CN116433671B - Colloidal gold detection method, system and storage medium based on image recognition - Google Patents

Colloidal gold detection method, system and storage medium based on image recognition Download PDF

Info

Publication number
CN116433671B
CN116433671B CN202310705073.XA CN202310705073A CN116433671B CN 116433671 B CN116433671 B CN 116433671B CN 202310705073 A CN202310705073 A CN 202310705073A CN 116433671 B CN116433671 B CN 116433671B
Authority
CN
China
Prior art keywords
test paper
paper image
line
image
preset
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
Application number
CN202310705073.XA
Other languages
Chinese (zh)
Other versions
CN116433671A (en
Inventor
郭诗静
曾剑明
彭运平
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.)
Guangzhou Wanfu Health Technology Co ltd
Original Assignee
Guangzhou Wanfu Health Technology Co ltd
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 Guangzhou Wanfu Health Technology Co ltd filed Critical Guangzhou Wanfu Health Technology Co ltd
Priority to CN202310705073.XA priority Critical patent/CN116433671B/en
Publication of CN116433671A publication Critical patent/CN116433671A/en
Application granted granted Critical
Publication of CN116433671B publication Critical patent/CN116433671B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • 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
    • G06T2207/10072—Tomographic images
    • G06T2207/10081—Computed x-ray tomography [CT]
    • 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
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30056—Liver; Hepatic
    • 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
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30061—Lung
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Abstract

The application discloses a colloidal gold detection method, a system and a storage medium based on image recognition, wherein the method comprises the following steps: acquiring test paper image information; based on the preset position, fixing the test paper image and extracting the CT line position in the fixed test paper image; obtaining the middle area position of the CT line according to the position of the CT line in the adjusted test paper image; preprocessing the position of a CT line and the position of a middle area of the CT line to obtain pixel values of all areas; obtaining a stable value of a corresponding test paper image according to the pixel value of each region; and obtaining a detection result corresponding to the test paper image based on a preset boundary range in which the stable value of the test paper image falls. According to the application, the test paper colloidal gold detection is completed through image comparison of the CT line positions, so that the error probability is reduced, and the detection efficiency and accuracy are improved.

Description

Colloidal gold detection method, system and storage medium based on image recognition
Technical Field
The application relates to the field of image processing, in particular to a colloidal gold detection method, a colloidal gold detection system and a storage medium based on image recognition.
Background
With the development and utilization of the technology, the colloidal gold detection technology is widely applied, for example, to the detection of viruses such as hepatitis and bronchoviruses, and has simple operation and strong practicability. However, the current colloidal gold detection technology has some small problems, such as: the method is easy to interpret and has large interference by external light; only qualitative judgment, and more specific quantitative analysis and the like cannot be realized.
Accordingly, there is a need for improvement in the art.
Disclosure of Invention
In view of the above problems, the present application aims to provide a colloidal gold detection method, a colloidal gold detection system and a storage medium based on image recognition, which can improve the detection efficiency and accuracy.
The first aspect of the application provides a colloidal gold detection method based on image recognition, which comprises the following steps:
acquiring test paper image information;
based on the preset position, fixing the test paper image and extracting the CT line position in the fixed test paper image;
obtaining the middle area position of the CT line according to the position of the CT line in the adjusted test paper image;
preprocessing the position of a CT line and the position of a middle area of the CT line to obtain pixel values of all areas;
obtaining a stable value of a corresponding test paper image according to the pixel value of each region;
and obtaining a detection result corresponding to the test paper image based on a preset boundary range in which the stable value of the test paper image falls.
In this scheme, still include:
numbering the test paper images, and sequentially storing the test paper images according to the numbers;
judging whether the test paper image has a CT line or not, if not, marking the number of the corresponding test paper image;
extracting the number value of the marked serial numbers of the test paper images and the total number value of the test paper images;
obtaining a standard rate of the corresponding test paper image according to the marked number value of the serial numbers of the test paper image and the total number value of the test paper image;
judging whether the standard rate of the test paper image is larger than a preset standard rate threshold value, and if not, triggering warning information;
and sending the warning information to a preset management terminal for display.
In this scheme, based on preset position, the step of fixing the test paper image and extracting CT line position in the fixed test paper image specifically includes:
uniformly and fixedly placing the test paper images according to preset positions;
establishing a test paper image plane coordinate system with the preset reference point as an original point based on the preset reference point;
and extracting each corner point of the CT line in the test paper image plane coordinate system, and setting the diagonal point in the same direction as the CT line position.
In this scheme, the step of preprocessing the position of the CT line and the position of the middle region of the CT line to obtain the pixel value of each region specifically includes:
preprocessing the CT line position and the middle area position of the CT line to obtain a gray scale image area of the CT line position and the middle area position of the CT line;
extracting all pixel values of the gray map areas, and sequentially arranging the pixel values in sequence from small to large to obtain a pixel value set of each gray map area;
extracting pixel values in the gray map region, wherein the pixel values are concentrated to be smaller than the median, and carrying out average value calculation to obtain an average pixel value;
the average pixel value is set to the pixel value of the region.
In this scheme, the step of obtaining the stable value of the corresponding test paper image according to the pixel value of each region specifically includes:
obtaining the ratio of the pixel values of each region according to the pixel values of each region;
based on a group of multiple photographing images of the same test paper, obtaining a ratio set of the images of the same test paper;
carrying out difference calculation on any two ratios in the ratio set of the same test paper image to obtain ratio difference;
judging whether the ratio difference is smaller than a preset ratio difference threshold value, if so, judging that the ratio set of the corresponding test paper image is normal;
based on the preset coefficient, obtaining a stable value corresponding to the test paper image according to the ratio set of the test paper image.
In this scheme, according to the ratio set of test paper image, obtain the formula of the steady value of corresponding test paper image, specifically include:
setting the stable value of the test paper image toThe formula is->Wherein->Indicate->Ratio of->Wherein->Representing the total number of ratios in the set of corresponding ratios, +.>For the preset coefficient, ++>Indicating the initial stable value of the test paper image.
The application provides a colloidal gold detection system based on image recognition, which comprises a memory and a processor, wherein the memory stores a colloidal gold detection method program based on image recognition, and the method realizes the following steps when the program is executed by the processor:
acquiring test paper image information;
based on the preset position, fixing the test paper image and extracting the CT line position in the fixed test paper image;
obtaining the middle area position of the CT line according to the position of the CT line in the adjusted test paper image;
preprocessing the position of a CT line and the position of a middle area of the CT line to obtain pixel values of all areas;
obtaining a stable value of a corresponding test paper image according to the pixel value of each region;
and obtaining a detection result corresponding to the test paper image based on a preset boundary range in which the stable value of the test paper image falls.
In this scheme, still include:
numbering the test paper images, and sequentially storing the test paper images according to the numbers;
judging whether the test paper image has a CT line or not, if not, marking the number of the corresponding test paper image;
extracting the number value of the marked serial numbers of the test paper images and the total number value of the test paper images;
obtaining a standard rate of the corresponding test paper image according to the marked number value of the serial numbers of the test paper image and the total number value of the test paper image;
judging whether the standard rate of the test paper image is larger than a preset standard rate threshold value, and if not, triggering warning information;
and sending the warning information to a preset management terminal for display.
In this scheme, based on preset position, the step of fixing the test paper image and extracting CT line position in the fixed test paper image specifically includes:
uniformly and fixedly placing the test paper images according to preset positions;
establishing a test paper image plane coordinate system with the preset reference point as an original point based on the preset reference point;
and extracting each corner point of the CT line in the test paper image plane coordinate system, and setting the diagonal point in the same direction as the CT line position.
In this scheme, the step of preprocessing the position of the CT line and the position of the middle region of the CT line to obtain the pixel value of each region specifically includes:
preprocessing the CT line position and the middle area position of the CT line to obtain a gray scale image area of the CT line position and the middle area position of the CT line;
extracting all pixel values of the gray map areas, and sequentially arranging the pixel values in sequence from small to large to obtain a pixel value set of each gray map area;
extracting pixel values in the gray map region, wherein the pixel values are concentrated to be smaller than the median, and carrying out average value calculation to obtain an average pixel value;
the average pixel value is set to the pixel value of the region.
In this scheme, the step of obtaining the stable value of the corresponding test paper image according to the pixel value of each region specifically includes:
obtaining the ratio of the pixel values of each region according to the pixel values of each region;
based on a group of multiple photographing images of the same test paper, obtaining a ratio set of the images of the same test paper;
carrying out difference calculation on any two ratios in the ratio set of the same test paper image to obtain ratio difference;
judging whether the ratio difference is smaller than a preset ratio difference threshold value, if so, judging that the ratio set of the corresponding test paper image is normal;
based on the preset coefficient, obtaining a stable value corresponding to the test paper image according to the ratio set of the test paper image.
In this scheme, according to the ratio set of test paper image, obtain the formula of the steady value of corresponding test paper image, specifically include:
setting the stable value of the test paper image toThe formula is->Wherein->Indicate->Ratio of->Wherein->Representing the total number of ratios in the set of corresponding ratios, +.>For the preset coefficient, ++>Indicating the initial stable value of the test paper image.
A third aspect of the present application provides a computer storage medium having stored therein an image recognition-based colloidal gold detection method program which, when executed by a processor, implements the steps of an image recognition-based colloidal gold detection method as described in any one of the above.
According to the colloidal gold detection method, the colloidal gold detection system and the storage medium based on image recognition, the test paper colloidal gold detection is completed through image comparison of CT line positions, error probability is reduced, and detection efficiency and accuracy are improved.
Drawings
FIG. 1 shows a flow chart of a colloidal gold detection method based on image recognition;
fig. 2 shows a block diagram of a colloidal gold detection system based on image recognition according to the present application.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, however, the present application may be practiced in other ways than those described herein, and therefore the scope of the present application is not limited to the specific embodiments disclosed below.
Fig. 1 shows a flow chart of a colloidal gold detection method based on image recognition.
As shown in fig. 1, the application discloses a colloidal gold detection method based on image recognition, which comprises the following steps:
s102, obtaining test paper image information;
s104, fixing the test paper image based on the preset position and extracting the CT line position in the fixed test paper image;
s106, obtaining the middle area position of the CT line according to the CT line position in the adjusted test paper image;
s108, preprocessing the position of the CT line and the position of the middle area of the CT line to obtain pixel values of all areas;
s110, obtaining a stable value of a corresponding test paper image according to the pixel value of each region;
s112, obtaining a detection result of the corresponding test paper image based on a preset boundary range in which the stable value of the test paper image falls.
After the test paper image information is acquired, intelligent positioning is carried out on the test paper image through a preset position, the positions of the C line and the T line among different test paper images are determined to be at the same position, the position of the CT line is extracted, the position of the middle area of the CT line is obtained according to the position of the CT line, and the preprocessing comprises the processing of graying, gaussian filtering, parameter consistency and the like on the position of the CT line and the position of the middle area of the CT line. If the detection results of the test paper images are classified into four grades, such as negative, weak positive, positive and strong positive, the stable values corresponding to the test paper images are also classified into four ranges, and each stable value range corresponds to one detection result.
According to an embodiment of the present application, further comprising:
numbering the test paper images, and sequentially storing the test paper images according to the numbers;
judging whether the test paper image has a CT line or not, if not, marking the number of the corresponding test paper image;
extracting the number value of the marked serial numbers of the test paper images and the total number value of the test paper images;
obtaining a standard rate of the corresponding test paper image according to the marked number value of the serial numbers of the test paper image and the total number value of the test paper image;
judging whether the standard rate of the test paper image is larger than a preset standard rate threshold value, and if not, triggering warning information;
and sending the warning information to a preset management terminal for display.
When neither the line C nor the line T of the test paper image nor the line CT is displayed, it is indicated that there is a problem in the corresponding test paper image, the number of the corresponding test paper image is marked, and the standard rate of the test paper image is set to beThe formula isWherein->Representing the total number of test paper images, +.>The number value of the marked numbers of the test paper images is represented, the preset standard rate threshold is set by a person skilled in the art according to actual demands, when the warning information is triggered, the fact that the operation of the test paper images of the corresponding batch is not standard or the like is possible is indicated, and corresponding prompt is carried out through the warning information.
According to an embodiment of the present application, the step of fixing the test paper image based on the preset position and extracting the position of the CT line in the fixed test paper image specifically includes:
uniformly and fixedly placing the test paper images according to preset positions;
establishing a test paper image plane coordinate system with the preset reference point as an original point based on the preset reference point;
and extracting each corner point of the CT line in the test paper image plane coordinate system, and setting the diagonal point in the same direction as the CT line position.
It should be noted that, based on the preset reference point, a test paper image plane coordinate system using the preset reference point as the origin is established, for example, the preset reference point is one corner point of the C line, and then the coordinate of one corner point corresponding to the C line isFor example, if the CT line position is displayed with the coordinate points of the upper left corner and the lower right corner of the CT line, the C line position is set asThe T line position is set to->The middle area of CT line is set as
The method comprises the steps of carrying out a first treatment on the surface of the Wherein->Coordinate points of x-axis and y-axis representing the upper left corner of the C-line position, wherein +.>Coordinate points of x-axis and y-axis representing the lower right corner of the C-line position; wherein the method comprises the steps ofCoordinate points of x-axis and y-axis representing the upper left corner of the T-line position, wherein +.>Coordinate points of x-axis and y-axis representing the lower right corner of the T-line position.
According to an embodiment of the present application, the step of preprocessing the position of the CT line and the position of the middle area of the CT line to obtain the pixel value of each area specifically includes:
preprocessing the CT line position and the middle area position of the CT line to obtain a gray scale image area of the CT line position and the middle area position of the CT line;
extracting all pixel values of the gray map areas, and sequentially arranging the pixel values in sequence from small to large to obtain a pixel value set of each gray map area;
extracting pixel values in the gray map region, wherein the pixel values are concentrated to be smaller than the median, and carrying out average value calculation to obtain an average pixel value;
the average pixel value is set to the pixel value of the region.
The pixel value set of the gray-scale image region at the C-line position is set asThenWhich is provided withMiddle->The gray-scale image area representing the position of the C line contains the total number of pixel values, the set of pixel values +.>The pixel values of the pixels are sequentially arranged from small to large, wherein the same pixel values are numbered according to the sequence at random, such as the number of +.>Only 3 identical pixel values exist later, and the corresponding 3 identical pixel values are numbered as +.>And->Wherein->Carrying out random one-to-one matching on the corresponding 3 same pixel values; setting the pixel value of the gray-scale image area at the C line position to +.>Then
Wherein->Indicate->Individual pixel values, and，/>indicate->Individual pixel values, and->. Similarly, the pixel value of the gray-scale image region at the T-line position can be obtained +.>Pixel value of gray-scale image region at middle region position of CT line +.>。
According to the embodiment of the application, the step of obtaining the stable value of the corresponding test paper image according to the pixel value of each region specifically comprises the following steps:
obtaining the ratio of the pixel values of each region according to the pixel values of each region;
based on a group of multiple photographing images of the same test paper, obtaining a ratio set of the images of the same test paper;
carrying out difference calculation on any two ratios in the ratio set of the same test paper image to obtain ratio difference;
judging whether the ratio difference is smaller than a preset ratio difference threshold value, if so, judging that the ratio set of the corresponding test paper image is normal;
based on the preset coefficient, obtaining a stable value corresponding to the test paper image according to the ratio set of the test paper image.
The ratio of the pixel values of the respective regions is set toThe formula is
In order to ensure the accuracy of the test paper image, a group of photographing is carried out on the test paper image for multiple times, a plurality of ratios of the test paper image are obtained and form a ratio set, for example, a preset ratio difference threshold value is set as +.>When the ratio difference is smallIn->When the method is used, the shooting of the corresponding test paper image is less influenced by the external environment, the ratio of the corresponding test paper image is effective, and the ratio of the pixel values of all the areas is the ratio of the corresponding test paper image.
According to the embodiment of the application, the formula for obtaining the stable value of the corresponding test paper image according to the ratio set of the test paper image specifically comprises:
setting the stable value of the test paper image toThe formula is->Wherein->Indicate->Ratio of->Wherein->Representing the total number of ratios in the set of corresponding ratios, +.>For the preset coefficient, ++>Indicating the initial stable value of the test paper image.
When the ratio of the test paper images is effective, calculating a stable value of the corresponding test paper image according to the ratio of the test paper images.
According to an embodiment of the present application, further comprising:
acquiring the area value of a detection area and the area value of a CT line position area of a test paper image;
obtaining the confidence coefficient of the corresponding CT line according to the sum of the areas of the CT line position areas and the detection area of the test paper image;
judging whether the confidence coefficient of the CT line is larger than a preset confidence coefficient threshold value, if so, the corresponding CT line is normal; otherwise, the device is abnormal;
and marking the abnormal CT line and sending the marked abnormal CT line to a preset management terminal for prompting.
It should be noted that, the confidence coefficient of the CT line is a ratio of an area value of the CT line position area to an area of the detection area corresponding to the test paper image, where if the confidence coefficient is lower than a preset confidence coefficient threshold, it is indicated that the area value of the CT line position area corresponding to the test paper image is insufficient, therefore, the CT line corresponding to the test paper image is set as abnormal, and the abnormal CT line is sent to a preset management terminal for revision, and the preset confidence coefficient threshold is set by a person skilled in the art according to actual requirements.
According to an embodiment of the present application, further comprising:
acquiring a light intensity value of the test paper image during shooting;
judging whether the light intensity value of the test paper image is larger than a preset light intensity threshold value or not, and if yes, triggering warning information;
based on the warning information, the light intensity value of the test paper image during shooting is adjusted.
The light intensity sensing device is used for detecting light rays when the test paper image is shot to obtain a light intensity value when the test paper image is shot, and if the light intensity value is larger than a preset light intensity threshold value, warning information is triggered; when the light intensity value is smaller than or equal to a preset light intensity value, the warning information is closed, and the preset light intensity threshold is set by a person skilled in the art according to actual requirements.
According to an embodiment of the present application, further comprising:
obtaining the number of the light intensity classes corresponding to the test paper image shooting according to the preset range in which the light intensity value falls when the test paper image shooting is performed;
and matching the initial stable value of the corresponding test paper image according to the number of the light intensity grades when the corresponding test paper image is shot.
It should be noted that, in order to eliminate the influence of the light intensity value on the test paper image, the light intensity is graded according to the preset range to obtain light intensities of different grades, the light intensities of different grades correspond to different initial stable values, and the correlation coefficient between the light intensity grade and the initial stable value and the preset range are all set by the person skilled in the art according to the actual situation.
Fig. 2 shows a block diagram of a colloidal gold detection system based on image recognition according to the present application.
As shown in fig. 2, the second aspect of the present application provides an image recognition-based colloidal gold detection system 2, which includes a memory 21 and a processor 22, wherein the memory stores an image recognition-based colloidal gold detection method program, and the processor executes the image recognition-based colloidal gold detection method program to implement the following steps:
acquiring test paper image information;
based on the preset position, fixing the test paper image and extracting the CT line position in the fixed test paper image;
obtaining the middle area position of the CT line according to the position of the CT line in the adjusted test paper image;
preprocessing the position of a CT line and the position of a middle area of the CT line to obtain pixel values of all areas;
obtaining a stable value of a corresponding test paper image according to the pixel value of each region;
and obtaining a detection result corresponding to the test paper image based on a preset boundary range in which the stable value of the test paper image falls.
After the test paper image information is acquired, intelligent positioning is carried out on the test paper image through a preset position, the positions of the C line and the T line among different test paper images are determined to be at the same position, the position of the CT line is extracted, the position of the middle area of the CT line is obtained according to the position of the CT line, and the preprocessing comprises the processing of graying, gaussian filtering, parameter consistency and the like on the position of the CT line and the position of the middle area of the CT line. If the detection results of the test paper images are classified into four grades, such as negative, weak positive, positive and strong positive, the stable values corresponding to the test paper images are also classified into four ranges, and each stable value range corresponds to one detection result.
According to an embodiment of the present application, further comprising:
numbering the test paper images, and sequentially storing the test paper images according to the numbers;
judging whether the test paper image has a CT line or not, if not, marking the number of the corresponding test paper image;
extracting the number value of the marked serial numbers of the test paper images and the total number value of the test paper images;
obtaining a standard rate of the corresponding test paper image according to the marked number value of the serial numbers of the test paper image and the total number value of the test paper image;
judging whether the standard rate of the test paper image is larger than a preset standard rate threshold value, and if not, triggering warning information;
and sending the warning information to a preset management terminal for display.
When neither the line C nor the line T of the test paper image nor the line CT is displayed, it is indicated that there is a problem in the corresponding test paper image, the number of the corresponding test paper image is marked, and the standard rate of the test paper image is set to beThe formula isWherein->Representing the total number of test paper images, +.>The preset standard rate threshold is set by a person skilled in the art according to actual requirements, and when the warning information is triggered, the action that the operation of the corresponding batch of test paper images is not standard and the like is possible is indicated, and the corresponding batch of test paper images are subjected to the action of warning informationThe prompt should be made.
According to an embodiment of the present application, the step of fixing the test paper image based on the preset position and extracting the position of the CT line in the fixed test paper image specifically includes:
uniformly and fixedly placing the test paper images according to preset positions;
establishing a test paper image plane coordinate system with the preset reference point as an original point based on the preset reference point;
and extracting each corner point of the CT line in the test paper image plane coordinate system, and setting the diagonal point in the same direction as the CT line position.
It should be noted that, based on the preset reference point, a test paper image plane coordinate system using the preset reference point as the origin is established, for example, the preset reference point is one corner point of the C line, and then the coordinate of one corner point corresponding to the C line isFor example, if the CT line position is displayed with the coordinate points of the upper left corner and the lower right corner of the CT line, the C line position is set asThe T line position is set to->The middle area of CT line is set as +.>The method comprises the steps of carrying out a first treatment on the surface of the Wherein->Coordinate points of x-axis and y-axis representing the upper left corner of the C-line position, wherein +.>Coordinate points of x-axis and y-axis representing the lower right corner of the C-line position; wherein the method comprises the steps ofCoordinate points of x-axis and y-axis representing the upper left corner of the T-line position, wherein +.>Coordinate points of x-axis and y-axis representing the lower right corner of the T-line position.
According to an embodiment of the present application, the step of preprocessing the position of the CT line and the position of the middle area of the CT line to obtain the pixel value of each area specifically includes:
preprocessing the CT line position and the middle area position of the CT line to obtain a gray scale image area of the CT line position and the middle area position of the CT line;
extracting all pixel values of the gray map areas, and sequentially arranging the pixel values in sequence from small to large to obtain a pixel value set of each gray map area;
extracting pixel values in the gray map region, wherein the pixel values are concentrated to be smaller than the median, and carrying out average value calculation to obtain an average pixel value;
the average pixel value is set to the pixel value of the region.
The pixel value set of the gray-scale image region at the C-line position is set asThenWherein->The gray-scale image area representing the position of the C line contains the total number of pixel values, the set of pixel values +.>The pixel values of the pixels are sequentially arranged from small to large, wherein the same pixel values are numbered according to the sequence at random, such as the number of +.>Only 3 identical pixel values exist later, and the corresponding 3 identical pixel values are numbered as +.>And->Wherein->Carrying out random one-to-one matching on the corresponding 3 same pixel values; setting the pixel value of the gray-scale image area at the C line position to +.>ThenWherein->Indicate->Individual pixel values, and，/>indicate->Individual pixel values, and->. Similarly, the pixel value of the gray-scale image region at the T-line position can be obtained +.>Pixel value of gray-scale image region at middle region position of CT line +.>。
According to the embodiment of the application, the step of obtaining the stable value of the corresponding test paper image according to the pixel value of each region specifically comprises the following steps:
obtaining the ratio of the pixel values of each region according to the pixel values of each region;
based on a group of multiple photographing images of the same test paper, obtaining a ratio set of the images of the same test paper;
carrying out difference calculation on any two ratios in the ratio set of the same test paper image to obtain ratio difference;
judging whether the ratio difference is smaller than a preset ratio difference threshold value, if so, judging that the ratio set of the corresponding test paper image is normal;
based on the preset coefficient, obtaining a stable value corresponding to the test paper image according to the ratio set of the test paper image.
The ratio of the pixel values of the respective regions is set toThe formula is->In order to ensure the accuracy of the test paper image, a group of photographing is carried out on the test paper image for multiple times, a plurality of ratios of the test paper image are obtained and form a ratio set, for example, a preset ratio difference threshold value is set as +.>When the ratio difference is smaller than +.>When the method is used, the shooting of the corresponding test paper image is less influenced by the external environment, the ratio of the corresponding test paper image is effective, and the ratio of the pixel values of all the areas is the ratio of the corresponding test paper image.
According to the embodiment of the application, the formula for obtaining the stable value of the corresponding test paper image according to the ratio set of the test paper image specifically comprises:
setting the stable value of the test paper image toThe formula is->Wherein->Indicate->Ratio of->Wherein->Representing the total number of ratios in the set of corresponding ratios, +.>For the preset coefficient, ++>Indicating the initial stable value of the test paper image.
When the ratio of the test paper images is effective, calculating a stable value of the corresponding test paper image according to the ratio of the test paper images.
According to an embodiment of the present application, further comprising:
acquiring the area value of a detection area and the area value of a CT line position area of a test paper image;
obtaining the confidence coefficient of the corresponding CT line according to the sum of the areas of the CT line position areas and the detection area of the test paper image;
judging whether the confidence coefficient of the CT line is larger than a preset confidence coefficient threshold value, if so, the corresponding CT line is normal; otherwise, the device is abnormal;
and marking the abnormal CT line and sending the marked abnormal CT line to a preset management terminal for prompting.
It should be noted that, the confidence coefficient of the CT line is a ratio of an area value of the CT line position area to an area of the detection area corresponding to the test paper image, where if the confidence coefficient is lower than a preset confidence coefficient threshold, it is indicated that the area value of the CT line position area corresponding to the test paper image is insufficient, therefore, the CT line corresponding to the test paper image is set as abnormal, and the abnormal CT line is sent to a preset management terminal for revision, and the preset confidence coefficient threshold is set by a person skilled in the art according to actual requirements.
According to an embodiment of the present application, further comprising:
acquiring a light intensity value of the test paper image during shooting;
judging whether the light intensity value of the test paper image is larger than a preset light intensity threshold value or not, and if yes, triggering warning information;
based on the warning information, the light intensity value of the test paper image during shooting is adjusted.
The light intensity sensing device is used for detecting light rays when the test paper image is shot to obtain a light intensity value when the test paper image is shot, and if the light intensity value is larger than a preset light intensity threshold value, warning information is triggered; when the light intensity value is smaller than or equal to a preset light intensity value, the warning information is closed, and the preset light intensity threshold is set by a person skilled in the art according to actual requirements.
According to an embodiment of the present application, further comprising:
obtaining the number of the light intensity classes corresponding to the test paper image shooting according to the preset range in which the light intensity value falls when the test paper image shooting is performed;
and matching the initial stable value of the corresponding test paper image according to the number of the light intensity grades when the corresponding test paper image is shot.
It should be noted that, in order to eliminate the influence of the light intensity value on the test paper image, the light intensity is graded according to the preset range to obtain light intensities of different grades, the light intensities of different grades correspond to different initial stable values, and the correlation coefficient between the light intensity grade and the initial stable value and the preset range are all set by the person skilled in the art according to the actual situation.
A third aspect of the present application provides a computer storage medium having stored therein an image recognition-based colloidal gold detection method program which, when executed by a processor, implements the steps of an image recognition-based colloidal gold detection method as described in any one of the above.
The application discloses a colloidal gold detection method, a system and a storage medium based on image recognition, wherein the method comprises the following steps: acquiring test paper image information; based on the preset position, fixing the test paper image and extracting the CT line position in the fixed test paper image; obtaining the middle area position of the CT line according to the position of the CT line in the adjusted test paper image; preprocessing the position of a CT line and the position of a middle area of the CT line to obtain pixel values of all areas; obtaining a stable value of a corresponding test paper image according to the pixel value of each region; and obtaining a detection result corresponding to the test paper image based on a preset boundary range in which the stable value of the test paper image falls. According to the application, the test paper colloidal gold detection is completed through image comparison of the CT line positions, so that the error probability is reduced, and the detection efficiency and accuracy are improved.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present application may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present application may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.

Claims (8)

1. The colloidal gold detection method based on image recognition is characterized by comprising the following steps of:
acquiring test paper image information;
based on the preset position, fixing the test paper image and extracting the CT line position in the fixed test paper image;
obtaining the middle area position of the CT line according to the position of the CT line in the adjusted test paper image;
preprocessing the position of a CT line and the position of a middle area of the CT line to obtain pixel values of all areas;
obtaining a stable value of a corresponding test paper image according to the pixel value of each region;
obtaining a detection result of the corresponding test paper image based on a preset boundary range in which a stable value of the test paper image falls;
the step of obtaining the stable value of the corresponding test paper image according to the pixel value of each region specifically comprises the following steps:
obtaining the ratio of the pixel values of each region according to the pixel values of each region;
based on a group of multiple photographing images of the same test paper, obtaining a ratio set of the images of the same test paper;
carrying out difference calculation on any two ratios in the ratio set of the same test paper image to obtain ratio difference;
judging whether the ratio difference is smaller than a preset ratio difference threshold value, if so, judging that the ratio set of the corresponding test paper image is normal;
based on a preset coefficient, obtaining a stable value corresponding to the test paper image according to the ratio set of the test paper image;
the formula for obtaining the stable value of the corresponding test paper image according to the ratio set of the test paper image specifically comprises the following steps:
setting the stable value of the test paper image toThe formula is->Wherein->Indicate->Ratio of->Wherein->Representing the total number of ratios in the set of corresponding ratios, +.>For the preset coefficient, ++>Indicating the initial stable value of the test paper image.
2. The method for detecting colloidal gold based on image recognition according to claim 1, further comprising:
numbering the test paper images, and sequentially storing the test paper images according to the numbers;
judging whether the test paper image has a CT line or not, if not, marking the number of the corresponding test paper image;
extracting the number value of the marked serial numbers of the test paper images and the total number value of the test paper images;
obtaining a standard rate of the corresponding test paper image according to the marked number value of the serial numbers of the test paper image and the total number value of the test paper image;
judging whether the standard rate of the test paper image is larger than a preset standard rate threshold value, and if not, triggering warning information;
and sending the warning information to a preset management terminal for display.
3. The method for detecting colloidal gold based on image recognition according to claim 1, wherein the step of fixing the test paper image based on the preset position and extracting the CT line position in the fixed test paper image specifically comprises:
uniformly and fixedly placing the test paper images according to preset positions;
establishing a test paper image plane coordinate system with the preset reference point as an original point based on the preset reference point;
and extracting each corner point of the CT line in the test paper image plane coordinate system, and setting the diagonal point in the same direction as the CT line position.
4. The method for detecting colloidal gold based on image recognition according to claim 1, wherein the step of preprocessing the positions of the CT lines and the positions of the middle regions of the CT lines to obtain pixel values of each region specifically comprises:
preprocessing the CT line position and the middle area position of the CT line to obtain a gray scale image area of the CT line position and the middle area position of the CT line;
extracting all pixel values of the gray map areas, and sequentially arranging the pixel values in sequence from small to large to obtain a pixel value set of each gray map area;
extracting pixel values in the gray map region, wherein the pixel values are concentrated to be smaller than the median, and carrying out average value calculation to obtain an average pixel value;
the average pixel value is set to the pixel value of the region.
5. The colloidal gold detection system based on image recognition is characterized by comprising a memory and a processor, wherein the memory stores a colloidal gold detection method program based on image recognition, and the method realizes the following steps when the program is executed by the processor:
acquiring test paper image information;
based on the preset position, fixing the test paper image and extracting the CT line position in the fixed test paper image;
obtaining the middle area position of the CT line according to the position of the CT line in the adjusted test paper image;
preprocessing the position of a CT line and the position of a middle area of the CT line to obtain pixel values of all areas;
obtaining a stable value of a corresponding test paper image according to the pixel value of each region;
obtaining a detection result of the corresponding test paper image based on a preset boundary range in which a stable value of the test paper image falls;
the step of obtaining the stable value of the corresponding test paper image according to the pixel value of each region specifically comprises the following steps:
obtaining the ratio of the pixel values of each region according to the pixel values of each region;
based on a group of multiple photographing images of the same test paper, obtaining a ratio set of the images of the same test paper;
carrying out difference calculation on any two ratios in the ratio set of the same test paper image to obtain ratio difference;
judging whether the ratio difference is smaller than a preset ratio difference threshold value, if so, judging that the ratio set of the corresponding test paper image is normal;
based on a preset coefficient, obtaining a stable value corresponding to the test paper image according to the ratio set of the test paper image;
the formula for obtaining the stable value of the corresponding test paper image according to the ratio set of the test paper image specifically comprises the following steps:
setting the stable value of the test paper image toThe formula is->Wherein->Indicate->Ratio of->Wherein->Representing the total number of ratios in the set of corresponding ratios, +.>For the preset coefficient, ++>Indicating the initial stable value of the test paper image.
6. The image recognition-based colloidal gold detection system according to claim 5, further comprising:
numbering the test paper images, and sequentially storing the test paper images according to the numbers;
judging whether the test paper image has a CT line or not, if not, marking the number of the corresponding test paper image;
extracting the number value of the marked serial numbers of the test paper images and the total number value of the test paper images;
obtaining a standard rate of the corresponding test paper image according to the marked number value of the serial numbers of the test paper image and the total number value of the test paper image;
judging whether the standard rate of the test paper image is larger than a preset standard rate threshold value, and if not, triggering warning information;
and sending the warning information to a preset management terminal for display.
7. The colloidal gold detection system based on image recognition according to claim 5, wherein the step of fixing the test paper image based on the preset position and extracting the CT line position in the fixed test paper image specifically comprises:
uniformly and fixedly placing the test paper images according to preset positions;
establishing a test paper image plane coordinate system with the preset reference point as an original point based on the preset reference point;
and extracting each corner point of the CT line in the test paper image plane coordinate system, and setting the diagonal point in the same direction as the CT line position.
8. A computer storage medium, wherein a colloidal gold detection method program based on image recognition is stored in the computer storage medium, and when the colloidal gold detection method program based on image recognition is executed by a processor, the steps of a colloidal gold detection method based on image recognition as claimed in any one of claims 1 to 4 are realized.
CN202310705073.XA 2023-06-14 2023-06-14 Colloidal gold detection method, system and storage medium based on image recognition Active CN116433671B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310705073.XA CN116433671B (en) 2023-06-14 2023-06-14 Colloidal gold detection method, system and storage medium based on image recognition

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310705073.XA CN116433671B (en) 2023-06-14 2023-06-14 Colloidal gold detection method, system and storage medium based on image recognition

Publications (2)

Publication Number Publication Date
CN116433671A CN116433671A (en) 2023-07-14
CN116433671B true CN116433671B (en) 2023-08-25

Family

ID=87087672

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310705073.XA Active CN116433671B (en) 2023-06-14 2023-06-14 Colloidal gold detection method, system and storage medium based on image recognition

Country Status (1)

Country Link
CN (1) CN116433671B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104122388A (en) * 2013-04-23 2014-10-29 苏州慧康电子信息科技有限公司 Batch reader and test method for gold-label detection card
CN104198695A (en) * 2014-09-28 2014-12-10 杨伟群 Method for analyzing developing result of colloidal gold test strip
CN108133481A (en) * 2017-12-22 2018-06-08 必欧瀚生物技术（合肥）有限公司 A kind of image processing algorithm for fluorescence immune chromatography strip imaging system
CN113537203A (en) * 2020-04-16 2021-10-22 北京爱康泰科技有限责任公司 Test paper identification method and device, storage medium and equipment
CN114486841A (en) * 2022-04-07 2022-05-13 南京长健生物科技有限公司 Miniature fluorescence immunoassay analyzer and image processing method thereof
CN114511522A (en) * 2022-01-21 2022-05-17 长沙协大生物科技有限公司 Automatic reagent judgment method based on fluorescence immunoassay and colloidal gold method
GB2601978A (en) * 2020-05-11 2022-06-15 Forsite Diagnostics Ltd Assay reading method
CN115311466A (en) * 2021-04-21 2022-11-08 中移(成都)信息通信科技有限公司 Image recognition method, electronic device, and storage medium

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11494571B2 (en) * 2020-07-22 2022-11-08 Donald Channing Cooper Computer vision method for improved automated image capture and analysis of rapid diagnostic test devices

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104122388A (en) * 2013-04-23 2014-10-29 苏州慧康电子信息科技有限公司 Batch reader and test method for gold-label detection card
CN104198695A (en) * 2014-09-28 2014-12-10 杨伟群 Method for analyzing developing result of colloidal gold test strip
CN108133481A (en) * 2017-12-22 2018-06-08 必欧瀚生物技术（合肥）有限公司 A kind of image processing algorithm for fluorescence immune chromatography strip imaging system
CN113537203A (en) * 2020-04-16 2021-10-22 北京爱康泰科技有限责任公司 Test paper identification method and device, storage medium and equipment
GB2601978A (en) * 2020-05-11 2022-06-15 Forsite Diagnostics Ltd Assay reading method
CN115311466A (en) * 2021-04-21 2022-11-08 中移(成都)信息通信科技有限公司 Image recognition method, electronic device, and storage medium
CN114511522A (en) * 2022-01-21 2022-05-17 长沙协大生物科技有限公司 Automatic reagent judgment method based on fluorescence immunoassay and colloidal gold method
CN114486841A (en) * 2022-04-07 2022-05-13 南京长健生物科技有限公司 Miniature fluorescence immunoassay analyzer and image processing method thereof

Also Published As

Publication number Publication date
CN116433671A (en) 2023-07-14

Similar Documents

Publication Publication Date Title
CN111307727B (en) Water body water color abnormity identification method and device based on time sequence remote sensing image
CN108596895B (en) Fundus image detection method, device and system based on machine learning
CN113159147B (en) Image recognition method and device based on neural network and electronic equipment
CN108090511B (en) Image classification method and device, electronic equipment and readable storage medium
CN111461165A (en) Image recognition method, recognition model training method, related device and equipment
CN110490204B (en) Image processing method, image processing device and terminal
Shaikh et al. A novel approach for automatic number plate recognition
CN111680690B (en) Character recognition method and device
CN105320970A (en) Potato disease diagnostic device, diagnostic system and diagnostic method
CN112417955A (en) Patrol video stream processing method and device
CN112381092A (en) Tracking method, device and computer readable storage medium
CN110879131A (en) Imaging quality testing method and imaging quality testing device for visual optical system, and electronic apparatus
CN116152261A (en) Visual inspection system for quality of printed product
CN111695373B (en) Zebra stripes positioning method, system, medium and equipment
CN111507957A (en) Identity card picture conversion method and device, computer equipment and storage medium
CN108877030B (en) Image processing method, device, terminal and computer readable storage medium
CN116703909B (en) Intelligent detection method for production quality of power adapter
CN113436162A (en) Method and device for identifying weld defects on surface of hydraulic oil pipeline of underwater robot
CN116433671B (en) Colloidal gold detection method, system and storage medium based on image recognition
CN111369531B (en) Image definition scoring method, device and storage device
CN115273123B (en) Bill identification method, device and equipment and computer storage medium
CN112001785A (en) Network credit fraud identification method and system based on image identification
CN113239738B (en) Image blurring detection method and blurring detection device
CN114332058A (en) Serum quality identification method, device, equipment and medium based on neural network
CN114998282A (en) Image detection method, image detection device, electronic equipment and storage 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
GR01 Patent grant
GR01 Patent grant