CN115019155A

CN115019155A - Reagent automatic identification method, device, equipment and readable storage medium

Info

Publication number: CN115019155A
Application number: CN202210504164.2A
Authority: CN
Inventors: 石岩; 白佳委; 陈伟川; 陈斌; 汪大明
Original assignee: Xiamen Institute Of Health Engineering And Innovation
Current assignee: Xiamen Institute Of Health Engineering And Innovation
Priority date: 2022-05-10
Filing date: 2022-05-10
Publication date: 2022-09-06

Abstract

The invention provides a method, a device and equipment for automatically identifying a reagent and a readable storage medium, which relate to the technical field of automatic identification and comprise the steps of collecting images of at least two test tubes to be detected on a hole site plate; preprocessing the image of the tube to be detected to obtain the outline of the image; extracting dots in all the image outlines and collecting the dots as a dot data set; and classifying the dot data set by using a support vector machine algorithm to obtain a classification result. The method has the advantages that the color change of the reagent is automatically identified by adopting a machine learning method to realize the automatic identification of the experimental result, the algorithm can be adapted to various light conditions and various complex environments by adopting the machine learning method, the method can be adapted to various color dyes commonly used in laboratories, and the high identification accuracy can be achieved.

Description

Reagent automatic identification method, device, equipment and readable storage medium

Technical Field

The invention relates to the technical field of automatic identification, in particular to a method, a device, equipment and a readable storage medium for automatically identifying a reagent.

Background

Modern society has entered the information age, and with the development of computer technology, communication technology and computer network technology, the automatic information processing capability and level are continuously improved, and are widely applied in various fields of people's social activities and lives. Under such circumstances, image recognition techniques as information sources are increasingly gaining attention.

The prior method for manually identifying the color change of the reagent is slow and inaccurate, can not adapt to various light conditions and complex environments, can not adapt to various color dyes commonly used in laboratories, and has low identification accuracy.

Disclosure of Invention

The invention aims to provide a method, a device, equipment and a readable storage medium for automatically identifying a reagent, so as to improve the problems. In order to achieve the purpose, the technical scheme adopted by the invention is as follows:

in a first aspect, the present application provides a method for automatically identifying a reagent, comprising:

collecting images of at least two to-be-detected test tubes on a hole site plate;

preprocessing the image of the tube to be detected to obtain the outline of the image;

extracting dots in all the image outlines and collecting the dots as a dot data set;

and classifying the dot data set by using a support vector machine algorithm to obtain a classification result.

Preferably, the image of the tube to be tested is preprocessed to obtain the outline of the image, which includes:

acquiring first information, wherein the first information comprises gray processing of the image of the tube to be tested to obtain a processed gray image;

acquiring second information, wherein the second information comprises the step of carrying out binarization processing on the first information to obtain a processed binarization image;

performing opening operation processing on the second information, wherein the opening operation processing is to corrode and expand firstly to obtain a first image;

extracting the outline of the first image to obtain the outlines of all dots in the first image;

acquiring third information, wherein the third information comprises the maximum circumscribed circle of the outline of each dot and the radius of the maximum circumscribed circle of each dot;

and obtaining the average value of the radiuses of the maximum circumscribed circles of all the dots according to the third information.

Preferably, extracting dots in all the image outlines and collecting the dots as a dot data set, and then:

according to the third information and the information of the round points, coordinate values of four points of the circumscribed rectangle of the maximum circumscribed circle are solved;

cutting the image of the test tube to be detected according to the information of the coordinate values of the four points to obtain a cut image;

acquiring specific position information of folders for placing different color reagents;

and corresponding the cut image to the specific position of the folder.

Preferably, a support vector machine algorithm is used to classify the dot data sets to obtain a classification result, where the classification result includes:

constructing three SVM classifiers;

training the SVM classifier to obtain the trained SVM classifier;

inputting data to be tested into the SVM classifier according to a support vector machine algorithm to obtain three classification results;

and storing the three classification results, and exiting the recognition mode.

In a second aspect, the present application also provides an automatic reagent identification device, including:

an acquisition module: the device is used for acquiring images of at least two to-be-detected test tubes on the hole site plate;

a preprocessing module: the device is used for preprocessing the image of the test tube to be detected to obtain the outline of the image;

an extraction module: the device is used for extracting dots in all the image outlines and collecting the dots as a dot data set;

a classification module: and the dot data set is classified by utilizing a support vector machine algorithm to obtain a classification result.

In a third aspect, the present application also provides an automatic reagent identification apparatus, including:

a memory for storing a computer program;

a processor for implementing the steps of the method for automatic identification of the reagent when executing the computer program.

In a fourth aspect, the present application further provides a readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the reagent-based automatic identification method described above.

The invention has the beneficial effects that: the invention relates to a full-automatic constant temperature heating instrument for different hole sites, and the algorithm realizes the functions of automatically adapting to different reagent colors, automatically identifying the reaction result of the reagent and the like. The full-automatic constant temperature heating instrument is an instrument which can heat a reagent at constant temperature and automatically identify the reaction result of the reagent according to the color change of the reagent. The color change of the reagent is automatically identified by adopting a machine learning method to realize the automatic identification of the experimental result, the algorithm can be adapted to various light conditions and various complex environments by adopting the machine learning method, the adaptation can be carried out on various color dyes commonly used in a laboratory, and the high identification accuracy can be achieved.

Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.

FIG. 1 is a schematic flow chart of a method for automatically identifying a reagent according to an embodiment of the present invention;

FIG. 2 is a schematic structural diagram of an automatic reagent identification device according to an embodiment of the present invention;

fig. 3 is a schematic structural diagram of an automatic reagent identification device according to an embodiment of the present invention.

In the figure, 701 an acquisition module; 702. a pre-processing module; 7021. a first acquisition unit; 7022. a second acquisition unit; 7023. a processing unit; 7024. an extraction unit; 7025. a third acquisition unit; 7026. an evaluation unit; 703. an extraction module; 7031. a solving unit; 7032. a cutting unit; 7033. a fourth acquisition unit; 7034. a corresponding unit; 704. a classification module; 7041. a building unit; 7042. an obtaining unit; 7043. an input unit; 7044. a holding unit; 800. a braking identification device of the reagent; 801. a processor; 802. a memory; 803. a multimedia component; 804. an input/output (I/O) interface; 805. a communication component.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined or explained in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only for distinguishing the description, and are not construed as indicating or implying relative importance.

Example 1:

the embodiment provides an automatic reagent identification method.

Referring to fig. 1, it is shown that the method includes step S100, step S200, step S300 and step S400.

The invention relates to a full-automatic constant temperature heating instrument for different hole sites, and the algorithm realizes the functions of automatically adapting to different reagent colors, automatically identifying the reaction result of the reagent and the like. The full-automatic constant temperature heating instrument is an instrument which can heat a reagent at constant temperature and automatically identify the reaction result of the reagent according to the color change of the reagent. Full-automatic constant temperature heating appearance has multiple hole site specification usually, and hole site board is penetrating from top to bottom in the instrument, and the lamp plate of the equal light of hole site board top installation, the camera is equipped with to the below, and the lamp of lamp plate can pass through the test tube hole on the hole site board, and the colour of test tube bottom can be shot to the camera.

For the image shot by the camera, firstly, automatic hole position adaptation and positioning operation are carried out to obtain the imageSpecification of the hole site plate, n rows and m columns; corresponding relations between all round points in the camera and hole positions in the actual hole position plate, namely a first coordinate in the M sequence represents a hole position at the upper left corner in the hole position plate, a last coordinate represents a hole position at the lower right corner in the hole position plate, and every n coordinates represent a row from the first coordinate; precise circle center coordinates of each hole site in hole site plate

Then the function to be realized by the algorithm is as follows: the obtained information is utilized to realize the functions of automatically adapting to different reagent colors and automatically identifying experimental results. The implementation of the automatic identification algorithm is mainly divided into two parts, the first part is needed to be completed when the machine is used for the first time: a recognition algorithm training learning part; the second part is the actual use part after the machine training has been learned. The following is a detailed implementation of the algorithm:

s100, collecting images of at least two to-be-detected test tubes on the hole site plate.

It is understood that the method further comprises the following steps before the step:

enter a commissioning mode and the user needs to specify which color represents a positive reagent and which color represents a negative reagent. In this example, red represents a positive reagent and yellow represents a negative reagent.

It should be noted that, first, the test tubes containing the red reagent and the test tubes containing the yellow reagent are randomly placed on the well site plate, then the image acquisition is performed, the above process is repeated for a plurality of times, and the total times of the appearance of the well sites containing the red reagent test tubes, the yellow reagent test tubes and the wells where no test tubes are placed are ensured to be equal. At least 20 images are acquired, and the more images are acquired, the higher the recognition accuracy is. In addition, in the actual experiment process, the biggest difficulty in judging negative and positive according to colors is that the colors of a plurality of reagents are not standard yellow or red, but are gradually changed between the standard yellow or red and the red, so that the colors of the reagents in the test tubes placed on the well site plate are as close as possible to the colors of the reagents in the test tubes in the actual experiment and are as comprehensive as possible in the image acquisition process.

S200, preprocessing the image of the test tube to be detected to obtain the outline of the image.

It is understood that the step S200 includes:

acquiring first information, wherein the first information comprises the gray level processing of the image of the test tube to be detected, and a processed gray level image is obtained;

acquiring second information, wherein the second information comprises a binaryzation treatment to the first information to obtain a treated binaryzation image;

It should be noted that, in this embodiment, first, the collected image is binarized to obtain a binarized image, then, the binarized image is subjected to operations of erosion and expansion, then, the image is subjected to contour search to obtain a contour of each dot, then, a maximum circumscribed circle of each contour is found to obtain a radius r of the maximum circumscribed circle of each dot, and an average value of the radii of the maximum circumscribed circles of all the dots is obtained

S300, extracting all dots in the image outline and collecting the dots as a dot data set.

It is understood that, in this step, the following steps are included:

according to the coordinate value information of the four points, cutting the image of the test tube to be detected to obtain a cut image;

and corresponding the cut image to the specific position of the folder.

And cutting each round point, storing the round points separately, and making the round points into a data set. Since the format of image saving can only be rectangular, the circumscribed rectangle of the largest circumscribed circle needs to be clipped. Here based on previously obtained coordinates of the center of a circle

And maximum radius of the circle of tangency

The coordinates of four points of the circumscribed rectangle of the maximum circumscribed circle can be obtained, then the cutting is completed according to the coordinates of the four points, then the cut images are separately stored in different folders according to the colors of the placed reagents, hole sites where test tubes are not placed are placed in the folder with the name of 'A', hole sites where yellow solution test tubes are placed in the folder with the name of 'B', hole sites where red solution test tubes are placed in the folder with the name of 'C', and ABC are respectively the labels of the three data.

S400, classifying the dot data set by using a support vector machine algorithm to obtain a classification result.

It is understood that, in this step, the following are included:

constructing three SVM classifiers;

training the SVM classifier to obtain the trained SVM classifier;

and storing the three classification results, and exiting the recognition mode.

To say thatIt is clear that a Support Vector Machine (SVM) is used to construct the three classifiers: the SVM is a two-classifier per se, and is constructed as a three-classifier below to accomplish three classification tasks of yellow and red reagents and vacant site (ABC). Firstly, selecting A and B; a, C; the data sets corresponding to B and C are divided into three groups and three SVM classifiers are trained respectively to obtain three trained SVM classifiers-f (x) _A,B ，f(x) _A,c ，f(x) _B,C . When actual testing is carried out, the test data D are put into three SVM classifiers to obtain three classification results, and finally, a voting form is adopted to obtain a final classification result. The specific voting rule is as follows:

setting A ═ B ═ C ═ 0;

f(D) _A,B if the test result of (a) is class a, then a + 1; otherwise B ═ B + 1;

f(D) _A,C if the test result is class a, then a is a + 1; otherwise, C is C + 1;

f(D) _B,C if the test result of (1) is class B, then B ═ B + 1; otherwise, C is C + 1;

and finally, taking the maximum value of the values A, B and C to represent the category to which the test data belong.

In the actual use process, only the image collected by the camera needs to be preprocessed to obtain the corresponding relation M of all round points in the camera and the hole positions in the actual hole position plate and the accurate circle center coordinate of each hole position in the hole position plate

Average of the radii of the largest circumscribed circles of all dots

And then cutting all the dots in the image according to the data, inputting the cut dots into an SVM (support vector machine) three-classifier to obtain a final recognition result, displaying the experimental result in a table according to the corresponding relation between the actual hole position and the dots in the image, and automatically storing the experimental result in an Excel table.

In conclusion, the color change of the reagent is automatically identified by adopting a machine learning method to realize the automatic identification of the experimental result, the algorithm can be adapted to various light conditions and various complex environments by adopting the machine learning method, the adaptation can be carried out on various color dyes commonly used in a laboratory, and the high identification accuracy can be achieved.

Example 2:

as shown in fig. 2, the present embodiment provides an automatic reagent identification apparatus, which includes a collection module 701, a preprocessing module 702, an extraction module 703 and a classification module 704, referring to fig. 2, wherein:

an acquisition module 701: the device is used for acquiring images of at least two to-be-detected test tubes on the hole site plate;

the preprocessing module 702: the image preprocessing device is used for preprocessing the image of the tube to be detected to obtain the outline of the image;

the extraction module 703: the system is used for extracting all dots in the image outline and collecting the dots as a dot data set;

the classification module 704: and the dot data set is classified by utilizing a support vector machine algorithm to obtain a classification result.

Specifically, the preprocessing module 702 includes a first obtaining unit 7021, a second obtaining unit 7022, a processing unit 7023, an extracting unit 7024, a third obtaining unit 7025, and an obtaining unit 7026, where:

first obtaining unit 7021: the device comprises a processing unit, a processing unit and a processing unit, wherein the processing unit is used for acquiring first information, and the first information comprises a gray level image which is obtained by carrying out gray level processing on an image of the tube to be tested;

second obtaining unit 7022: the binary image processing device is used for acquiring second information, wherein the second information comprises a processed binary image obtained by performing binary processing on the first information;

processing unit 7023: the second information is subjected to opening operation processing, wherein the opening operation processing is to corrode and expand firstly to obtain a first image;

extraction unit 7024: the outline of the first image is extracted to obtain the outlines of all dots in the first image;

third obtaining unit 7025: the third information is used for obtaining third information, and the third information comprises the maximum circumscribed circle of the outline of each dot and the radius of the maximum circumscribed circle of each dot;

obtaining unit 7026: and the average value of the radius of the maximum circumscribed circle of all the dots is obtained according to the third information.

Specifically, the extracting module 703 then includes a solving unit 7031, a clipping unit 7032, a fourth obtaining unit 7033, and a corresponding unit 7034, where:

solving unit 7031: the coordinate values of four points of the circumscribed rectangle of the maximum circumscribed circle are solved according to the third information and the information of the dots;

cutting unit 7032: the coordinate value information of the four points is used for cutting the image of the test tube to be detected to obtain a cut image;

fourth acquiring unit 7033: the system comprises a folder, a display device and a control device, wherein the folder is used for acquiring specific position information of folders for placing different color reagents;

corresponding unit 7034: and the image is used for corresponding the cut image to the specific position of the folder.

Specifically, the classification module 704 includes a construction unit 7041, an obtaining unit 7042, an input unit 7043, and a storage unit 7044, where:

construction unit 7041: the method is used for constructing three SVM classifiers;

obtaining unit 7042: the SVM classifier is used for training the SVM classifier to obtain the trained SVM classifier;

input unit 7043: the SVM-based classifier is used for inputting data to be tested into the SVM classifier according to a support vector machine algorithm to obtain three classification results;

saving unit 7044: and the system is used for storing the three classification results and exiting the recognition mode.

It should be noted that, regarding the apparatus in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated herein.

Example 3:

corresponding to the above method embodiment, the present embodiment further provides an automatic reagent identification apparatus, and the automatic reagent identification apparatus described below and the automatic reagent identification method described above may be referred to in correspondence with each other.

Fig. 3 is a block diagram illustrating an automatic reagent identification apparatus 800 according to an exemplary embodiment. As shown in fig. 3, the automatic reagent recognition apparatus 800 may include: a processor 801, a memory 802. The automatic identification of the agent device 800 may also include one or more of a multimedia component 803, an I/O interface 804, and a communication component 805.

The processor 801 is configured to control the overall operation of the automatic reagent identification apparatus 800, so as to complete all or part of the steps of the automatic reagent identification method. The memory 802 is used to store various types of data to support the operation of the automatic identification device 800 for the reagent, which data may include, for example, instructions for any application or method operating on the automatic identification device 800 for the reagent, as well as application-related data, such as contact data, messages sent or received, pictures, audio, video, and the like. The Memory 802 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk or optical disk. The multimedia components 803 may include screen and audio components. Wherein the screen may be, for example, a touch screen and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may further be stored in the memory 802 or transmitted through the communication component 805. The audio assembly further comprises at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, such as a keyboard, mouse, buttons, and the like. These buttons may be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the automatic identification device 800 of the reagent and other devices. Wireless communication, such as Wi-Fi, bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them, so that the corresponding communication component 805 may include: Wi-Fi module, bluetooth module, NFC module.

In an exemplary embodiment, the automatic reagent recognition apparatus 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the automatic reagent recognition methods described above.

In another exemplary embodiment, there is also provided a computer readable storage medium comprising program instructions which, when executed by a processor, implement the steps of the above-described method for automatic identification of an agent. For example, the computer readable storage medium may be the above-described memory 802 including program instructions executable by the processor 801 of the automatic reagent identification apparatus 800 to perform the above-described automatic reagent identification method.

Example 4:

corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment, and a readable storage medium described below and an automatic identification method of a reagent described above may be referred to in correspondence with each other.

A readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the method for automatic identification of a reagent of the above-mentioned method embodiment.

The readable storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various other readable storage media capable of storing program codes.

The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for automatically identifying a reagent, comprising:

2. The method according to claim 1, wherein the preprocessing is performed on the image of the tube to be tested to obtain a profile of the image, and the method comprises:

3. The method of claim 2, wherein the extracting and collecting dots in all the image outlines into a dot data set comprises:

and corresponding the cut image to the specific position of the folder.

4. The method for automatically identifying a reagent according to claim 1, wherein the classifying the dot data set by using a support vector machine algorithm to obtain a classification result comprises:

constructing three SVM classifiers;

training the SVM classifier to obtain the trained SVM classifier;

and storing the three classification results, and exiting the recognition mode.

5. An apparatus for automatically identifying a reagent, comprising:

a preprocessing module: the image preprocessing device is used for preprocessing the image of the tube to be detected to obtain the outline of the image;

6. The apparatus for automatically identifying a reagent according to claim 5, wherein the preprocessing module comprises:

a first acquisition unit: the device comprises a processing unit, a processing unit and a processing unit, wherein the processing unit is used for acquiring first information, and the first information comprises a gray level image which is obtained by carrying out gray level processing on an image of the tube to be tested;

a second acquisition unit: the binary image processing device is used for acquiring second information, wherein the second information comprises a processed binary image obtained by performing binary processing on the first information;

a processing unit: the second information is subjected to opening operation processing, wherein the opening operation processing is to corrode and expand firstly to obtain a first image;

an extraction unit: the outline of the first image is extracted to obtain the outlines of all dots in the first image;

a third acquisition unit: the third information comprises the maximum circumscribed circle of the outline of each dot and the radius of the maximum circumscribed circle of each dot;

an acquisition unit: and the average value of the radius of the maximum circumscribed circle of all the dots is obtained according to the third information.

7. The device for the automatic identification of reagents according to claim 6, characterized in that said extraction module subsequently comprises:

a solving unit: the coordinate values of four points of the circumscribed rectangle of the maximum circumscribed circle are solved according to the third information and the information of the dots;

a cutting unit: the coordinate value information of the four points is used for cutting the image of the test tube to be detected to obtain a cut image;

a fourth acquisition unit: the system comprises a folder, a display device and a control device, wherein the folder is used for acquiring specific position information of folders for placing different color reagents;

a corresponding unit: and the image is used for corresponding the cut image to the specific position of the folder.

8. The apparatus for automatically identifying a reagent according to claim 5, wherein the classification module comprises:

a construction unit: the method is used for constructing three SVM classifiers;

an obtaining unit: the SVM classifier is used for training the SVM classifier to obtain the trained SVM classifier;

an input unit: the SVM-based classifier is used for inputting data to be tested into the SVM classifier according to a support vector machine algorithm to obtain three classification results;

a storage unit: and the system is used for storing the three classification results and exiting the recognition mode.

9. An automatic reagent identification device, comprising:

a memory for storing a computer program;

a processor for implementing the steps of the method for automatic identification of an agent according to any one of claims 1 to 4 when said computer program is executed.

10. A readable storage medium, characterized by: the readable storage medium has stored thereon a computer program which, when executed by a processor, carries out the steps of the method for automatic identification of an agent according to any one of claims 1 to 4.