Microorganism identifying and picking method, device and system and storage medium

Abstract

The invention discloses a microorganism recognition and picking method, device and system and a storage medium, and the method and device specifically comprise the steps that a plane image of a culture dish carrying microorganisms is collected, and the plane image comprises a culture dish image and the microorganisms to be recognized; the plane image is recognized, a to-be-recognized area is obtained, and the to-be-recognized area is the minimum circumscribed polygon of the culture dish; identifying the to-be-identified area based on the bacterial colony segmentation model to obtain a bacterial colony gray level image comprising a plurality of bacterial colony areas; performing morphological parameter calculation on the bacterial colony class grayscale image, and obtaining a picking position parameter of each class of bacterial colony area in the bacterial colony class by using a bacterial colony class morphological classifier; and controlling the picking equipment to pick the microorganisms based on the picking position parameters. According to the scheme, the microorganisms can be automatically picked, so that the identifying and picking efficiency is improved.

Description

Technical Field

[0001] This application relates to the technical field of bioinformatics processing, and more specifically, to a method, device, system, and storage medium for identifying and picking microorganisms. Background Art

[0002] In the fields of biology, medicine, and healthcare, it is often necessary to use petri dishes for microorganism cultivation in order to achieve specific purposes based on the cultivated microorganisms, such as bacteria identification, yeast cultivation, algae cultivation and purification, etc. For any of these uses, it is necessary to identify and pick microorganisms. However, there is currently no automated method for identification and picking, and only visual identification can be performed by operators using microscopes, and picking operations are based on visual identification, resulting in low work efficiency. Summary of the Invention

[0003] In view of this, this application provides a method, device, system, and storage medium for identifying and picking microorganisms, which realizes the automatic identification and picking of microbial communities based on AI + image recognition and precise positioning control algorithms to improve the picking efficiency.

[0004] In order to achieve the above object, the following solutions are proposed:

[0005] A method for identifying and picking microorganisms includes the steps of:

[0006] Collecting a planar image of a petri dish carrying microorganisms, where the planar image includes a petri dish image and the microorganisms to be identified;

[0007] Identifying the planar image to obtain a region to be identified, where the region to be identified is the minimum circumscribed polygon of the petri dish;

[0008] Identifying the region to be identified based on a colony segmentation model to obtain a colony class gray-scale image including multiple category colony regions, where the colony class gray-scale image includes the colony classes to be processed and other classes to be discarded;

[0009] Using a morphological classifier to perform morphological parameter calculation processing on the colony class gray-scale image and calculating the picking position parameters of the colony classes to be identified in each of the category colony regions based on the classification results;

[0010] Controlling a picking device to pick the microorganisms based on the picking position parameters.

[0011] Optionally, the identifying the planar image to obtain a region to be identified, where the region to be identified is the minimum circumscribed polygon of the petri dish, includes the steps of:

[0012] Reducing the planar image to a predetermined size;

[0013] Input the scaled-down planar image into the culture dish inner and outer edge segmentation model to obtain the connected regions of the inner and outer edges of the culture dish;

[0014] Enlarge the planar image to its original size;

[0015] Calculate the circumscribed polygon of the outer edge in the planar image to obtain the minimum circumscribed polygon.

[0016] Optionally, the step of identifying the area to be recognized based on the colony segmentation model to obtain a colony class grayscale image including multiple category colony regions includes:

[0017] Traverse the inner region of the minimum circumscribed rectangle based on the colony segmentation model to obtain the multiple category colony regions;

[0018] Stitch the multiple category regions to obtain the colony class grayscale image.

[0019] Optionally, the picking position parameters include some or all of the centroid coordinates, area, perimeter, radius, major axis diameter of the fitted ellipse, minor axis diameter of the fitted ellipse, angle, and proximity of each category colony region, and also include the center coordinates of the minimum circumscribed polygon and the length and width of the rectangle.

[0020] A microbial identification and picking device includes:

[0021] An image acquisition module configured to acquire a planar image of a culture dish carrying microorganisms, where the planar image includes a culture dish image and microorganisms to be recognized;

[0022] A first identification module configured to identify the planar image to obtain an area to be recognized, where the area to be recognized is the minimum circumscribed polygon of the culture dish;

[0023] A second identification module configured to identify the area to be recognized based on a colony segmentation model to obtain a colony class grayscale image including multiple category colony regions, where the colony class grayscale image includes colony classes to be processed and other classes to be discarded;

[0024] A parameter calculation module configured to perform morphological parameter calculation processing on the colony class grayscale image using a morphological classifier and calculate the picking position parameters of the colony class to be recognized in each category colony region based on the classification result;

[0025] A picking control module configured to control a picking device to pick the microorganisms based on the picking position parameters.

[0026] Optionally, the first identification module includes:

[0027] A reduction processing unit, configured to reduce the planar image according to a predetermined size;

[0028] An edge recognition unit, configured to input the reduced planar image into a culture dish inner and outer edge segmentation model to obtain a connected region of the inner edge and the outer edge of the culture dish;

[0029] An enlargement processing unit, configured to enlarge the planar image to the original size;

[0030] An outer edge calculation unit, configured to calculate a circumscribed polygon of the outer edge in the planar image to obtain the minimum circumscribed polygon.

[0031] Optionally, the second recognition module includes:

[0032] A recognition execution unit, configured to traverse the inner region of the minimum circumscribed polygon based on the colony segmentation model to obtain the multiple category colony regions;

[0033] A splicing processing unit, configured to splice the multiple category regions to obtain the colony category grayscale image.

[0034] Optionally, the picking position parameters include some or all of the centroid coordinates, area, perimeter, radius, major axis diameter of the fitted ellipse, minor axis diameter of the fitted ellipse, angle, and proximity of each of the category colony regions, and further include the center coordinates of the minimum circumscribed polygon and the length and width of the rectangle.

[0035] A system includes at least one processor and a memory connected to the processor, wherein:

[0036] The memory is used to store computer programs or instructions;

[0037] The processor is used to execute the computer programs or instructions so that the device system implements the recognition and picking method as described above.

[0038] A storage medium, applied to the system, the storage medium carries one or more computer programs, and the one or more computer programs can be executed by the device system, so that the device system can implement the recognition and picking method as described above.

[0039] As can be seen from the above technical solution, the present application discloses a method, apparatus, system and storage medium for identifying and picking microorganisms. Specifically, the method and apparatus collect a planar image of a culture dish carrying microorganisms, where the planar image includes a culture dish image and the microorganisms to be identified; identify the planar image to obtain a region to be identified, which is the minimum circumscribed rectangle of the culture dish; identify the region to be identified based on a colony segmentation model to obtain a colony class grayscale image including multiple category colony regions; calculate the morphological parameters of the colony class grayscale image to obtain the picking position parameters of each category colony region; and control the picking device to pick the microorganisms based on the picking position parameters. Through this solution, automatic picking of microorganisms can be achieved, thereby improving the identification and picking efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0041] Figure 1 It is a flowchart of a method for identifying and picking microorganisms according to an embodiment of the present application;

[0042] Figure 2 It is a block diagram of an apparatus for identifying and picking microorganisms according to an embodiment of the present application;

[0043] Figure 3 It is a block diagram of a system according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0045] Figure 1 It is a flowchart of a method for identifying and picking microorganisms according to an embodiment of the present application.

[0046] As Figure 1 shown, the identification and picking method provided in this embodiment is applied to an equipment system for controlling a picking device to pick microorganisms from a culture dish, such as bacteria, fungi, algae, etc. The equipment system can be understood as a computer, server or cloud platform with data calculation capabilities and information processing capabilities. The identification and picking method includes the following steps:

[0047] S1. Collect the planar image of the culture dish carrying microorganisms.

[0048] That is, after taking a photo of the culture dish with a high-definition photographing device, obtain the planar image of the culture dish taken by the photographing device. When taking a photo, a supplementary light device can be used for supplementary lighting so that the brightness of the planar image meets the requirements of subsequent processing.

[0049] S2. Perform recognition processing on the planar image to obtain the area to be recognized.

[0050] The area to be recognized is a polygonal area, specifically the area enclosed by the minimum circumscribed polygon of the culture dish in the planar image. The specific recognition process is as follows:

[0051] First, perform a reduction process on the original planar image. Specifically, it can be resized into a smaller image of 256*256.

[0052] Then, use the pre-trained inner and outer edge segmentation model of the culture dish to process the smaller image, so as to obtain the inner edge, outer edge and their connected areas of the culture dish.

[0053] Next, perform an enlargement process on the smaller image so that the smaller image is restored to its original size.

[0054] Finally, calculate the circumscribed polygon of the outer edge, such as a circumscribed quadrilateral, so as to obtain the minimum circumscribed polygon of the culture dish.

[0055] S3. Recognize the area to be recognized based on the colony segmentation model.

[0056] Through the recognition processing of the area to be recognized, obtain a colony class gray-scale image including multiple category colony areas based on the colony segmentation model. The specific process is as follows:

[0057] First, perform a traversal process on the area to be recognized based on the colony segmentation model to obtain multiple category colony areas. For example, when the minimum circumscribed polygon is a quadrilateral, starting from the upper left corner, take image patches of the original image with a window of 256*256 and input them into the colony segmentation model. The output is a 4-class semantic segmentation gray-scale image, where the gray value 256 is the fungal category area, the gray value 200 is the contamination area, and the gray value 150 is a large impurity point.

[0058] Then, perform a splicing process on the multiple category colony areas to obtain the colony class gray-scale image.

[0059] S4. Calculate the position parameters of each category colony area in the colony class gray-scale image.

[0060] The position parameters here include the centroid coordinates (CenX, CenY), area, perimeter, radius, major axis diameter of the fitted ellipse, minor axis diameter of the fitted ellipse, angle, and proximity of each category of colony area, and also include the center coordinates of the circumscribed rectangle (RectX, RectY), and the length and width of the rectangle (RectW, RectH), etc., a total of 13-dimensional features. In addition, the above 13-dimensional features can be input into the colony morphology classifier to obtain the category of each colony, such as an identifier for normal, too small circularity, too close adjacent distance, or too small radius.

[0061] S5. Control the picking device to pick microorganisms based on the position parameters.

[0062] That is, input the above position parameters into the control module of the picking device or the host computer, so that the control module or the host computer controls the picking device to perform the picking operation on the microorganisms based on the preset steps. For example, the above position parameters can be grouped into a record, and all records are summarized into a colony list, so that the picking device picks the colonies based on this colony list.

[0063] For example, calculate the number of plate positions to be eluted based on this colony list. In the pre-picked colony list, the centroid coordinates of each colony are calculated starting from the lower left corner of the image. The distance between each needle of the 8*12 array picking needles is 9X9 cm. To improve the movement efficiency, rearrange the order to minimize the movement path. The system starts picking single colonies. After each run of the 96-needle picking head is completed, it automatically moves to the elution plate position for elution, then undergoes ultrasonic cleaning, drying and disinfection, and waits. If the picking list has not been completed, continue picking, eluting, ultrasonic cleaning, drying and disinfection, and waiting. During this period, if the elution plate positions have been used up, the system will automatically prompt to replenish the elution plates.

[0064] The training samples of the petri dish recognition model of this application are 100 circles and 92 rectangles. When training, some common methods for amplifying data are used, and the UNet network model is used to train a binary semantic segmentation model. The fungi recognition model uses the ResUNet++ network to train a four-class semantic segmentation model for fungi, contaminated areas, large impurity points, and background. The training set consists of 21 large images, and 4641 images with a size of 256*256 are effectively intercepted.

[0065] As can be seen from the above technical solution, this embodiment provides a method for identifying and picking microorganisms. Specifically, a planar image of a culture dish carrying microorganisms is collected. The planar image includes a culture dish image and the microorganisms to be identified. The planar image is identified to obtain a region to be identified, which is the minimum circumscribed polygon of the culture dish. Based on a colony segmentation model, the region to be identified is identified to obtain a colony-class gray-scale image including multiple category colony regions. The morphological parameter calculation process is performed on the colony-class gray-scale image to obtain the picking position parameters of each category colony region. The picking device is controlled to pick the microorganisms based on the picking position parameters. Through this solution, the automatic picking of microorganisms can be realized, thereby improving the identification and picking efficiency.

[0066] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that includes one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0067] Although the operations are depicted in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or in sequential order. Under certain conditions, multitasking and parallel processing may be advantageous.

[0068] It should be understood that the various steps recorded in the method embodiments of the present disclosure may be executed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this regard.

[0069] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the C language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer.

[0070] Figure 2 It is a block diagram of a device for identifying and picking a microorganism according to an embodiment of the present application.

[0071] As Figure 2 shown, the identification and picking device provided in this embodiment is applied to a system for controlling a picking device to pick microorganisms such as bacteria, fungi, algae, etc. from a culture dish. The system can be understood as a computer, server, or cloud platform with data computing capabilities and information processing capabilities. The identification and picking device includes an image acquisition module 10, a first identification module 20, a second identification module 30, a parameter calculation module 40, and a picking control module 50.

[0072] The image acquisition module is used to acquire a planar image of a culture dish carrying microorganisms.

[0073] That is, after taking a picture of the culture dish with a high-definition photographing device, a planar image of the culture dish taken by the photographing device is obtained. When taking a picture, a supplementary lighting device can be used for supplementary lighting to make the brightness of the planar image meet the requirements of subsequent processing.

[0074] The first identification module is used to perform identification processing on the planar image to obtain an area to be identified.

[0075] The area to be identified is a polygonal area, specifically the area surrounded by the minimum circumscribed polygon of the culture dish in the planar image. This module includes a reduction processing unit, an edge calculation unit, an enlargement processing unit, and an edge calculation unit.

[0076] The reduction processing unit is used to perform reduction processing on the original planar image. Specifically, it can resize it into a smaller image of 256*256.

[0077] The edge calculation unit is used to process the smaller image by using a pre-trained model for segmenting the inner and outer edges of the culture dish, so as to obtain the inner edge, outer edge, and their connected regions of the culture dish.

[0078] The magnification processing unit is used to magnify the smaller image so that the smaller image is restored to its original size.

[0079] The edge computing unit is used to calculate the circumscribed polygon of the outer edge, such as a circumscribed quadrilateral, so as to obtain the minimum circumscribed polygon of the petri dish.

[0080] The second recognition module is used to recognize the area to be recognized based on the colony segmentation model.

[0081] Through the recognition processing of the area to be recognized, a colony-class grayscale image including multiple category colony areas is obtained based on the colony segmentation model. This module includes a recognition execution unit and a splicing Charlie unit.

[0082] The recognition execution unit is used to traverse the area to be recognized based on the colony segmentation model to obtain multiple category colony areas. For example, when the minimum circumscribed polygon is a quadrilateral, starting from the upper left corner, an image block of the original image with a size of 256*256 is slid as a window and input into the colony segmentation model, and the output is a 4-class semantic segmentation grayscale image, where the gray value of 256 is the fungal category area, the gray value of 200 is the pollution area, and the gray value of 150 is a large impurity point.

[0083] The splicing processing unit is used to splice multiple category colony areas to obtain the colony-class grayscale image.

[0084] The parameter calculation module is used to calculate the position parameters of each category colony area in the colony-class grayscale image.

[0085] The position parameters here include the centroid coordinates (CenX, CenY), area, perimeter, radius, major axis diameter of the fitted ellipse, minor axis diameter of the fitted ellipse, angle, and proximity of each category colony area, and also include the center coordinates of the circumscribed rectangle (RectX, RectY), and the length and width of the rectangle (RectW, RectH) and other 13-dimensional features. In addition, the above 13-dimensional features can be input into the colony morphology classifier to obtain the category of each colony, such as a label of normal, too small circularity, too close adjacent distance, or too small radius.

[0086] The picking control module is used to control the picking device to pick microorganisms based on the position parameters.

[0087] That is, the above position parameters are input into the control module of the picking device or the upper computer, so that the control module or the upper computer controls the picking device to perform a picking operation on the microorganisms based on a preset procedure. For example, the above position parameters can be grouped into a record, and all records are summarized into a colony list, so that the picking device picks colonies based on the colony list.

[0088] For example, the number of plate positions to be eluted is calculated based on this colony list. In the pre-picked colony list, the centroid coordinates of each colony are calculated starting from the lower left corner of the image. The distance between each needle of the 8*12 array picking needles is 9X9 cm. To improve the movement efficiency, the order is rearranged to minimize the movement path. Starting from the system picking single colonies, after each run of the 96-needle picking, it automatically moves to the elution plate position for elution, then undergoes ultrasonic cleaning, drying and disinfection, and waits. If the picking list has not been completed, continue picking, eluting, ultrasonic cleaning, drying and disinfection, and waiting. During this period, if the elution plate positions have been used up, the system will automatically prompt to replenish the elution plates.

[0089] The training samples of the petri dish recognition model of this application are 100 circles and 92 rectangles. When training, some common methods for amplifying data are used, and the UNet network model is used to train a binary semantic segmentation model. The fungus recognition model uses the ResUNet++ network to train a four-class semantic segmentation model for fungi, contaminated areas, large impurity points, and the background. The training set consists of 21 large images, and 4641 images with a size of 256*256 are effectively intercepted.

[0090] As can be seen from the above technical solutions, this embodiment provides a microbial recognition and picking device, specifically for collecting a planar image of a petri dish carrying microorganisms. The planar image includes the petri dish image and the microorganisms to be recognized; recognizing the planar image to obtain the area to be recognized, and the area to be recognized is the minimum circumscribed polygon of the petri dish; recognizing the area to be recognized based on the colony segmentation model to obtain a colony class gray-scale image including multiple category colony areas; performing morphological parameter calculation and processing on the colony class gray-scale image to obtain the picking position parameters of each category colony area; controlling the picking device to pick the microorganisms based on the picking position parameters. Through this solution, automatic picking of microorganisms can be realized, thereby improving the recognition and picking efficiency.

[0091] The units involved in the embodiments described in this disclosure can be implemented in software or in hardware. Among them, the name of the unit does not constitute a limitation to the unit itself in some cases. For example, the first acquisition unit can also be described as "the unit for acquiring at least two Internet protocol addresses".

[0092] The functions described above in this article can be performed at least in part by one or more hardware logic components. For example, without limitation, the exemplary types of hardware logic components that can be used include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Product (ASSP), System on Chip (SOC), Complex Programmable Logic Device (CPLD), and so on.

[0093] Figure 3 It is a block diagram of a system for an embodiment of this application.

[0094] Refer to the following Figure 3 , which shows a schematic structural diagram suitable for implementing the system in the embodiments of the present disclosure. The terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. This device system is merely an example and should not impose any limitations on the functions and usage scopes of the embodiments of the present disclosure.

[0095] The system may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 601, which may perform various appropriate actions and processes according to the programs stored in the read-only memory ROM 602 or the programs loaded from the input device 606 into the random access memory RAM 603. In the RAM, various programs and data required for the system operation are also stored. The processing device, the ROM, and the RAM are connected to each other through a bus 604. The input / output (I / O) interface 605 is also connected to the bus 604.

[0096] Generally, the following devices may be connected to the I / O interface: input devices including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 608 including, for example, magnetic tapes, hard disks, etc.; and a communication device 609. The communication device 609 may allow the system to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows a system with various devices, it should be understood that it is not required to implement or include all the shown devices. Instead, more or fewer devices may be implemented or included.

[0097] This application also provides an embodiment of a computer-readable storage medium.

[0098] The above computer-readable storage medium is applied to a system and stores one or more computer programs. When the one or more computer programs are executed by the system, the system acquires a planar image of a culture dish carrying microorganisms. The planar image includes a culture dish image and the microorganisms to be recognized. The planar image is recognized to obtain a region to be recognized, which is the minimum circumscribed polygon of the culture dish. Based on a colony segmentation model, the region to be recognized is recognized to obtain a colony-class gray-scale image including multiple category colony regions. Morphological parameter calculation processing is performed on the colony-class gray-scale image to obtain picking position parameters for each category colony region. A picking device is controlled to pick the microorganisms based on the picking position parameters. Through this solution, automatic picking of microorganisms can be achieved, thereby improving the recognition and picking efficiency.

[0099] It should be noted that the computer-readable medium in the present disclosure can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium can include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0100] In the present disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable signal medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0101] Each embodiment in this specification is described in a progressive manner. The key point of each embodiment is the difference from other embodiments. The same or similar parts among the embodiments can be referred to each other.

[0102] While the preferred embodiments of the embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the embodiments of the present invention.

[0103] Finally, it should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or terminal device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or terminal device comprising the element.

[0104] The technical solutions provided by the present invention have been introduced in detail above. Specific examples are used in this text to elaborate on the principles and implementation manners of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for identifying and picking a microorganism, characterized in that, The described recognition and picking method includes the steps of: Collecting a planar image of a culture dish carrying microorganisms, where the planar image includes the culture dish image and the microorganisms to be recognized; Recognizing the planar image to obtain a region to be recognized, where the region to be recognized is the minimum circumscribed polygon of the culture dish; Recognizing the region to be recognized based on a colony segmentation model to obtain a colony class gray-scale image including multiple category colony regions, where the colony class gray-scale image includes the colony classes to be processed and other classes to be discarded; Using a morphological classifier to perform morphological parameter calculation processing on the colony class gray-scale image and calculating the picking position parameters of the colony classes to be recognized in each of the category colony regions based on the classification results; Controlling a picking device to pick the microorganisms based on the picking position parameters.

2. The recognition and picking method according to claim 1, characterized in that, The step of recognizing the planar image to obtain a region to be recognized, where the region to be recognized is the minimum circumscribed polygon of the culture dish, includes the steps of: Reducing the planar image to a predetermined size; Inputting the reduced planar image into a culture dish inner and outer edge segmentation model to obtain the connected regions of the inner and outer edges of the culture dish; Enlarging the planar image to its original size; Calculating the circumscribed polygon of the outer edge in the planar image to obtain the minimum circumscribed polygon.

3. The identification and picking method according to claim 1, characterized in that, The step of recognizing the region to be recognized based on a colony segmentation model to obtain a colony class gray-scale image including multiple category colony regions includes the steps of: Traversing the internal region of the minimum circumscribed polygon based on the colony segmentation model to obtain the multiple category colony regions; Performing stitching processing on the multiple category regions to obtain the colony class gray-scale image.

4. The recognition method according to claim 1, wherein The picking position parameters include some or all of the centroid coordinates, area, perimeter, radius, major axis diameter of the fitted ellipse, minor axis diameter of the fitted ellipse, angle, and proximity of each of the category colony regions, and also include the center coordinates and rectangle length and width of the minimum circumscribed polygon, and the morphological classifier is trained based on multiple position parameters collected in advance.

5. An identification and picking device for microorganisms, which is applied to an equipment system, and is characterized in that, The recognition and picking device includes: An image acquisition module configured to collect a planar image of a culture dish carrying microorganisms, where the planar image includes the culture dish image and the microorganisms to be recognized; A first recognition module configured to recognize the planar image to obtain a region to be recognized, where the region to be recognized is the minimum circumscribed polygon of the culture dish; A second recognition module configured to recognize the region to be recognized based on a colony segmentation model to obtain a colony class gray-scale image including multiple category colony regions, where the colony class gray-scale image includes the colony classes to be processed and other classes to be discarded; A parameter calculation module configured to use a morphological classifier to perform morphological parameter calculation processing on the colony class gray-scale image and calculate the picking position parameters of the colony classes to be recognized in each of the category colony regions based on the classification results; A picking control module configured to control a picking device to pick the microorganisms based on the picking position parameters.

6. The identifying and picking device according to claim 5, characterized in that The first recognition module includes: A reduction processing unit, configured to reduce the planar image according to a predetermined size; An edge recognition unit, configured to input the reduced planar image into a segmentation model of the inner and outer edges of a petri dish to obtain a connected region of the inner edge and the outer edge of the petri dish; An enlargement processing unit, configured to enlarge the planar image to its original size; An outer edge calculation unit, configured to calculate a circumscribed polygon of the outer edge in the planar image to obtain the minimum circumscribed polygon.

7. The identifying and picking device according to claim 5, characterized in that The second recognition module includes: A recognition execution unit, configured to traverse an inner region of the minimum circumscribed rectangle based on the colony segmentation model to obtain the multiple category colony regions; A splicing processing unit, configured to splice the multiple category regions to obtain the colony category grayscale image.

8. The recognition device according to claim 5, characterized in that The picking position parameters include some or all of the centroid coordinates, area, perimeter, radius, major axis diameter of the fitted ellipse, minor axis diameter of the fitted ellipse, angle, and proximity of each of the category colony regions, and also include the center coordinates of the minimum circumscribed polygon and the length and width of the rectangle, and the morphology classifier is trained based on a plurality of position parameters collected in advance.

9. A system, characterized in that, Including at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs or instructions; The processor is used to execute the computer programs or instructions so that the device system can implement the recognition and picking method according to any one of claims 1 to 4.

10. A storage medium, applied to a system, characterized in that, The storage medium carries one or more computer programs, and the one or more computer programs can be executed by the device system, so that the device system can implement the recognition and picking method according to any one of claims 1 to 4.

Images