Hough transform algorithm to detect the edge lines in the edge detection image after filling;

Detect the edge line in the image by filling the edge, and calculate the inclination angle of the edge line;

Through the inclination angle of the edge line, the rotation angle of the edge detection image to be corrected after filling is calculated.

Optionally, performing binarization processing, erosion and expansion processing, and mean filtering processing on the rotated image, respectively, to generate a denoised binarized image;

Use the second preset algorithm to detect several black areas in the denoised binarized image, the rectangular outlines of the black areas correspond to the black areas corresponding to each test strip in the rotated image, each Each test strip has a black area, and the black area is the mark position of each test strip.

Optionally, the color development result area of the test paper is divided into upper and lower parts.

Optionally, through a third preset algorithm, it is detected whether the upper and lower regions respectively contain red lines, and the detection result of the test paper is judged.

Optionally, the detection result includes:

If there is no red line in the upper and lower parts, or only the lower part has a red line, the detection result is invalid;

If there is a red line in the upper part and no red line in the lower part, the test result is negative;

If the upper and lower parts have red lines, the test result is positive.

In a second aspect, an embodiment of the present invention provides a detection system for a stool test paper, including:

a sample acquisition module, used for acquiring an image of a stool test strip, wherein the image of the stool test strip includes at least one sign of the test strip;

a witness image generation module, used for generating a corrected image of the test strip image by using the first preset algorithm;

The extraction module of the color development result area is used for extracting the color development result area of the detection test strip by using the mark position of each test strip in the corrected image;

The detection result generation module is used for identifying and judging the color development result area of each test strip respectively, and generating the corresponding detection result of each test strip.

In a third aspect, an embodiment of the present invention provides a terminal, including: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores a program executable by the at least one processor. The instruction is executed by the at least one processor, so that the at least one processor executes the method for detecting a stool test paper according to the first aspect of the embodiment of the present invention.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where the computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the computer to execute the first aspect of the embodiment of the present invention. The detection method of stool test paper.

The technical scheme of the present invention has the following advantages:

The detection method and system of the stool test paper provided by the present invention can accurately identify the color development result of the test paper in the image. It has a good recognition effect in the image detection of different stool test strips, and the algorithm has strong adaptability. The parameter structure is simple, and the linear computational complexity is low.

Description of drawings

In order to illustrate the specific embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the specific embodiments or the prior art. Obviously, the accompanying drawings in the following description The drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

1 is a flowchart of a specific example of a method for detecting a urine test paper provided by an embodiment of the present invention;

FIG. 2 is an edge detection image of a specific example of a method for detecting a test strip provided by an embodiment of the present invention;

3 is a corrected image of a specific example of a method for detecting a urine test strip provided by an embodiment of the present invention;

4 is a binarized image of a specific example of a method for detecting a urine test strip provided by an embodiment of the present invention;

5 is a binarized image after denoising of a specific example of a method for detecting a urine test strip provided by an embodiment of the present invention;

FIG. 6 is an original image mark position detection result image of a specific example of a method for detecting a urine test strip provided by an embodiment of the present invention;

Figures 7a and 7b are respectively images of the upper and lower parts of the color of the test paper of a specific example of a method for detecting a urine test paper provided by an embodiment of the present invention;

FIG. 8 is a module composition diagram of a detection system for a urine test paper provided by an embodiment of the present invention;

FIG. 9 is a composition diagram of a specific example of a terminal according to an embodiment of the present invention.

Detailed ways

The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. The indicated orientation or positional relationship is based on the orientation or positional relationship shown in the accompanying drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the indicated device or element must have a specific orientation or a specific orientation. construction and operation, and therefore should not be construed as limiting the invention. Furthermore, the terms "first", "second", and "third" are used for descriptive purposes only and should not be construed to indicate or imply relative importance.

In the description of the present invention, it should be noted that the terms "installed", "connected" and "connected" should be understood in a broad sense, unless otherwise expressly specified and limited, for example, it may be a fixed connection or a detachable connection connection, or integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal connection of two components, which can be a wireless connection or a wired connection connect. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood in specific situations.

In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

Example 1

A method for detecting a stool test paper provided in the embodiment of the present invention is applied to the detection of stool in a smart toilet, and the stool test paper can detect occult blood, transferrin, Helicobacter pylori, etc., which is only an example and not limited to this , and detect corresponding diseases according to actual needs in practical applications. The use of test strip detection combined with image processing to identify the test results can facilitate the subject to conduct self-examination at home and provide an effective guarantee for the early detection of the disease. It avoids cumbersome procedures and does not need to touch feces, which can effectively avoid infection with bacteria in feces. It is safer and more practical. It is a detection method that is very suitable for home self-inspection. It can realize remote online detection and bring great benefits to users. convenient.

As shown in FIG. 1 , a method for detecting a stool test paper provided by an embodiment of the present invention includes the following steps:

Step S1 : acquiring an image of the stool inspection test strip, where the image of the stool inspection test strip includes at least one sign of the test strip.

In the embodiment of the present invention, the image acquisition of the urine test paper selects a device with a camera and shooting function according to the specific situation, which is not limited here.

Step S2: using the first preset algorithm to generate a corrected image of the stool test strip image.

In the embodiment of the present invention, the step of generating a corrected image of the stool test strip image by using the first preset algorithm includes: converting the stool test strip image into a grayscale image, and using a Gaussian filter with preset parameters to remove the grayscale The selection of preset parameters is not limited here, and the corresponding selection is made according to the actual situation; the contour of the denoised grayscale image is extracted through the preset edge detection algorithm, and the image after edge detection is filled through image expansion. , the preset edge detection algorithm is not limited here, and the corresponding selection is made according to the actual situation; the Hough transform algorithm is used to detect the edge line in the edge detection image after filling; the edge line in the image is detected by the edge after filling, and the edge line is calculated. Tilt angle: Calculate the rotation angle of the edge detection image to be corrected after filling according to the tilt angle of the edge line. Taking the center of the edge detection image after filling as the rotation center, combined with the rotation angle to be corrected, the first preset algorithm is used to generate a corrected image of the test strip image. The first preset algorithm is not limited here, and the corresponding Select.

In a specific embodiment, in order to correct the image, the rotation angle of the image needs to be calculated first. First, convert the original color image (the image of the test paper) into a grayscale image, and use a Gaussian filter to denoise it so as not to affect the edge detection, where the convolution kernel in the Gaussian filter is set to (9,9). Then, use the Canny detection algorithm to detect the image contour, set the detection threshold to (1,20), extract the image contour, and fill the edge-detected image through image expansion, and set the convolution kernel parameter of image expansion to (5,5) . Finally, the edge lines in the image are detected by Hough transform, the inclination angle of the edge lines is calculated, and then the rotation angle to be corrected by the image is calculated.

In a specific embodiment, as shown in FIG. 2, it is an image after edge detection, and the edge line in the red frame in the figure is the edge straight line that needs to be detected by Hough transform, and the angle between this straight line and the vertical direction is calculated, that is, The angle of rotation needed to rectify the image.

In a specific embodiment, take the center of the image as the rotation center, combine the rotation angle, and use the getRotationMatrix2D function of the OpenCV library to obtain the rotation transformation matrix, and use the warpAffine affine transformation function of the OpenCV library to obtain the rotated image, as shown in Figure 3. As shown, the corrected blank area is filled with white for subsequent calculation.

Step S3 : extracting the color development result area of the detection test strip by using the flag bit of each test strip in the corrected image.

In the embodiment of the present invention, the rotated image is subjected to binarization processing, erosion and expansion processing, and mean filtering processing, respectively, to generate a binarized image after denoising; the second preset algorithm is used, wherein the second preset algorithm is used. The design method is not limited here, and the corresponding selection is made according to the actual situation. Detect several black areas in the binarized image after denoising, the rectangular outline of the black area corresponds to the black area corresponding to each test strip in the rotated image, and each test strip in the image has a black area , the black area is the sign of each test strip.

In the embodiment of the present invention, the color development result area of the test paper is divided into upper and lower parts. The third preset algorithm is used to detect whether the upper and lower regions contain red lines respectively, and the detection result of the test strip is judged. The third preset algorithm is not limited here, and is selected according to the actual situation.

In a specific embodiment, when observing the rotated image, since the position of each shot is not fixed, it is necessary to locate the position of each test strip. Each test strip in the image has a black area, and the black area is set as the mark position of each test strip.

In a specific embodiment, first, for the binarization of the rotated image, since the threshold of the image pixel points is 0 to 255, the detection threshold is set to 65 (obtained by experiments), that is, the pixel points in the image larger than the threshold value are set to 65. The value is changed to 255, and the value of pixels less than or equal to the threshold is changed to 0. The binarized image is shown in Figure 4.

In a specific embodiment, as shown in FIG. 4 , the three black rectangular areas are the black areas corresponding to each test strip in the rotated image, and the binarized image also includes other interference areas, Therefore, by performing erosion and dilation processing on the image, the outliers in the image are removed, and the dilation and erosion convolution kernel parameters are set to (5, 5), and then the outliers are further removed by mean filtering, and the outlier noise in the image is eliminated. , set the mean filter convolution kernel parameter to (13,13), this parameter is selected according to the actual situation, and the binarized image after denoising is shown in Figure 5.

Finally, use the findContours function of the OpenCV library to detect the rectangular contours of the three black areas in Figure 5, and return each rectangular contour x, y, w, h four parameters, where x and y represent the coordinates of the left vertex of the contour, w represents the width of the rectangular outline, h represents the height of the rectangular outline, and the rectangular outline of the detected black area corresponds to the original image position as shown in Figure 6.

Step S4: Identifying and judging the color development result area of each test strip respectively, and generating a corresponding detection result for each test strip.

In a specific embodiment, the position of each test paper is detected, and the color development result area of the test paper is a fixed area under the red frame in FIG. There will be at most two red lines. Therefore, the color development area of each test strip is divided into upper and lower parts for extraction. As shown in Figure 7, the color development area of the upper and lower parts of the first test strip is shown. Check whether there is a red line in each part of the color area to judge the result.

Identify whether the two-part test paper color area image in Figure 7 contains red lines. Therefore, it is necessary to convert the colored RGB image into an HSV image. The HSV image uses Hue, Saturation, and Value. A way to represent color, the value range of H (0-180), the value range of S (0-255), the value range of V (0-255), and the red representation method is to set H(0 -10), S(43-255), V(46-255) and H(156-180), S(43-255), V(46-255), by detecting whether the HSV image is converted into The pixels in the red threshold are included, so as to detect whether the upper and lower regions in FIG. 7 contain red lines respectively, so as to judge the detection result of the test paper.

In the embodiment of the present invention, if there is no red line in the upper and lower parts or only the lower part has a red line, the detection result is invalid; if there is a red line in the upper part and no red line in the lower part, the detection result is invalid. Negative; if there are red lines on the upper and lower parts, the test result is positive. This judgment method is used to identify the final result of each test strip.

The detection method of the stool test paper provided in the embodiment of the present invention can accurately identify the color development result of the test paper in the image, has a good recognition effect in the detection of different stool test paper images, has strong algorithm adaptability, and simple parameter structure , the linear computational complexity is low.

Example 2

An embodiment of the present invention provides a detection system for a stool test paper, as shown in FIG. 8 , including:

The sample acquisition module 1 is used for acquiring the image of the stool test paper, and the image of the stool test paper includes the flag position of at least one test strip; this module executes the method described in step S1 in the embodiment 1, and will not be repeated here.

The witness image generation module 2 is used for generating a corrected image of the test strip image by using the first preset algorithm; this module executes the method described in step S2 in Embodiment 1, and details are not repeated here.

The extraction module 3 of the color development result area is used to extract the color development result area of the detection test paper by utilizing the sign of each test strip in the corrected image; this module executes the method described in step S3 in Embodiment 1, and will not be repeated here. Repeat.

The detection result generation module 4 is used for identifying and judging the color development result area of each test strip respectively, and generating the corresponding detection result of each test strip; this module executes the method described in step S4 in Embodiment 1, and will not be repeated here. Repeat.

The embodiment of the present invention provides a detection system for stool test strips, which can accurately identify the color development results of the test strips in images, has a better recognition effect in the detection of different stool test strip images, has strong algorithm adaptability, and simple parameter structure , the linear computational complexity is low.

Example 3

An embodiment of the present invention provides a terminal, as shown in FIG. 9 , including: at least one processor 401 , such as a CPU (Central Processing Unit, central processing unit), at least one communication interface 403 , memory 404 , and at least one communication bus 402 . Among them, the communication bus 402 is used to realize the connection and communication between these components. The communication interface 403 may include a display screen (Display) and a keyboard (Keyboard), and the optional communication interface 403 may also include a standard wired interface and a wireless interface. The memory 404 may be a high-speed RAM memory (Random Access Memory, volatile random access memory), or may be a non-volatile memory (non-volatile memory), such as at least one disk memory. The memory 404 can optionally also be at least one storage device located away from the aforementioned processor 401 . The processor 401 may execute the method for detecting a stool test paper in Embodiment 1. A set of program codes are stored in the memory 404, and the processor 401 calls the program codes stored in the memory 404 for executing the method for detecting a stool test paper in the first embodiment. The communication bus 402 may be a peripheral component interconnect (PCI for short) bus or an extended industry standard architecture (extended industry standard architecture, EISA for short) bus or the like. The communication bus 402 can be divided into an address bus, a data bus, a control bus, and the like. For ease of presentation, only one line is shown in FIG. 9, but it does not mean that there is only one bus or one type of bus. The memory 404 may include volatile memory (English: volatile memory), such as random-access memory (English: random-access memory, abbreviation: RAM); the memory may also include non-volatile memory (English: non-volatile memory) memory), such as flash memory (English: flash memory), hard disk (English: hard disk drive, abbreviation: HDD) or solid-state drive (English: solid-state drive, abbreviation: SSD); the memory 404 may also include the above types of combination of memory. The processor 401 may be a central processing unit (English: central processing unit, abbreviation: CPU), a network processor (English: network processor, abbreviation: NP), or a combination of CPU and NP.

The memory 404 may include volatile memory (English: volatile memory), such as random-access memory (English: random-access memory, abbreviation: RAM); the memory may also include non-volatile memory (English: non-volatile memory) memory), such as flash memory (English: flash memory), hard disk (English: hard diskdrive, abbreviation: HDD) or solid-state drive (English: solid-state drive, abbreviation: SSD); the memory 404 may also include the above-mentioned types of memory The combination.

The processor 401 may be a central processing unit (English: central processing unit, abbreviation: CPU), a network processor (English: network processor, abbreviation: NP), or a combination of CPU and NP.

The processor 401 may further include a hardware chip. The above-mentioned hardware chip may be an application-specific integrated circuit (English: application-specific integrated circuit, abbreviation: ASIC), a programmable logic device (English: programmable logic device, abbreviation: PLD) or a combination thereof. The above-mentioned PLD may be a complex programmable logic device (English: complex programmable logic device, abbreviation: CPLD), a field programmable gate array (English: field-programmable gate array, abbreviation: FPGA), a general array logic (English: generic arraylogic , abbreviation: GAL) or any combination thereof.

Optionally, memory 404 is also used to store program instructions. The processor 401 can invoke the program instructions to implement the detection method for the stool test paper in the first embodiment of the present application.

Embodiments of the present invention further provide a computer-readable storage medium, where computer-executable instructions are stored on the computer-readable storage medium, and the computer-executable instructions can execute the method for detecting a stool test paper in Embodiment 1. Wherein, the storage medium may be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a flash memory (Flash Memory), a hard disk (Hard) Disk Drive, abbreviation: HDD) or solid-state drive (Solid-State Drive, SSD), etc.; the storage medium may also include a combination of the above-mentioned types of memories.

Obviously, the above-mentioned embodiments are only examples for clear description, and are not intended to limit the implementation manner. For those of ordinary skill in the art, changes or modifications in other different forms can also be made on the basis of the above description. There is no need and cannot be exhaustive of all implementations here. However, the obvious changes or changes derived from this are still within the protection scope of the present invention.

Claims (10)

1. A method for detecting stool test paper is characterized by comprising the following steps:

acquiring an image of the stool test paper, wherein the image of the stool test paper comprises at least one marker bit of the test paper;

generating a corrected image of the test paper image to be detected by using a first preset algorithm;

extracting a color development result area of the detection test paper by using the marker bit of each test paper in the corrected image;

and respectively identifying and judging the color development result area of each piece of test paper to generate a corresponding detection result of each piece of test paper.

2. The method for detecting a stool test strip according to claim 1, wherein the step of generating a corrected image of the stool test strip using a first predetermined algorithm includes:

converting an image of the stool test paper into a gray image, and removing noise of the gray image by using a Gaussian filter with preset parameters;

extracting the outline of the denoised gray level image by a preset edge detection algorithm, and filling the image after edge detection by image expansion;

detecting edge lines in the edge detection image after filling by using a Hough transform algorithm, and calculating a rotation angle to be corrected of the edge detection image after filling;

and taking the center of the edge detection image after filling as a rotation center, and generating a correction image of the test paper image to be detected by utilizing a first preset algorithm in combination with the rotation angle to be corrected.

3. The method for detecting stool test paper according to claim 2, wherein the step of detecting the edge line in the filled edge detection image by using a hough transform algorithm and calculating the rotation angle to be corrected of the filled edge detection image comprises:

detecting edge lines in the edge detection image after filling by using a Hough transform algorithm;

calculating the inclination angle of the edge line by detecting the edge line in the image after filling;

and calculating the rotation angle to be corrected of the edge detection image after filling according to the inclination angle of the edge line.

4. The method of detecting a stool test strip according to claim 3,

respectively carrying out binarization processing, corrosion and expansion processing and mean value filtering processing on the rotated image to generate a denoised binarization image;

and detecting a plurality of black areas in the denoised binary image by using a second preset algorithm, wherein the rectangular outlines of the black areas correspond to each other, the black area corresponding to each test paper in the rotated image is provided, each test paper in the image is provided with one black area, and the black area is a mark position of each test paper.

5. The method of detecting a stool test strip according to claim 4, wherein the color-developing result area of the test strip is divided into an upper portion and a lower portion.

6. The method of claim 1, wherein a third predetermined algorithm is used to determine whether the upper and lower regions respectively contain a red line, thereby determining the detection result of the test strip.

7. The method of claim 5, wherein the detecting result comprises:

if the upper part area and the lower part area have no red line or only the lower part area has a red line, the detection result is invalid;

if the upper part has a red line and the lower part does not have a red line, the detection result is negative;

if the upper and lower parts have red lines, the detection result is positive.

8. A detection system for stool test paper is characterized by comprising:

the system comprises a sample acquisition module, a detection module and a display module, wherein the sample acquisition module is used for acquiring an image of the stool test paper, and the image of the stool test paper comprises at least one marker bit of the test paper;

the witness image generation module is used for generating a corrected image of the test paper image to be detected by utilizing a first preset algorithm;

the extraction module of the color development result area is used for extracting the color development result area of the detection test paper by utilizing the marker bit of each piece of test paper in the correction image;

and the detection result generation module is used for respectively identifying and judging the color development result area of each piece of test paper to generate a corresponding detection result of each piece of test paper.

9. A terminal, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to cause the at least one processor to perform the method of testing a stool test strip of any of claims 1-7.

10. A computer-readable storage medium storing computer instructions for causing a computer to perform the method of detecting a stool test strip according to any one of claims 1 to 7.

Images