WO2017166778A1 - 细菌鉴定方法及装置 - Google Patents

细菌鉴定方法及装置 Download PDF

Info

Publication number
WO2017166778A1
WO2017166778A1 PCT/CN2016/102094 CN2016102094W WO2017166778A1 WO 2017166778 A1 WO2017166778 A1 WO 2017166778A1 CN 2016102094 W CN2016102094 W CN 2016102094W WO 2017166778 A1 WO2017166778 A1 WO 2017166778A1
Authority
WO
WIPO (PCT)
Prior art keywords
colony
identified
information
species
feature
Prior art date
Application number
PCT/CN2016/102094
Other languages
English (en)
French (fr)
Inventor
李辰
Original Assignee
李辰
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 李辰 filed Critical 李辰
Publication of WO2017166778A1 publication Critical patent/WO2017166778A1/zh

Links

Images

Classifications

    • C—CHEMISTRY; METALLURGY
    • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
    • C12M—APPARATUS FOR ENZYMOLOGY OR MICROBIOLOGY; APPARATUS FOR CULTURING MICROORGANISMS FOR PRODUCING BIOMASS, FOR GROWING CELLS OR FOR OBTAINING FERMENTATION OR METABOLIC PRODUCTS, i.e. BIOREACTORS OR FERMENTERS
    • C12M1/00—Apparatus for enzymology or microbiology
    • C12M1/34—Measuring or testing with condition measuring or sensing means, e.g. colony counters
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
    • G06V20/693—Acquisition
    • C—CHEMISTRY; METALLURGY
    • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
    • C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
    • C12Q1/00—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions
    • C12Q1/02—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions involving viable microorganisms
    • C12Q1/04—Determining presence or kind of microorganism; Use of selective media for testing antibiotics or bacteriocides; Compositions containing a chemical indicator therefor
    • C—CHEMISTRY; METALLURGY
    • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
    • C12M—APPARATUS FOR ENZYMOLOGY OR MICROBIOLOGY; APPARATUS FOR CULTURING MICROORGANISMS FOR PRODUCING BIOMASS, FOR GROWING CELLS OR FOR OBTAINING FERMENTATION OR METABOLIC PRODUCTS, i.e. BIOREACTORS OR FERMENTERS
    • C12M1/00—Apparatus for enzymology or microbiology
    • C12M1/36—Apparatus for enzymology or microbiology including condition or time responsive control, e.g. automatically controlled fermentors
    • C—CHEMISTRY; METALLURGY
    • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
    • C12M—APPARATUS FOR ENZYMOLOGY OR MICROBIOLOGY; APPARATUS FOR CULTURING MICROORGANISMS FOR PRODUCING BIOMASS, FOR GROWING CELLS OR FOR OBTAINING FERMENTATION OR METABOLIC PRODUCTS, i.e. BIOREACTORS OR FERMENTERS
    • C12M41/00—Means for regulation, monitoring, measurement or control, e.g. flow regulation
    • C12M41/30—Means for regulation, monitoring, measurement or control, e.g. flow regulation of concentration
    • C12M41/36—Means for regulation, monitoring, measurement or control, e.g. flow regulation of concentration of biomass, e.g. colony counters or by turbidity measurements
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
    • G06V20/695—Preprocessing, e.g. image segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
    • G06V20/698—Matching; Classification

Definitions

  • the invention relates to the field of image processing technology and bacterial identification technology, and in particular to a method and device for identifying bacteria.
  • bacterial identification is often required for treatment or research purposes, and the type of bacteria is identified by a certain bacterial identification method to meet the requirements of treatment, research or teaching.
  • the commonly used bacterial identification method mainly identifies bacteria according to the physiological activity characteristics of the bacteria by biochemical methods. Before the identification, the bacteria are separated into pure medium to obtain pure colonies, and then the colony biochemical tubes are taken to observe the color change. In this way, the specific colony species is judged, or the colony is made into a suspension, and the suspension is identified according to a special identification card and a special analyzer to determine the colony species.
  • the above biochemical methods are used to identify the colony species, and the colonies can be made into suspensions or colonies which can be fully dispersed in the liquid.
  • the purity of the colonies is very high, and the identification technology of the appraisers is very high, and in the identification process, when When the identification personnel are exposed to bacteria, there is a certain safety risk, and the instruments and equipment required for traditional identification are often expensive and bulky, which leads to complex identification of bacteria and high cost, which makes the identification of bacteria difficult to promote and has potential safety hazards.
  • the object of the present invention is to provide a method and a device for identifying bacteria, which can realize the identification of colonies by a non-contact method and improve the safety of the identification personnel; the bacteria identification method and device can identify the bacteria of the personnel And the professional requirements of medical treatment are very low; through the automated information processing process, the identification process can be completed quickly, and the identification results can be quickly obtained, which greatly improves the identification efficiency, and the identification result is highly accurate; it can be obtained in various ways. Identification of colony images, and the bacteria identification device is lighter and less expensive than traditional identification instruments, thereby greatly reducing the cost of identification and the requirements of the site, facilitating the promotion of bacterial identification technology and playing a greater role, so that the technology can benefit more people.
  • the present invention provides a method for identifying bacteria, the method comprising the steps of:
  • the embodiment of the present invention provides the first possible implementation manner of the foregoing first aspect, wherein the step of extracting colony feature information from the image of the colony to be identified includes:
  • the colony characteristic information of the colony to be identified is generated according to the size, color, shape, gloss, stereoscopic feature and dryness and wetness of the colony to be identified.
  • an embodiment of the present invention provides a second possible implementation manner of the foregoing first aspect, wherein, according to the extracted colony feature information and a pre-established colony feature database, the corresponding colony to be identified is determined.
  • the steps of the species information include:
  • colony information set including the colony feature information of the to-be-identified colony from the pre-established colony feature database according to the corresponding relationship between the preset colony feature information and the colony information collection identifier, wherein the colony feature library includes a plurality of colony information sets, the plurality of colony information sets respectively including colony information collection identifiers corresponding to respective colony information sets, and colony characteristics of a plurality of colonies;
  • the species information corresponding to the colony characteristic having the highest matching degree is determined as the species information corresponding to the colony to be identified.
  • the embodiment of the present invention provides the third possible implementation manner of the foregoing first aspect, wherein the step of acquiring an image of the colony to be identified includes:
  • the image of the colony to be identified is collected by the colony picture collector provided by the terminal, or the image of the colony to be identified transmitted by the device other than the terminal is received, or the stored image of the colony to be identified is locally retrieved.
  • the embodiment of the present invention provides the fourth possible implementation manner of the foregoing first aspect, wherein the method further includes:
  • the species information corresponding to each type of colony the species information including the colony species and the colony characteristic information corresponding to the colony species;
  • a correspondence relationship between the colony characteristic information of the various types of colonies and the corresponding colony information collection identifier is generated, and a colony feature library is established.
  • the embodiment of the present invention provides the fifth possible implementation manner of the foregoing first aspect, wherein the step of extracting colony feature information from the image of the colony to be identified includes:
  • the colony characteristic information of the colony to be identified is generated according to the size, color, shape, gloss and dryness of the colony to be identified.
  • the embodiment of the present invention provides a sixth possible implementation manner of the foregoing first aspect, wherein, according to the extracted colony feature information and a pre-established colony feature database, the corresponding colony to be identified is determined.
  • the steps of the species information include:
  • the species information corresponding to the colony characteristic having the highest matching degree is determined as the species information corresponding to the colony to be identified.
  • the embodiment of the present invention provides the seventh possible implementation manner of the foregoing first aspect, wherein the method further includes:
  • the species information including the colony species and the colony characteristics corresponding to the colony species;
  • a colony feature library is established based on the species information corresponding to the respective species of colonies.
  • the present invention provides a bacterial identification device, the device comprising:
  • a first obtaining module configured to or used to acquire an image of the colony to be identified
  • An extraction module configured to or for extracting colony feature information from the image of the colony to be identified
  • a determination module configured to determine the species information corresponding to the colony to be identified according to the extracted colony feature information and the pre-established colony feature library.
  • the embodiment of the present invention provides the first possible implementation manner of the foregoing second aspect, wherein the extracting module includes:
  • An extracting unit configured to or used to extract the size, color, shape, gloss, stereoscopic feature, and dryness and wetness of the colony to be identified from the image of the colony to be identified;
  • a generating unit configured to generate colony feature information of the colony to be identified according to the size, color, shape, gloss, stereoscopic feature, and dryness and wetness of the colony to be identified.
  • the embodiment of the present invention provides the second possible implementation manner of the foregoing second aspect, wherein the determining module includes:
  • a first determining unit configured to or for determining a colony including the colony feature information of the colony to be identified from the pre-established colony feature database according to a preset correspondence between the colony feature information and the colony information set identifier a collection of information, wherein the colony signature library comprises a plurality of colony letters And the plurality of colony information sets respectively include a colony information collection identifier corresponding to each colony information set and colony characteristics of the plurality of colonies;
  • a second determining unit configured to or used to determine a colony characteristic having the highest degree of matching with the colony feature information of the colony to be identified from the colony information set including the colony feature information of the colony to be identified;
  • a third determining unit configured to determine the species information corresponding to the colony feature with the highest degree of matching as the species information corresponding to the colony to be identified.
  • the embodiment of the present invention provides a third possible implementation manner of the foregoing second aspect, where the first acquiring module includes:
  • the collecting unit is configured to be used to collect an image of the colony to be identified by the colony picture collector provided by the terminal;
  • a receiving unit configured to receive an image of a colony to be identified transmitted by a device other than the terminal
  • the retrieval unit is configured or used to locally retrieve the stored image of the colony to be identified.
  • the embodiment of the present invention provides the fourth possible implementation manner of the foregoing second aspect, wherein the device further includes:
  • a second obtaining module configured to obtain the species information corresponding to each type of colony, the species information including the colony species and the colony characteristic information corresponding to the colony species;
  • a collection determining module configured to be used to determine a colony information set corresponding to each type of colony according to the species information corresponding to the respective species of colonies;
  • a establishing module configured to generate a corresponding relationship between the colony feature information of the various types of colonies and the corresponding colony information collection identifier, and establish a colony feature library.
  • the embodiment of the present invention provides the fifth possible implementation manner of the foregoing second aspect, wherein the extracting module includes:
  • An extracting unit configured to or used to extract a size, a color, a shape, a gloss, and a dryness and wetness of the colony to be identified from an image of the colony to be identified;
  • a generating unit configured to generate colony characteristic information of the colony to be identified according to the size, color, shape, gloss, and dryness and wetness of the colony to be identified.
  • the embodiment of the present invention provides the sixth possible implementation manner of the foregoing second aspect, wherein the determining module includes:
  • a first determining unit configured to be used for determining, from the pre-established colony feature library, a colony feature having the highest degree of matching with the colony feature information of the colony to be identified;
  • the second determining unit is configured to be used to determine the species information corresponding to the colony feature having the highest degree of matching as the species information corresponding to the colony to be identified.
  • the embodiment of the present invention provides the seventh possible implementation manner of the foregoing second aspect, wherein the device further includes:
  • a second obtaining module configured to obtain the species information corresponding to each type of colony, the species information including a colony species and a colony characteristic corresponding to the colony species;
  • a building module is configured or configured to establish a colony signature library based on the species information corresponding to the respective species of colonies.
  • the method for identifying bacteria comprises: obtaining an image of a colony to be identified; extracting colony feature information from the image of the colony to be identified; and determining the colony characteristic information based on the extracted colony feature information and the pre-established colony feature database Corresponding species information of the colony to be identified; the bacteria identification device comprises a first acquisition module configured to obtain an image of the colony to be identified; an extraction module configured to be used or to extract from the image of the colony to be identified The colony characteristic information is determined or configured to determine the species information corresponding to the colony to be identified according to the extracted colony feature information and the pre-established colony feature database.
  • the method and device for identifying bacteria can bring at least the following beneficial effects: the strain identification of the colonies is realized by a non-contact method, and the safety of the identification personnel is improved; the method and device for identifying the bacteria are identified The professional requirements for bacteria and medical treatment of personnel are very low; the identification process can be completed quickly through automated information processing, and the identification results can be quickly obtained, which greatly improves the identification efficiency, and the identification results are highly accurate; The way to obtain the image of the colony to be identified, the cost of the bacteria identification device is very low, thereby greatly reducing the cost of identification.
  • Example 1 is a schematic flow chart showing a method for identifying bacteria provided in Example 1 of the present invention
  • FIG. 2 is a schematic view showing the structure of a bacteria identification device provided in Embodiment 2 of the present invention.
  • the biochemical method is used to identify the colony species, and the colony can be made into a suspension or the colony can be fully dispersed in the liquid, and the purity of the colony is very high, and the identification technology of the identification personnel is very high, and In the identification process, when the identification personnel are exposed to bacteria, there is a certain safety risk, which leads to complex bacteria identification, high cost and potential safety hazards.
  • the present invention provides a method and device for identifying bacteria, which realizes the identification of colonies by non-contact method, and improves the safety of the identification personnel; the bacteria identification method and device for the bacteria and medical aspects of the identification personnel
  • the professional requirements are very low; through the automated information processing process, the identification process can be completed quickly, and the identification results can be quickly obtained, the identification efficiency is greatly improved, and the identification results are highly accurate; the colonies to be identified can be obtained in various ways.
  • Image the bacteria identification device costs very low, which greatly reduces the cost of identification. Description will be made below by way of examples.
  • an embodiment of the present invention provides a method for identifying bacteria.
  • the method includes the following steps S103-S105.
  • Step S101 acquiring the species information corresponding to each type of colony, and the strain information includes colony species and colony characteristic information corresponding to the colony species;
  • Step S102 Determine the colony information set corresponding to each type of colony according to the species information corresponding to each type of colony, and generate a correspondence relationship between the colony feature information of each type of colony and the corresponding colony information collection identifier, and establish a colony feature database.
  • the species information corresponding to each type of colony can be obtained according to biological and medical classification of the colonies.
  • the above species information also includes information on the living environment and activities of each type of colony.
  • the colony characteristic information in the strain information includes the size, color, shape, gloss, dryness and wetness and/or stereoscopic characteristics of the colony; the colony species and the colony characteristics are in one-to-one correspondence.
  • the colony feature library includes a plurality of colony information sets, and the plurality of colony information sets respectively include colony information collection identifiers corresponding to the respective colony information sets and colony characteristics of the plurality of colonies.
  • colony characteristics such as colony size, glossiness, and dryness and wetness can be directly characterized by numerical values.
  • a correspondence relationship between numerical ranges of colony features that can be numerically characterized by at least one of the colony information set and the colony feature information may be established in advance; the correspondence relationship is The colony information set identifier described above is expressed in association with a numerical range of colony characteristics that can be numerically characterized.
  • the process of determining the colony information set corresponding to a species of colony first extracting the value of the colony feature associated with the colony information collection identifier from the obtained colony feature information of the species of the colony, and then according to the extracted colony feature The numerical value determines the numerical range of the colony characteristics in which the numerical value falls; finally, the colony information set corresponding to the colony of the species is determined by the correlation between the numerical range of the colony characteristics of the numerical value and the colony information collection identifier. Thereby, the above process is repeated, and the correspondence relationship between the colony characteristic information of each type of colony and the corresponding colony information collection identifier is generated, and a colony feature library is established.
  • a one-to-one correspondence between the colony species and the colony characteristic information can be established, that is, the species information of each species of colonies is established, and the established species of the various species of colonies are established.
  • the information is stored in a corresponding database, and a database containing the species information of each type of colony is used as a colony feature library.
  • the strains of the colonies to be identified can be identified by the following steps S103-S105.
  • Step S103 acquiring an image of the colony to be identified
  • Step S104 extracting colony feature information from the image of the colony to be identified
  • Step S105 Determine the species information corresponding to the colony to be identified according to the extracted colony feature information and the pre-established colony feature database.
  • the colony to be identified Before obtaining the image of the colony to be identified through the above step S103, the colony to be identified needs to be purified by the culture medium, and the pure purpose is to obtain the colony of the standard strain with the relevant strain. Consistent colonies to facilitate identification of the colony species of the colony to be identified. In the embodiment of the present invention, the purity of the colony to be identified after the fractionation is very low, and the identification of most colonies is applied.
  • the image of the colony to be identified can be obtained by any one of the following three methods.
  • the first way the image of the colony to be identified is collected by the colony picture collector provided by the terminal.
  • the terminal may be a mobile terminal such as a mobile phone or a tablet computer
  • the colony picture collector may be a camera disposed on the mobile terminal; the colony picture collector may also be a CMOS (Complementary Metal Oxide Semiconductor) camera.
  • the mobile terminal or CMOS camera automatically transmits the image of the colony to be identified to the colony identification device by taking an image of the colony to be identified on site.
  • the second way receiving an image of the colony to be identified transmitted by the device other than the terminal.
  • the device other than the terminal may be a mobile terminal such as a mobile phone or a tablet computer, or may be a fixed terminal such as a desktop computer.
  • the mobile terminal or the fixed terminal transmits the image of the to-be-identified colony to be photographed to the colony identification device through a wired, wireless or transmission interface.
  • the third way retrieve the stored image of the colony to be identified from the local.
  • the collected images of the colonies to be identified may be stored in the local storage in advance, and when it is necessary to identify a certain colony, the image of the colony to be identified may be retrieved from the local storage.
  • the colony feature information can be extracted from the image of the colony to be identified by the above step S104, which can be specifically extracted by the following steps S1041-S1042.
  • Step S1041 extracting the size, color, shape, gloss, and dryness and wetness and/or stereoscopic characteristics of the colony to be identified from the image of the colony to be identified;
  • Step S1042 generating colony characteristic information of the colony to be identified according to the size, color, shape, gloss, stereoscopic characteristics and dryness and wetness of the colony to be identified.
  • step S1041 the size of the colony to be identified is extracted, firstly, the position of the colony to be identified in the image of the colony to be identified needs to be located, and then the area of the colony to be identified is determined according to the position of the colony to be identified, and The area of the area is calculated, and the size of the colony to be identified is determined by the calculated area.
  • the color comparison card includes a one-to-one correspondence between the respective colors and values.
  • the shape of the colony to be identified is extracted, firstly, the area occupied by the colony to be identified is determined, and then the boundary line of the area is measured, and the shape corresponding to the colony to be identified is determined according to the measurement result and the shape calculation algorithm.
  • Extracting the gloss of the colony to be identified first determining the area occupied by the colony to be identified in the image, then calculating the contrast and brightness of the image in the area, and finally determining according to the calculated contrast, brightness and image glossiness criteria.
  • the gloss of the colonies to be identified first determining the area occupied by the colony to be identified in the image, then calculating the contrast and brightness of the image in the area, and finally determining according to the calculated contrast, brightness and image glossiness criteria.
  • Extracting the stereoscopic features of the colonies to be identified firstly identifying the characteristic regions of the identified colonies in the image, and then pre-processing the acquired images, and then identifying the feature points in the image to identify the stereoscopic features of the objects in the image. Finally, the stereoscopic features of the colonies to be identified are extracted.
  • Extracting the dryness and wetness of the colony to be identified first determining the area occupied by the colony to be identified in the image, and then calculating the illuminance of the image in the area, and determining the colony to be identified according to the calculated reflectance and dryness and wetness comparison table The degree of dryness and wetness; wherein the dryness and wetness comparison table includes a one-to-one correspondence between the reflective pair and the degree of dryness and wetness.
  • image features and/or stereo features such as size, color, shape, gloss, dryness and wetness of the colony to be identified are extracted, and the size, color, and size of the image may also be adopted by existing image processing technologies.
  • Image feature extraction techniques such as shape, gloss, and wet/dryness and/or stereoscopic features are implemented.
  • the above-mentioned step S105 After extracting the colony feature information of the colony to be identified by the above method, the above-mentioned step S105, according to the extracted colony feature information and the pre-established colony feature database, determine the species information corresponding to the colony to be identified, specifically by the following steps S1051-S1052 to make sure.
  • Step S1051 Determine a colony information set including colony feature information of the colony to be identified from the pre-established colony feature database according to the corresponding relationship between the preset colony feature information and the colony information collection identifier, and the colony feature information including the colony to be identified In the colony information set, the colony characteristic having the highest degree of matching with the colony characteristic information of the colony to be identified is determined;
  • Step S1052 determining the species information corresponding to the colony feature with the highest matching degree as the species information corresponding to the colony to be identified.
  • the colony feature value associated with the colony information set identifier is extracted from the acquired colony feature information of the colony to be identified, and then the numerical value of the extracted colony feature is determined according to the extracted colony feature value.
  • the numerical range of the colony characteristics; finally, the colony information set corresponding to the colony to be identified is determined by the correlation between the numerical range of the colony characteristics of the numerical value and the colony information collection identifier.
  • the colony characteristics of the colony to be identified are Each feature in the information and the colony information collection or each of the bacteria in the signature database
  • Each of the features of the drop feature is aligned, including the size of the colony to be identified and the size of the colony in each colony feature; the color of the colony to be identified and the color of the colony in each colony feature; Shape and colony shape in each colony; greater than the gloss of the colony to be identified and the colony gloss in each colony; the stereoscopic characteristics of the colony to be identified and the colony stereotypes in each colony; and The degree of dryness and wetness of the colonies and the degree of dryness and wetness of the colonies in each colony feature were identified. Then, the number of coincident feature items of the colony feature is
  • the statistical characteristics of the colonies with the highest matching characteristic items are determined as the colony characteristics with the highest matching degree with the colony characteristics of the colonies to be identified.
  • the strain information corresponding to the colony characteristic with the highest matching degree may be determined as the species information corresponding to the colony to be identified by the above step S1052.
  • the colony information set including the colony characteristic information of the colony to be identified is first determined from the pre-established colony feature library, and then the colony characteristic information including the colony to be identified is included.
  • the colony characteristic having the highest matching degree with the colony characteristic information of the colony to be identified is determined, and only the colony information information of the colony information to be identified including the colony information information of the colony characteristic to be identified is matched, and no need to
  • the colony characteristic information of the colony to be identified and the matching of all the colony characteristics in the colony characteristic library can shorten the time of detecting the colony and further improve the identification efficiency of the colony.
  • the matching degree of the colony characteristic information of the colony to be identified is determined, if the matching degree of all the colony characteristics in the colony feature database and the colony feature information of the colony to be identified is lower than a preset matching degree, At this time, it is impossible to accurately determine the species of the colony to be identified according to the colony characteristics in the colony characteristic library, and it is also necessary to supplement the corresponding identification technology to supplement the brief biochemical information of the bacteria corresponding to the identified colony, and the colony to be identified according to the supplementary identification The brief biochemical information of the bacteria is used to further determine the species of the colony to be identified.
  • the brief biochemical information of the bacteria corresponding to the identified species to be identified may be generated according to the identified strains.
  • the strain information of the colony is identified, and the information of the strain can be added to the colony characteristic database to provide an identification basis for the identification of the subsequently identified colony, thereby also improving the identification efficiency of the colony.
  • a large number of colony images may be stored in the colony feature library, and each colony image corresponds to unique species information.
  • each colony image corresponds to unique species information.
  • determining the species information corresponding to the colony to be identified can be realized by the following process.
  • the colony image with the highest matching degree of the colony characteristic information of the colony to be identified is determined from the colony image in the colony characteristic library; the strain information corresponding to the colony image with the highest matching degree is determined as the corresponding bacteria of the colony to be identified Kind of information.
  • the above species information includes colony characteristics corresponding to colony species and colony species.
  • each feature in the colony characteristic information of the colony to be identified is compared with each of the colony features of each colony image, including the size of the colony to be identified and the image of each colony Colony size in colony characteristics; colony color in colony characteristics of each colony image compared to the color of the colony to be identified; colony of the image of each colony than the shape of the colony to be identified Colony shape in the feature; colony gloss in the colony characteristics of the colony to be identified and the colony characteristics of each colony image; stereoscopic characteristics of the colony to be identified and colony stereoscopic features in each colony feature; and colony to be identified
  • the degree of dryness and wetness is the degree of dryness and wetness of the colonies in the colony characteristics of each colony image. Then, the number of coincident feature items of the colony feature is counted based on the comparison result of each feature in the colony characteristics of each colony image. Among them, the data obtained by comparison
  • the statistical characteristics of the colonies with the highest matching characteristic items are determined as the colony characteristics with the highest matching degree with the colony characteristics of the colonies to be identified.
  • the strain information corresponding to the colony image containing the colony characteristic with the highest matching degree is determined as the to-be-identified
  • the species information corresponding to the colony is determined as the to-be-identified
  • the identifier when identifying the species information of the colony to be identified, it is only necessary to obtain an image of the colony to be identified, and the identifier does not need to actually contact the colon to be identified, thereby avoiding the bacterial infection caused by contact with the colon to be identified.
  • the appraisers improve the safety of the appraisers; in the entire appraisal process, the appraisers do not need to master very professional bacteria and medical knowledge, only need to master the operation of related equipment and related software, and the professional requirements for the appraisers are very low.
  • the image of the colony to be identified can be quickly obtained, and the identification process can be quickly completed by the automated information processing equipment and software, so that the identification result can be quickly obtained, and the identification result is greatly improved.
  • the identification efficiency is high, and the identification result is highly accurate; in the present invention, the image of the colony to be identified can be obtained in various ways, and the entire identification process does not require the payment for the preservation, transportation and management of the identified colony, and the appraisal personnel
  • the cost to be paid is also low, and the cost of the bacteria identification device is very low. Thus greatly reducing the cost of identification.
  • the colony identification method comprises: obtaining an image of the colony to be identified; extracting colony feature information from the image of the colony to be identified; determining the corresponding colony to be identified according to the extracted colony feature information and the pre-established colony feature database; Species information.
  • the bacteria identification method and device have low requirements on the bacteria and medical specialties of the appraisers; through the automated information processing process
  • the identification process can be completed quickly, and the identification result can be quickly obtained, the identification efficiency is greatly improved, and the identification result is highly accurate; the image of the colony to be identified can be obtained in various ways, and the cost of the bacteria identification device is very low, thereby greatly reducing The cost of identification.
  • an embodiment of the present invention provides a bacteria identification device, which includes:
  • the first obtaining module S1 is configured to or used to acquire an image of the colony to be identified;
  • An extraction module S2 configured to or for extracting colony feature information from an image of the colony to be identified
  • the determining module S3 is configured or configured to determine the species information corresponding to the colony to be identified based on the extracted colony feature information and the pre-established colony feature library.
  • the colony feature library needs to be established through the following second obtaining module and the establishing module and/or the set determining module.
  • the above device further includes a second acquisition module, an establishment module and/or a collection determination module;
  • a second obtaining module configured to obtain the species information corresponding to each type of colony, and the strain information includes colony species and colony characteristic information corresponding to the colony species;
  • a collection determining module configured to or be used to determine a colony information set corresponding to each species of colonies according to the species information corresponding to each species of colonies;
  • a building module is configured to generate or generate a colony feature library based on the correspondence between the colony or strain characteristic information of each species of colonies and the corresponding colony information collection identifier.
  • the above obtaining module can obtain the species information corresponding to each type of colony according to the classification of the colonies by biology and medicine.
  • the above species information also includes information on the living environment and activities of each type of colony.
  • the colony characteristics in the strain information include the size, color, shape, gloss and dryness and wetness and/or stereoscopic characteristics of the colony; the colony species correspond one-to-one with the colony characteristics.
  • the establishing module may establish a one-to-one correspondence between the colony species and the colony characteristics according to the colony characteristics corresponding to the colonies of each species determined by the second obtaining module. That is, the species information of each type of colony is established, and the established species information of each type of colony is stored in a corresponding database, and a database containing the species information of each type of colony is used as a colony characteristic library.
  • the colony to be identified needs to be purified by the medium first, and the pure purpose is to be the standard strain with the related strain.
  • the colonies are consistent colonies to facilitate identification of the colony species of the colonies to be identified.
  • the purity of the colony to be identified after the fractionation is very low, and the identification of most colonies is applied.
  • the first acquisition module S1 acquires an image of the colony to be identified through the following acquisition unit, receiving unit or retrieval unit.
  • the first acquiring module S1 includes an acquiring unit, a receiving unit, or a calling unit.
  • the collecting unit is configured to be used to collect an image of the colony to be identified by the colony picture collector provided by the terminal;
  • a receiving unit configured to receive an image of a colony to be identified transmitted by a device other than the terminal
  • the retrieval unit is configured or used to locally retrieve the stored image of the colony to be identified.
  • the above acquisition unit may be a mobile terminal such as a mobile phone or a tablet computer embedded with a camera, or may be a CMOS camera.
  • the collecting unit automatically records the image of the colony to be identified to the colony identification device by taking an image of the colony to be identified on site.
  • the device other than the terminal may be a mobile terminal such as a mobile phone or a tablet computer, or may be a fixed terminal such as a desktop computer.
  • the mobile terminal or the fixed terminal transmits the image of the to-be-identified colony to be photographed to the receiving unit through a wired, wireless or transmission interface.
  • the collected images of the colonies to be identified may be stored in the local storage in advance, and when the identification of a certain colony is required, the retrieving unit may retrieve the colony to be identified from the local storage. image.
  • the colony feature information may be extracted from the image of the colony to be identified by the extraction module S2, and may be extracted by the following extraction unit and the generation unit.
  • the above extraction module S2 includes an extraction unit and a generation unit
  • An extracting unit configured to or for extracting, from an image of the colony to be identified, a size, a color, a shape, a gloss, and a dry and wet degree and/or a stereoscopic feature of the colony to be identified;
  • the generating unit is configured or used to generate colony characteristic information of the colony to be identified according to the size, color, shape, gloss, dryness and wetness and/or stereoscopic characteristics of the colony to be identified.
  • the extracting unit extracts the size of the colony to be identified, firstly needs to locate the position of the colony to be identified in the image of the colony to be identified, and then determine the area to be identified in the image according to the position of the colony to be identified, and calculate the area. The area of the colony to be identified is determined by the calculated area.
  • the extracting unit extracts the color of the colony to be identified, first determines the area occupied by the colony to be identified in the image, and then counts the pixel value of each pixel in the area, and converts the pixel value into a corresponding value, and finally according to each pixel.
  • the color corresponding to the point, the color comparison card and the probability of each pixel distribution determine the color of the colony to be identified.
  • the color comparison card includes a one-to-one correspondence between the respective colors and values.
  • the extracting unit extracts the shape of the colony to be identified, first determines the area occupied by the colony to be identified in the image, and then measures the boundary line of the area, and determines the shape corresponding to the colony to be identified according to the measurement result and the shape calculation algorithm.
  • the extraction unit extracts the gloss of the colon to be identified, first determines the area occupied by the colony to be identified in the image, and then calculates the contrast and brightness of the image in the area, and finally judges the standard according to the calculated contrast, brightness and image gloss. Determine the gloss of the colonies to be identified.
  • Extracting the stereoscopic features of the colonies to be identified firstly identifying the characteristic regions of the identified colonies in the image, and then pre-processing the acquired images, and then identifying the feature points in the image to identify the stereoscopic features of the objects in the image. Finally, the stereoscopic features of the colonies to be identified are extracted.
  • the extracting unit extracts the dryness and wetness of the colony to be identified, first determines the area occupied by the colony to be identified in the image, and then calculates the glare of the image in the area, and determines the illuminance according to the calculated reflectance and dryness and wetness comparison table.
  • the extracting unit extracts image features such as size, color, shape, gloss, dryness and wetness, and/or stereoscopic features of the colony to be identified, and may also use image processing technology to reduce the size of the image.
  • Image feature extraction techniques such as color, shape, gloss, and wet and dryness and/or stereoscopic features are implemented.
  • the above-mentioned generating module will identify the size, color, shape, gloss, stereoscopic characteristics and dryness of the colony to be identified.
  • the degree of wetness constitutes the colony characteristic information of the colony to be identified, and the species of the colony to be identified is determined according to the colony characteristics of the colony to be identified, and finally the colony characteristics and the strain of the colony to be identified are used as the colony characteristic information of the colony to be identified.
  • the strain type information corresponding to the colony to be identified can be determined by the above determining module S3.
  • the determining module S3 may be determined by the following first determining unit, third determining unit, and/or second determining unit.
  • the determining module includes a first determining unit, a third determining unit, and/or a second determining unit;
  • a first determining unit configured to or be configured to determine a colony information set including colony feature information of the colony to be identified from the pre-established colony feature database according to the preset relationship between the preset colony feature information and the colony information set identifier, wherein
  • the colony feature library includes a plurality of colony information sets, and the plurality of colony information sets respectively include colony information collection identifiers corresponding to the respective colony information sets and colony characteristics of the plurality of colonies;
  • a second determining unit configured to or for determining a colony characteristic having the highest degree of matching with the colony feature information of the colony to be identified from the colony information set including the colony feature information of the colony to be identified;
  • the third determining unit is configured to or used to determine the species information corresponding to the colony feature with the highest matching degree as the species information corresponding to the colony to be identified.
  • the first determining unit obtains the colony information set including the colony feature information of the colony to be identified from the pre-established colony feature database according to the corresponding relationship between the preset colony feature information and the colony information set identifier.
  • the colony characteristic information of the colony to be identified is extracted from the colony characteristic of the colony information collection identifier, and then based on the value of the extracted colony characteristic, The numerical range of the colony characteristics in which the numerical value falls is determined; finally, the colony information set corresponding to the colony to be identified is determined by the correlation between the numerical range of the colony characteristics of the numerical value and the colony information collection identifier.
  • the second determining unit When determining the degree of matching with the colony feature information of the colony to be identified, the second determining unit first needs to compare the colony feature information of the colony to be identified with each colony information set or the feature of each colony in the feature library, wherein Each feature in the colony characteristic information of the identified colony is compared with each of the colony information sets or each colony feature in the feature library, including the size of the colony to be identified and the colony size in each colony feature.
  • the first determining unit counts the number of matching feature items of the colony feature according to the comparison result of each feature in each colony feature in the colony feature library. Among them, the data obtained by comparison and statistics are schematically shown in Table 1 below.
  • the first determining unit determines the colony characteristics of the statistically most consistent feature items as the colony characteristics having the highest matching degree with the colony characteristics of the colonies to be identified.
  • the second species determining unit may determine the strain information corresponding to the colony feature with the highest matching degree as the corresponding colony to be identified. Species information.
  • the colony information set including the colony feature information of the colony to be identified is first determined from the pre-established colony feature library, and then In the colony information set for identifying the colony characteristic information of the colony, the colony characteristic having the highest matching degree with the colony characteristic information of the colony to be identified is determined, and only the colony characteristics of the colony to be identified are determined in the colony information set including the colony characteristic information of the colony to be identified. The information is matched, and it is not necessary to match the colony characteristic information of the colony to be identified with all the colony characteristics in the colony characteristic database, thereby shortening the time of detecting the colony and further improving the identification efficiency of the colony.
  • the second determining unit when the first determining unit determines the matching degree of the colony feature information of the colony to be identified, if the matching degree of all the colony features in the colony feature database and the colony characteristics of the colony to be identified is lower than the preset matching At the time, at this time, the second determining unit cannot accurately determine the species of the colony to be identified according to the colony characteristics in the colony characteristic library, and needs to supplement the corresponding identification technology to supplement the brief biochemical information identifying the bacteria corresponding to the identified colony, according to the supplement.
  • the identified colony to be identified corresponds to the brief biochemical information of the bacteria to further determine the species of the colony to be identified.
  • the second determining unit When the second determining unit finally determines the species of the colony to be identified, it may be identified according to the determined strain and the supplementary identification.
  • the colony corresponds to the brief biochemical information of the bacteria to generate the species information of the colony to be identified, and the strain information can be added to the colony characteristic database to provide an identification basis for the identification of subsequent colonies to be identified, thereby also improving the identification efficiency of the colony.
  • a large number of colony images may be stored in the colony feature library, and each colony image corresponds to unique species information.
  • the first obtaining module S1 acquires an image of the colony to be identified, and then the extracting module S2 extracts the colony characteristic information from the image of the colony to be identified; finally, the above determining module S3 determines the species information corresponding to the colony to be identified based on the extracted colony feature information and the colony image in the colony feature library.
  • the first obtaining module S1 obtains an image of the colony to be identified, which can be obtained by the colony image obtaining method provided above, and the extracting module S2 extracts the colony feature information from the image of the colony to be identified, and can obtain the colony feature extraction method provided above. Come to extract.
  • the determining module S3 determines the species information corresponding to the colony to be identified based on the extracted colony feature information and the colony image in the colony feature library, and can be implemented by the following process.
  • the colony image with the highest matching degree of the colony characteristic information of the colony to be identified is determined from the colony image in the colony characteristic library; the species information corresponding to the colony image with the highest matching degree is determined as the strain corresponding to the colony to be identified information.
  • the above species information includes colony characteristics corresponding to colony species and colony species.
  • the determining module S3 first needs to extract the colony features of all the colony images in the colony feature library through the above-mentioned extraction module S2, and then the colony feature information of the colony to be identified is The colony characteristics of each colony image are compared, wherein each feature in the colony feature information of the colony to be identified is compared with each of the colony features of each colony image, including the colony to be identified.
  • the determining module S3 determines the colony characteristics of the statistically most consistent feature items as the colony characteristics with the highest degree of matching with the colony characteristics of the colonies to be identified.
  • the determining module S3 determines the colony feature having the highest degree of matching with the colony feature of the colony to be identified, the determining module S3 selects the species corresponding to the colony image of the colony characteristic with the highest matching degree according to the correspondence relationship between the colony image and the strain information. The information is determined as the species information corresponding to the colony to be identified.
  • the identifier when identifying the species information of the colony to be identified, it is only necessary to obtain an image of the colony to be identified, and the identifier does not need to actually contact the colon to be identified, thereby avoiding the bacterial infection caused by contact with the colon to be identified.
  • the appraisers improve the safety of the appraisers; in the entire appraisal process, the appraisers do not need to master very professional bacteria and medical knowledge, only need to master the operation of related equipment and related software, and the professional requirements for the appraisers are very low.
  • the image of the colony to be identified can be quickly obtained, and the identification process can be quickly completed by the automated information processing equipment and software, so that the identification result can be quickly obtained, and the identification result is greatly improved.
  • the identification efficiency is high, and the identification result is highly accurate; in the present invention, the image of the colony to be identified can be obtained in various ways, and the entire identification process does not require the payment for the preservation, transportation and management of the identified colony, and the appraisal personnel
  • the cost to be paid is also low, and the cost of the bacteria identification device is very low. Thus greatly reducing the cost of identification.
  • the bacteria identification device includes a first acquisition module configured to or used to acquire an image of the colony to be identified; and an extraction module configured to or used to extract colony feature information from the image of the colony to be identified;
  • the determining module is configured or configured to determine the species information corresponding to the colony to be identified based on the extracted colony characteristic information and the pre-established colony feature library.
  • the bacteria identification method and device have low requirements on the bacteria and medical specialties of the appraisers; through the automated information processing process
  • the identification process can be completed quickly, and the identification result can be quickly obtained, the identification efficiency is greatly improved, and the identification result is highly accurate; the image of the colony to be identified can be obtained in various ways, and the bacterial identification device is lighter than the conventional identification instrument.
  • the low cost which greatly reduces the cost of identification and the requirements of the site, is conducive to the promotion of bacterial identification technology, and plays a greater role, so that the technology can benefit more people.

Landscapes

  • Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Organic Chemistry (AREA)
  • Wood Science & Technology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Zoology (AREA)
  • General Health & Medical Sciences (AREA)
  • Biotechnology (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Biochemistry (AREA)
  • General Engineering & Computer Science (AREA)
  • Microbiology (AREA)
  • Genetics & Genomics (AREA)
  • Physics & Mathematics (AREA)
  • Analytical Chemistry (AREA)
  • Proteomics, Peptides & Aminoacids (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Sustainable Development (AREA)
  • Medicinal Chemistry (AREA)
  • Toxicology (AREA)
  • Biophysics (AREA)
  • Immunology (AREA)
  • Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
  • Apparatus Associated With Microorganisms And Enzymes (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

本发明提供了一种细菌鉴定方法及装置。该方法包括：获取待鉴定菌落的图像；从所述待鉴定菌落的图像中提取菌落特征信息；根据提取的所述菌落特征信息和预先建立的菌落特征库，确定所述待鉴定菌落对应的菌种信息。

Description

细菌鉴定方法及装置 技术领域
本发明涉及图像处理技术及细菌鉴定技术领域，具体而言，涉及一种细菌鉴定方法及装置。
背景技术
目前，在医院、科研单位和学校，由于治疗或研究等目的，常常需要进行细菌鉴定，通过某种细菌鉴定方法来鉴定该细菌的种类，以满足治疗、研究或教学等要求。
当前，常用的细菌鉴定方法，主要通过生化的方法根据细菌自身的生理活动特点鉴定细菌，鉴定前，将细菌用培养基分纯，得到纯菌落，然后取菌落穿刺生化管，观察其颜色变化，以此判断具体菌落种类，或者将菌落制成悬液，根据专用鉴定卡和专用分析仪对悬液进行鉴定，确定菌落种类。
以上通过生化的方法鉴定菌落种类，需要菌落能够制成悬液或菌落在液体中能够充分分散开，对菌落纯度要求很高，对鉴定人员的鉴定技术要求很高，且在鉴定过程中，当鉴定人员接触到细菌时，存在一定安全风险，而且传统鉴定所需仪器设备往往价格贵、体积大，从而导致细菌鉴定复杂、成本高，使细菌鉴定不易开展推广，并存在安全隐患。
发明内容
有鉴于此，本发明的目的在于提供一种细菌鉴定方法及装置，实现通过非接触式的方式对菌落进行菌种鉴定，提高鉴定人员的安全性；该细菌鉴定方法及装置对鉴定人员的细菌及医疗方面的专业性要求很低；通过自动化的信息处理过程可以快速地完成鉴定过程，以及快速地得到鉴定结果，大大提高鉴定效率，且鉴定结果准确性很高；可以通过多种方式获取待鉴定菌落的图像，且细菌鉴定装置较传统鉴定仪器轻便、费用低，从而大大降低鉴定成本和对场地的要求，有利于细菌鉴定技术开展推广，发挥更大作用，使该项技术能惠及更多人。
第一方面，本发明提供了一种细菌鉴定方法，所述方法包括如下步骤：
获取待鉴定菌落的图像；
从所述待鉴定菌落的图像中提取菌落特征信息；
根据提取的所述菌落特征信息和预先建立的菌落特征库，确定所述待鉴定菌落对应的菌种信息。
结合第一方面，本发明实施例提供了上述第一方面的第一种可能的实现方式，其中，从所述待鉴定菌落的图像中提取菌落特征信息的所述步骤包括：
从所述待鉴定菌落的图像中提取所述待鉴定菌落的大小、颜色、形状、光泽度、立体特征及干湿程度；
根据所述待鉴定菌落的大小、颜色、形状、光泽度、立体特征和干湿程度生成所述待鉴定菌落的菌落特征信息。
结合第一方面，本发明实施例提供了上述第一方面的第二种可能的实现方式，其中，根据提取的所述菌落特征信息和预先建立的菌落特征库而确定所述待鉴定菌落对应的菌种信息的所述步骤包括：
根据预设的菌落特征信息与菌落信息集合标识的对应关系，从所述预先建立的菌落特征库中确定包括所述待鉴定菌落的菌落特征信息的菌落信息集合，其中，所述菌落特征库包括多个菌落信息集合，所述多个菌落信息集合分别包括各个菌落信息集合对应的菌落信息集合标识、和多种菌落的菌落特征；
从包括所述待鉴定菌落的菌落特征信息的菌落信息集合中，确定出与所述待鉴定菌落的菌落特征信息匹配度最高的菌落特征；
将所述匹配度最高的菌落特征对应的菌种信息，确定为所述待鉴定菌落对应的菌种信息。
结合第一方面，本发明实施例提供了上述第一方面的第三种可能的实现方式，其中，获取待鉴定菌落的图像的所述步骤包括：
通过终端自带的菌落图片采集器采集待鉴定菌落的图像，或者接收除所述终端外的设备传输的待鉴定菌落的图像，或者从本地调取存储的待鉴定菌落的图像。
结合第一方面，本发明实施例提供了上述第一方面的第四种可能的实现方式，其中，所述方法还包括：
获取各个种类菌落对应的菌种信息，所述菌种信息包括菌落种类和所述菌落种类对应的菌落特征信息；
根据所述各个种类菌落对应的菌种信息，确定所述各个种类菌落分别对应的菌落信息集合；
生成所述各个种类菌落的菌落特征信息与对应的菌落信息集合标识的对应关系，建立菌落特征库。
结合第一方面，本发明实施例提供了上述第一方面的第五种可能的实现方式，其中，从所述待鉴定菌落的图像中提取菌落特征信息的所述步骤包括：
从所述待鉴定菌落的图像中提取所述待鉴定菌落的大小、颜色、形状、光泽度及干湿程度；
根据所述待鉴定菌落的大小、颜色、形状、光泽度和干湿程度生成所述待鉴定菌落的菌落特征信息。
结合第一方面，本发明实施例提供了上述第一方面的第六种可能的实现方式，其中，根据提取的所述菌落特征信息和预先建立的菌落特征库而确定所述待鉴定菌落对应的菌种信息的所述步骤包括：
从所述预先建立的菌落特征库中，确定出与所述待鉴定菌落的菌落特征信息匹配度最高的菌落特征；
将所述匹配度最高的菌落特征对应的菌种信息，确定为所述待鉴定菌落对应的菌种信息。
结合第一方面，本发明实施例提供了上述第一方面的第七种可能的实现方式，其中，所述方法还包括：
获取各个种类菌落对应的菌种信息，所述菌种信息包括菌落种类和所述菌落种类对应的菌落特征；
根据所述各个种类菌落对应的菌种信息建立菌落特征库。
第二方面，本发明提供了一种细菌鉴定装置，所述装置包括：
第一获取模块，被配置成或用于获取待鉴定菌落的图像；
提取模块，被配置成或用于从所述待鉴定菌落的图像中提取菌落特征信息；
确定模块，被配置成或用于根据提取的所述菌落特征信息和预先建立的菌落特征库，确定所述待鉴定菌落对应的菌种信息。
结合第二方面，本发明实施例提供了上述第二方面的第一种可能的实现方式，其中，所述提取模块包括：
提取单元，被配置成或用于从所述待鉴定菌落的图像中提取所述待鉴定菌落的大小、颜色、形状、光泽度、立体特征及干湿程度；
生成单元，被配置成或用于根据所述待鉴定菌落的大小、颜色、形状、光泽度、立体特征和干湿程度生成所述待鉴定菌落的菌落特征信息。
结合第二方面，本发明实施例提供了上述第二方面的第二种可能的实现方式，其中，所述确定模块包括：
第一确定单元，被配置成或用于根据预设的菌落特征信息与菌落信息集合标识的对应关系，从所述预先建立的菌落特征库中确定包括所述待鉴定菌落的菌落特征信息的菌落信息集合，其中，所述菌落特征库包括多个菌落信 息集合，所述多个菌落信息集合分别包括各个菌落信息集合对应的菌落信息集合标识和多种菌落的菌落特征；
第二确定单元，被配置成或用于从包括所述待鉴定菌落的菌落特征信息的菌落信息集合中，确定出与所述待鉴定菌落的菌落特征信息匹配度最高的菌落特征；
第三确定单元，被配置成或用于将所述匹配度最高的菌落特征对应的菌种信息，确定为所述待鉴定菌落对应的菌种信息。
结合第二方面，本发明实施例提供了上述第二方面的第三种可能的实现方式，其中，所述第一获取模块包括：
采集单元，被配置成或用于通过终端自带的菌落图片采集器采集待鉴定菌落的图像；
接收单元，被配置成或用于接收除所述终端外的设备传输的待鉴定菌落的图像；
调取单元，被配置成或用于从本地调取存储的待鉴定菌落的图像。
结合第二方面，本发明实施例提供了上述第二方面的第四种可能的实现方式，其中，所述装置还包括：
第二获取模块，被配置成或用于获取各个种类菌落对应的菌种信息，所述菌种信息包括菌落种类和所述菌落种类对应的菌落特征信息；
集合确定模块，被配置成或用于根据所述各个种类菌落对应的菌种信息，确定所述各个种类菌落对应的菌落信息集合；
建立模块，被配置成或用于生成所述各个种类菌落的菌落特征信息与对应的菌落信息集合标识的对应关系，建立菌落特征库。
结合第二方面，本发明实施例提供了上述第二方面的第五种可能的实现方式，其中，所述提取模块包括：
提取单元，被配置成或用于从所述待鉴定菌落的图像中提取所述待鉴定菌落的大小、颜色、形状、光泽度及干湿程度；
生成单元，被配置成或用于根据所述待鉴定菌落的大小、颜色、形状、光泽度和干湿程度生成所述待鉴定菌落的菌落特征信息。
结合第二方面，本发明实施例提供了上述第二方面的第六种可能的实现方式，其中，所述确定模块包括：
第一确定单元，被配置成或用于从所述预先建立的菌落特征库中，确定出与所述待鉴定菌落的菌落特征信息匹配度最高的菌落特征；
第二确定单元，被配置成或用于将所述匹配度最高的菌落特征对应的菌种信息，确定为所述待鉴定菌落对应的菌种信息。
结合第二方面，本发明实施例提供了上述第二方面的第七种可能的实现方式，其中，所述装置还包括：
第二获取模块，被配置成或用于获取各个种类菌落对应的菌种信息，所述菌种信息包括菌落种类和所述菌落种类对应的菌落特征；
建立模块，被配置成或用于根据所述各个种类菌落对应的菌种信息建立菌落特征库。
在本发明提供的细菌鉴定方法包括：获取待鉴定菌落的图像；从所述待鉴定菌落的图像中提取菌落特征信息；根据提取的所述菌落特征信息和预先建立的菌落特征库，确定所述待鉴定菌落对应的菌种信息；细菌鉴定装置包括第一获取模块，被配置成或用于获取待鉴定菌落的图像；提取模块，被配置成或用于从所述待鉴定菌落的图像中提取菌落特征信息；确定模块，被配置成或用于根据提取的所述菌落特征信息和预先建立的菌落特征库，确定所述待鉴定菌落对应的菌种信息。
根据本发明提供的细菌鉴定方法及装置，能够带来至少以下有益效果：实现了通过非接触式的方式对菌落进行菌种鉴定，提高了鉴定人员的安全性；该细菌鉴定方法及装置对鉴定人员的细菌及医疗方面的专业性要求很低；通过自动化的信息处理过程可以快速地完成鉴定过程，以及快速地得到鉴定结果，大大提高了鉴定效率，且鉴定结果准确性很高；可以通过多种方式获取待鉴定菌落的图像，细菌鉴定装置费用很低，从而大大降低了鉴定成本。
为使本发明的上述目的、特征和优点能更明显易懂，下文特举较佳实施例，并配合所附附图，作详细说明如下。
附图说明
为了更清楚地说明本发明实施例的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，应当理解，以下附图仅示出了本发明的某些实施例，因此不应被看作是对范围的限定，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他相关的附图。
图1示出了本发明实施例1所提供的一种细菌鉴定方法的流程示意图；
图2示出了本发明实施例2所提供的一种细菌鉴定装置的结构示意图。
具体实施方式
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。通常在此处附图中描述和示出的本发明实施例的组件可以以各种不同的配置来布置和设计。因此，以下对在附图中提供的本发明的实施例的详细描述并非旨在限制要求保护的本发明的范围，而是仅仅表示本发明的选定实施例。基于本发明的实施例，本领域技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都属于本发明保护的范围。
下面将结合本发明实施例中附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。通常在此处附图中描述和示出的本发明实施例的组件可以以各种不同的配置来布置和设计。因此，以下对在附图中提供的本发明的实施例的详细描述并非旨在限制要求保护的本发明的范围，而是仅仅表示本发明的选定实施例。基于本发明的实施例，本领域技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都属于本发明保护的范围。
考虑到相关鉴定技术中，通过生化的方法鉴定菌落种类，需要菌落能够制成悬液或菌落在液体中能够充分分散开，对菌落纯度要求很高，对鉴定人员的鉴定技术要求很高，且在鉴定过程中，当鉴定人员接触到细菌时，存在一定安全风险，从而导致细菌鉴定复杂、成本高和存在安全隐患。基于此，本发明提供了一种细菌鉴定方法及装置，实现通过非接触式的方式对菌落进行菌种鉴定，提高鉴定人员的安全性；该细菌鉴定方法及装置对鉴定人员的细菌及医疗方面的专业性要求很低；通过自动化的信息处理过程可以快速地完成鉴定过程，以及快速地得到鉴定结果，大大提高鉴定效率，且鉴定结果准确性很高；可以通过多种方式获取待鉴定菌落的图像，细菌鉴定装置费用很低，从而大大降低鉴定成本。下面通过实施例进行描述。
实施例1
参见图1，本发明实施例提供了一种细菌鉴定方法。该方法包括以下S103-S105步骤。
在本发明实施例中，在通过S103步骤获取待鉴定菌落的图像之前，首先需要通过以下S101-S102步骤建立菌落特征库。
步骤S101：获取各个种类菌落对应的菌种信息，菌种信息包括菌落种类和菌落种类对应的菌落特征信息；
步骤S102：根据各个种类菌落对应的菌种信息，确定各个种类菌落分别对应的菌落信息集合，生成各个种类菌落的菌落特征信息与对应的菌落信息集合标识的对应关系，建立菌落特征库。
在上述步骤S101中，可依据生物学和医学上对菌落的分类来获取各个种类菌落对应的菌种信息。上述菌种信息还包括各个种类菌落的生存环境和活动信息。其中，菌种信息中的菌落特征信息包括菌落的大小、颜色、形状、光泽度及干湿程度和/或立体特征；菌落种类与菌落特征一一对应。
上述菌落特征库，包括多个菌落信息集合，该多个菌落信息集合分别包括各个菌落信息集合对应的菌落信息集合标识和多种菌落的菌落特征。
上述菌落特征信息中，菌落的大小、光泽度及干湿程度等菌落特征可以直接通过数值表征。
在上述步骤S102中，为了确定一菌落信息集合所关联的菌落，可以预先建立该菌落信息集合与菌落特征信息中至少一种可以通过数值表征的菌落特征的数值范围的对应关系；该对应关系由上述菌落信息集合标识与可以通过数值表征的菌落特征的数值范围的关联关系表示。
在确定一个种类菌落对应的菌落信息集合的过程中，先从获取到的该种类菌落的菌落特征信息中提取与菌落信息集合标识形成关联关系的菌落特征的数值，然后根据提取到的菌落特征的数值，确定该数值落入的菌落特征的数值范围；最后通过该数值落入的菌落特征的数值范围与菌落信息集合标识的关联关系，确定该种类菌落对应的菌落信息集合。从而重复以上过程，生成各个种类菌落的菌落特征信息与对应的菌落信息集合标识的对应关系，建立菌落特征库。
在确定出各个种类菌落对应的菌落特征后，从而可以建立起菌落种类与菌落特征信息的一一对应关系，即建立起各个种类菌落的菌种信息，将该建立起的各个种类菌落的菌种信息存入相应的数据库，将包含各个种类菌落的菌种信息的数据库作为菌落特征库。
在建立菌落特征库后，可通过以下S103-S105步骤鉴定待鉴定菌落的菌种。
步骤S103：获取待鉴定菌落的图像；
步骤S104：从待鉴定菌落的图像中提取菌落特征信息；
步骤S105：根据提取的菌落特征信息和预先建立的菌落特征库，确定待鉴定菌落对应的菌种信息。
在通过上述步骤S103获取待鉴定菌落的图像之前，需要先通过培养基对该待鉴定菌落进行分纯，分纯的目的是为了获取与相关菌种的标准菌株的菌落 一致的菌落，以便于鉴定该待鉴定菌落的菌落种类。在本发明实施例中，对分纯后的待鉴定菌落的纯度要求很低，适用大多数菌落的鉴定。
在对待鉴定菌落进行分纯后可以通过以下三种方式中任意一种方式获取待鉴定菌落的图像。
第一种方式：通过终端自带的菌落图片采集器采集待鉴定菌落的图像。
上述终端可以是手机或者平板电脑等移动终端，上述菌落图片采集器可以是设置在上述移动终端上的摄像头；上述菌落图片采集器还可以是CMOS(Complementary Metal Oxide Semiconductor，互补金属氧化物半导体)照相机。该移动终端或者CMOS照相机通过现场拍摄待鉴定菌落的图像，自动将该待鉴定菌落的图像传输给菌落鉴定设备。
第二种方式：接收除终端外的设备传输的待鉴定菌落的图像。
上述除终端外的设备可以是手机、平板电脑等移动终端，还可以是台式机等固定终端。该移动终端或固定终端通过有线、无线或传输接口将事先拍摄的待鉴定菌落图像传输给菌落鉴定设备。
第三种方式：从本地调取存储的待鉴定菌落的图像。
在对待鉴定菌落进行鉴定之前，可以事先将采集的待鉴定菌落的图像存储在本地存储器中，当需要对某种菌落进行鉴定时，可以从本地存储器中调取该待鉴定菌落的图像。
通过以上方法获取到待鉴定菌落的图像后，可以通过上述步骤S104从待鉴定菌落的图像中提取菌落特征信息，具体可通过以下S1041-S1042步骤来提取。
步骤S1041：从待鉴定菌落的图像中提取待鉴定菌落的大小、颜色、形状、光泽度及干湿程度和/或立体特征；
步骤S1042：根据待鉴定菌落的大小、颜色、形状、光泽度、立体特征和干湿程度生成待鉴定菌落的菌落特征信息。
在上述步骤S1041中，提取待鉴定菌落的大小，首先需要定位该待鉴定菌落的图像中待鉴定菌落的位置，然后根据该待鉴定菌落的位置确定待鉴定菌落在图像中所占的区域，并计算该区域的面积，通过计算出的面积确定待鉴定菌落的大小。
提取待鉴定菌落的颜色，首先确定待鉴定菌落在图像中所占的区域，然后统计出该区域内各个像素点的像素值，并将像素值转换为对应的数值，最后根据各个像素点对应的数值、颜色比对卡和各个像素分布的概率，确定出待鉴定菌落的颜色。其中，颜色比对卡包括各个颜色与数值的一一对应关系。
提取待鉴定菌落的形状，首先确定待鉴定菌落在图像中所占的区域，然后对该区域的边界线进行测量，根据测量结果和形状计算算法确定出该待鉴定菌落对应的形状。
提取待鉴定菌落的光泽度，首先确定待鉴定菌落在图像中所占的区域，然后计算该区域内图像的对比度和明暗程度，最后根据计算的对比度、明暗程度和图像光泽度判断标准，确定出待鉴定菌落的光泽度。
提取待鉴定菌落的立体特征，首先对待鉴定菌落在图像中的各特征区域进行定位，然后对采集的图像进行预处理,再对图像中的特征点进行识别,从而识别出图中物体的立体特征，最后提取出待鉴定菌落的立体特征。
提取待鉴定菌落的干湿程度，首先确定待鉴定菌落在图像中所占的区域，然后计算该区域内图像的反光度，根据计算的反光度和干湿程度对照表，确定出该待鉴定菌落的干湿程度；其中，干湿程度对照表包括反光对与干湿程度的一一对应关系。
在本发明实施例中，提取待鉴定菌落的大小、颜色、形状、光泽度及干湿程度等图像特征和/或立体特征，还可以通过现有图像处理技术中，对图像的大小、颜色、形状、光泽度及干湿程度和/或立体特征等图像特征提取技术来实现。
通过以上方法提取待鉴定菌落的菌落特征信息后，可通过上述步骤S105，根据提取的菌落特征信息和预先建立的菌落特征库，确定待鉴定菌落对应的菌种信息，具体通过以下S1051-S1052步骤来确定。
步骤S1051：根据预设的菌落特征信息与菌落信息集合标识的对应关系，从预先建立的菌落特征库中确定包括待鉴定菌落的菌落特征信息的菌落信息集合，从包括待鉴定菌落的菌落特征信息的菌落信息集合中，确定出与待鉴定菌落的菌落特征信息匹配度最高的菌落特征；
步骤S1052：将匹配度最高的菌落特征对应的菌种信息，确定为待鉴定菌落对应的菌种信息。
在上述步骤S1051中，先从获取到的待鉴定菌落的菌落特征信息中提取与菌落信息集合标识形成关联关系的菌落特征的数值，然后根据提取到的菌落特征的数值，确定该数值落入的菌落特征的数值范围；最后通过该数值落入的菌落特征的数值范围与菌落信息集合标识的关联关系，确定待鉴定菌落对应的菌落信息集合。
在确定与待鉴定菌落的菌落特征信息匹配度时，首先需要将待鉴定菌落的菌落特征信息与该菌落信息集合或特征库中每个菌落特征进行比对，其中，将待鉴定菌落的菌落特征信息中的每一项特征与菌落信息集合或特征库中每个菌 落特征中的每一项特征进行比对，包括比对待鉴定菌落的大小与每个菌落特征中的菌落大小；比对待鉴定菌落的颜色与每个菌落特征中的菌落颜色；比对待鉴定菌落的形状与每个菌落特征中的菌落形状；比对待鉴定菌落的光泽度与每个菌落特征中的菌落光泽度；比对待鉴定菌落的立体特征与每个菌落特征中的菌落立体特征；以及比对待鉴定菌落的干湿程度与每个菌落特征中的菌落的干湿程度。然后，根据菌落特征库中每个菌落特征中的各项特征的比对结果统计该菌落特征的相符特征项的数量。其中，比对及统计得到的数据示意性地如下表1所示。
表1
Figure PCTCN2016102094-appb-000001
最后，将统计出的相符特征项最多的菌落特征，确定为与待鉴定菌落的菌落特征的匹配度最高的菌落特征。
当确定出与待鉴定菌落的菌落特征匹配度最高的菌落特征后，可以通过上述步骤S1052，将匹配度最高的菌落特征对应的菌种信息，确定为待鉴定菌落对应的菌种信息。
通过上述确定待鉴定菌落对应的菌种信息的过程可以看出，先从预先建立的菌落特征库中确定包括待鉴定菌落的菌落特征信息的菌落信息集合，然后从包括待鉴定菌落的菌落特征信息的菌落信息集合中，确定出与待鉴定菌落的菌落特征信息匹配度最高的菌落特征，只需在包括待鉴定菌落的菌落特征信息的菌落信息集合对待鉴定菌落的菌落特征信息进行匹配，无需将待鉴定菌落的菌落特征信息与菌落特征库中所有的菌落特征进行匹配操作，可以缩短检定菌落的时间，进一步提高菌落的鉴定效率。
在本发明实施例中，在确定与待鉴定菌落的菌落特征信息匹配度时，若菌落特征库中所有菌落特征与待鉴定菌落的菌落特征信息的匹配度均低于预设的匹配度时，此时无法根据菌落特征库中的菌落特征准确地确定的出待鉴定菌落的菌种，还需要结合相应的鉴定技术补充鉴定待鉴定菌落对应细菌的简要生化信息，根据补充鉴定的待鉴定菌落对应细菌的简要生化信息来进一步确定待鉴定菌落的菌种，当最终确定出该待鉴定菌落的菌种后，可以根据确定的菌种、补充鉴定的待鉴定菌落对应细菌的简要生化信息生成该待鉴定菌落的菌种信息，并可以将该菌种信息添加到菌落特征库，为后续待鉴定菌落的鉴定提供鉴定依据，从而也可以提高菌落的鉴定效率。
在本发明实施例中，上述菌落特征库中还可以存入大量菌落图像，每个菌落图像对应唯一的菌种信息。当需要确定待鉴定菌落的菌种信息时，首先获取待鉴定菌落的图像，然后从待鉴定菌落的图像中提取菌落特征信息；最后根据提取的菌落特征信息和菌落特征库中的菌落图像，确定待鉴定菌落对应的菌种信息。
上述根据提取的菌落特征信息和菌落特征库中菌落图像，确定待鉴定菌落对应的菌种信息，可以通过以下过程来实现。
从菌落特征库中的菌落图像中，确定出与待鉴定菌落的菌落特征信息匹配度最高的菌落图像；将匹配度最高的菌落图像对应的菌种信息，确定为所述待鉴定菌落对应的菌种信息。
上述菌种信息包括菌落种类和菌落种类对应的菌落特征。在确定与待鉴定菌落的菌落特征信息匹配度最高的菌落图像时，首先需要提取菌落特征库中所有菌落图像的菌落特征，然后将待鉴定菌落的菌落特征信息与每个菌落图像的菌落特征进行比对，其中，将待鉴定菌落的菌落特征信息中的每一项特征与每个菌落图像的菌落特征中的每一项特征进行比对，包括比对待鉴定菌落的大小与每个菌落图像的菌落特征中的菌落大小；比对待鉴定菌落的颜色与每个菌落图像的菌落特征中的菌落颜色；比对待鉴定菌落的形状与每个菌落图像的菌落 特征中的菌落形状；比对待鉴定菌落的光泽度与每个菌落图像的菌落特征中的菌落光泽度；比对待鉴定菌落的立体特征与每个菌落特征中的菌落立体特征；以及比对待鉴定菌落的干湿程度与每个菌落图像的菌落特征中的菌落的干湿程度。然后，根据每个菌落图像的菌落特征中的各项特征的比对结果统计该菌落特征的相符特征项的数量。其中，比对及统计得到的数据示意性地如上表1所示。
最后，将统计出的相符特征项最多的菌落特征，确定为与待鉴定菌落的菌落特征的匹配度最高的菌落特征。
当确定出与待鉴定菌落的菌落特征匹配度最高的菌落特征后，根据菌落图像与菌种信息的对应关系，将包含匹配度最高的菌落特征的菌落图像对应的菌种信息，确定为待鉴定菌落对应的菌种信息。
在本发明实施例中，在鉴定待鉴定菌落的菌种信息时，只需获取待鉴定菌落的图像，鉴定人员不需要实际接触待鉴定菌落，避免了与待鉴定菌落接触而引发的细菌感染，从而提高了鉴定人员的安全性；在整个鉴定过程中，鉴定人员不需要掌握非常专业的细菌和医疗知识，只需要掌握相关设备和相关软件的操作即可，对鉴定人员的专业性要求很低；通过本发明提供的方法鉴定菌落的菌种信息，可以快速地获取到待鉴定菌落的图像，并通过自动化的信息处理设备和软件快速地完成鉴定过程，因此可以快速地得到鉴定结果，大大提高了鉴定效率，且鉴定结果准确性很高；本发明中，可以通过多种方式获取待鉴定菌落的图像，整个鉴定过程不需要对待鉴定菌落进行保藏、运输和管理等支付的费用，鉴定人员所需支付的费用也很低，细菌鉴定装置的成本很低，从而大大降低了鉴定成本。
在本发明实施例中，菌落鉴定方法包括获取待鉴定菌落的图像；从待鉴定菌落的图像中提取菌落特征信息；根据提取的菌落特征信息和预先建立的菌落特征库，确定待鉴定菌落对应的菌种信息。实现了通过非接触式的方式对菌落进行菌种鉴定，提高了鉴定人员的安全性；该细菌鉴定方法及装置对鉴定人员的细菌及医疗方面的专业性要求很低；通过自动化的信息处理过程可以快速地完成鉴定过程，以及快速地得到鉴定结果，大大提高了鉴定效率，且鉴定结果准确性很高；可以通过多种方式获取待鉴定菌落的图像，细菌鉴定装置费用很低，从而大大降低了鉴定成本。
实施例2
参见图2，本发明实施例提供了一种细菌鉴定装置，该装置包括：
第一获取模块S1，被配置成或用于获取待鉴定菌落的图像；
提取模块S2，被配置成或用于从待鉴定菌落的图像中提取菌落特征信息；
确定模块S3，被配置成或用于根据提取的菌落特征信息和预先建立的菌落特征库，确定待鉴定菌落对应的菌种信息。
在本发明实施例中，通过上述第一获取模块S1获取待鉴定菌落的图像之前，首先需要通过以下第二获取模块和建立模块和/或集合确定模块建立菌落特征库。
上述装置还包括第二获取模块、建立模块和/或集合确定模块；
第二获取模块，被配置成或用于获取各个种类菌落对应的菌种信息，菌种信息包括菌落种类和菌落种类对应的菌落特征信息；
集合确定模块，被配置成或用于根据各个种类菌落对应的菌种信息，确定各个种类菌落对应的菌落信息集合；
建立模块，被配置成或用于生成或根据各个种类菌落的菌落或菌种特征信息与对应的菌落信息集合标识的对应关系，建立菌落特征库。
上述获取模块，可依据生物学和医学上对菌落的分类来获取各个种类菌落对应的菌种信息。上述菌种信息还包括各个种类菌落的生存环境和活动信息。其中，菌种信息中的菌落特征包括菌落的大小、颜色、形状、光泽度及干湿程度和/或立体特征；菌落种类与菌落特征一一对应。
在上述第二获取模块确定出各个种类菌落对应的菌落特征后，上述建立模块，可以根据第二获取模块确定出的各个种类菌落对应的菌落特征，建立起菌落种类与菌落特征的一一对应关系，即建立起各个种类菌落的菌种信息，将该建立起的各个种类菌落的菌种信息存入相应的数据库，将包含各个种类菌落的菌种信息的数据库作为菌落特征库。
当上述建立模块建立起菌落特征库后，当需要鉴定待鉴定菌落的菌种信息时，需要先通过培养基对该待鉴定菌落进行分纯，分纯的目的是为了与相关菌种的标准菌株的菌落一致的菌落，以便于鉴定该待鉴定菌落的菌落种类。在本发明实施例中，对分纯后的待鉴定菌落的纯度要求很低，适用大多数菌落的鉴定。
当对待鉴定菌落进行分纯后，上述第一获取模块S1会通过以下采集单元、接收单元或者调取单元获取该待鉴定菌落的图像。
上述第一获取模块S1包括采集单元、接收单元或者调取单元；
采集单元，被配置成或用于通过终端自带的菌落图片采集器采集待鉴定菌落的图像；
接收单元，被配置成或用于接收除终端外的设备传输的待鉴定菌落的图像，
调取单元，被配置成或用于从本地调取存储的待鉴定菌落的图像。
上述采集单元可以是嵌入有摄像头的手机或者平板电脑等移动终端，还可以是CMOS照相机。该采集单元通过现场拍摄待鉴定菌落的图像，自动将该待鉴定菌落的图像传输给菌落鉴定设备。
上述除终端外的设备可以是手机、平板电脑等移动终端，还可以是台式机等固定终端。该移动终端或固定终端通过有线、无线或传输接口将事先拍摄的待鉴定菌落图像传输给上述接收单元。
在对待鉴定菌落进行鉴定之前，可以事先将采集的待鉴定菌落的图像存储在本地存储器中，当需要对某种菌落进行鉴定时，上述调取单元可以从本地存储器中调取该待鉴定菌落的图像。
上述第一获取模块S1获取到待鉴定菌落的图像后，可以通过上述提取模块S2从待鉴定菌落的图像中提取菌落特征信息，具体可以通过以下提取单元和生成单元来提取。
上述提取模块S2包括提取单元和生成单元；
提取单元，被配置成或用于从待鉴定菌落的图像中提取待鉴定菌落的大小、颜色、形状、光泽度及干湿程度和/或立体特征；
生成单元，被配置成或用于根据待鉴定菌落的大小、颜色、形状、光泽度、干湿程度和/或立体特征生成待鉴定菌落的菌落特征信息。
上述提取单元提取待鉴定菌落的大小，首先需要定位该待鉴定菌落的图像中待鉴定菌落的位置，然后根据该待鉴定菌落的位置确定待鉴定菌落在图像中所占的区域，并计算该区域的面积，通过计算出的面积确定待鉴定菌落的大小。
上述提取单元提取待鉴定菌落的颜色，首先确定待鉴定菌落在图像中所占的区域，然后统计出该区域内各个像素点的像素值，并将像素值转换为对应的数值，最后根据各个像素点对应的数值、颜色比对卡和各个像素分布的概率，确定出待鉴定菌落的颜色。其中，颜色比对卡包括各个颜色与数值的一一对应关系。
上述提取单元提取待鉴定菌落的形状，首先确定待鉴定菌落在图像中所占的区域，然后对该区域的边界线进行测量，根据测量结果和形状计算算法确定出该待鉴定菌落对应的形状。
上述提取单元提取待鉴定菌落的光泽度，首先确定待鉴定菌落在图像中所占的区域，然后计算该区域内图像的对比度和明暗程度，最后根据计算的对比度、明暗程度和图像光泽度判断标准，确定出待鉴定菌落的光泽度。
提取待鉴定菌落的立体特征，首先对待鉴定菌落在图像中的各特征区域进行定位，然后对采集的图像进行预处理,再对图像中的特征点进行识别,从而识别出图中物体的立体特征，最后提取出待鉴定菌落的立体特征。
上述提取单元提取待鉴定菌落的干湿程度，首先确定待鉴定菌落在图像中所占的区域，然后计算该区域内图像的反光度，根据计算的反光度和干湿程度对照表，确定出该待鉴定菌落的干湿程度；其中，干湿程度对照表包括反光对与干湿程度的一一对应关系。
在本发明实施例中，上述提取单元提取待鉴定菌落的大小、颜色、形状、光泽度及干湿程度和/或立体特征等图像特征，还可以通过现有图像处理技术中，对图像的大小、颜色、形状、光泽度及干湿程度和/或立体特征等图像特征提取技术来实现。
当上述提取单元提取出待鉴定菌落的大小、颜色、形状、光泽度、干湿程度和/或立体特征后，上述生成模块将待鉴定菌落的大小、颜色、形状、光泽度、立体特征和干湿程度组成待鉴定菌落的菌落特征信息，并根据待鉴定菌落的菌落特征确定出该待鉴定菌落的菌种，最后将该待鉴定菌落的菌落特征和菌种作为待鉴定菌落的菌落特征信息。
当上述提取模块S2提取出待鉴定菌落的菌落特征信息后，可通过上述确定模块S3确定出待鉴定菌落对应的菌种信息。其中，上述确定模块S3可通过以下第一确定单元、第三确定单元和/或第二确定单元来确定。
上述确定模块包括第一确定单元、第三确定单元和/或第二确定单元；
第一确定单元，被配置成或用于根据预设的菌落特征信息与菌落信息集合标识的对应关系，从预先建立的菌落特征库中确定包括待鉴定菌落的菌落特征信息的菌落信息集合，其中，菌落特征库包括多个菌落信息集合，多个菌落信息集合分别包括各个菌落信息集合对应的菌落信息集合标识和多种菌落的菌落特征；
第二确定单元，被配置成或用于从包括待鉴定菌落的菌落特征信息的菌落信息集合中，确定出与待鉴定菌落的菌落特征信息匹配度最高的菌落特征；
第三确定单元，被配置成或用于将匹配度最高的菌落特征对应的菌种信息，确定为待鉴定菌落对应的菌种信息。
上述第一确定单元在根据预设的菌落特征信息与菌落信息集合标识的对应关系，从预先建立的菌落特征库中确定包括待鉴定菌落的菌落特征信息的菌落信息集合时，先从获取到的待鉴定菌落的菌落特征信息中提取与菌落信息集合标识形成关联关系的菌落特征的数值，然后根据提取到的菌落特征的数值，确 定该数值落入的菌落特征的数值范围；最后通过该数值落入的菌落特征的数值范围与菌落信息集合标识的关联关系，确定待鉴定菌落对应的菌落信息集合。
上述第二确定单元在确定与待鉴定菌落的菌落特征信息匹配度时，首先需要将待鉴定菌落的菌落特征信息与该菌落信息集合或特征库中每个菌落特征进行比对，其中，将待鉴定菌落的菌落特征信息中的每一项特征与菌落信息集合或特征库中每个菌落特征中的每一项特征进行比对，包括比对待鉴定菌落的大小与每个菌落特征中的菌落大小；比对待鉴定菌落的颜色与每个菌落特征中的菌落颜色；比对待鉴定菌落的形状与每个菌落特征中的菌落形状；比对待鉴定菌落的光泽度与每个菌落特征中的菌落光泽度；比对待鉴定菌落的立体特征与每个菌落特征中的菌落立体特征；以及比对待鉴定菌落的干湿程度与每个菌落特征中的菌落的干湿程度。然后，第一确定单元，根据菌落特征库中每个菌落特征中的各项特征的比对结果统计该菌落特征的相符特征项的数量。其中，比对及统计得到的数据示意性地如下表1所示。
表1
Figure PCTCN2016102094-appb-000002
最后，第一确定单元，将统计出的相符特征项最多的菌落特征，确定为与待鉴定菌落的菌落特征的匹配度最高的菌落特征。
当第一确定单元确定出与待鉴定菌落的菌落特征匹配度最高的菌落特征后，可以通过上述第二确定单元，将匹配度最高的菌落特征对应的菌种信息，确定为待鉴定菌落对应的菌种信息。
通过对上述第一确定单元、第二确定单元和第三确定单元的描述可以看出，先从预先建立的菌落特征库中确定包括待鉴定菌落的菌落特征信息的菌落信息集合，然后从包括待鉴定菌落的菌落特征信息的菌落信息集合中，确定出与待鉴定菌落的菌落特征信息匹配度最高的菌落特征，只需在包括待鉴定菌落的菌落特征信息的菌落信息集合对待鉴定菌落的菌落特征信息进行匹配，无需将待鉴定菌落的菌落特征信息与菌落特征库中所有的菌落特征进行匹配操作，可以缩短检定菌落的时间，进一步提高菌落的鉴定效率。
在本发明实施例中，第一确定单元在确定与待鉴定菌落的菌落特征信息匹配度时，若菌落特征库中所有菌落特征与待鉴定菌落的菌落特征的匹配度均低于预设的匹配度时，此时第二确定单元无法根据菌落特征库中的菌落特征准确地确定出待鉴定菌落的菌种，还需要结合相应的鉴定技术补充鉴定待鉴定菌落对应细菌的简要生化信息，根据补充鉴定的待鉴定菌落对应细菌的简要生化信息来进一步确定待鉴定菌落的菌种，当第二确定单元最终确定出该待鉴定菌落的菌种后，可以根据确定的菌种、补充鉴定的待鉴定菌落对应细菌的简要生化信息生成该待鉴定菌落的菌种信息，并可以将该菌种信息添加到菌落特征库，为后续待鉴定菌落的鉴定提供鉴定依据，从而也可以提高菌落的鉴定效率。
在本发明实施例中，上述菌落特征库中还可以存入大量菌落图像，每个菌落图像对应唯一的菌种信息。当需要确定待鉴定菌落的菌种信息时，首先，上述第一获取模块S1获取待鉴定菌落的图像，然后，上述提取模块S2从待鉴定菌落的图像中提取菌落特征信息；最后，上述确定模块S3根据提取的菌落特征信息和菌落特征库中菌落图像，确定待鉴定菌落对应的菌种信息。其中，第一获取模块S1获取待鉴定菌落的图像，可以通过上述提供的菌落图像获取方法来获取，提取模块S2从待鉴定菌落的图像中提取菌落特征信息，可以通过上述提供的菌落特征提取方法来提取。
上述确定模块S3根据提取的菌落特征信息和菌落特征库中的菌落图像，确定待鉴定菌落对应的菌种信息，可以通过以下过程来实现。
从菌落特征库中菌落图像中，确定出与待鉴定菌落的菌落特征信息匹配度最高的菌落图像；将匹配度最高的菌落图像对应的菌种信息，确定为所述待鉴定菌落对应的菌种信息。
上述菌种信息包括菌落种类和菌落种类对应的菌落特征。确定模块S3在确定与待鉴定菌落的菌落特征信息匹配度最高的菌落图像时，首先需要通过上述提取模块S2提取菌落特征库中所有菌落图像的菌落特征，然后将待鉴定菌落的菌落特征信息与每个菌落图像的菌落特征进行比对，其中，将待鉴定菌落的菌落特征信息中的每一项特征与每个菌落图像的菌落特征中的每一项特征进行比对，包括比对待鉴定菌落的大小与每个菌落图像的菌落特征中的菌落大小；比对待鉴定菌落的颜色与每个菌落图像的菌落特征中的菌落颜色；比对待鉴定菌落的形状与每个菌落图像的菌落特征中的菌落形状；比对待鉴定菌落的光泽度与每个菌落图像的菌落特征中的菌落光泽度；比对待鉴定菌落的立体特征与每个菌落特征中的菌落立体特征；以及比对待鉴定菌落的干湿程度与每个菌落图像的菌落特征中的菌落的干湿程度。然后，根据每个菌落图像的菌落特征中的各项特征的比对结果统计该菌落特征的相符特征项的数量。其中，比对及统计得到的数据示意性地如上表1所示。
最后，确定模块S3将统计出的相符特征项最多的菌落特征，确定为与待鉴定菌落的菌落特征的匹配度最高的菌落特征。
当确定模块S3确定出与待鉴定菌落的菌落特征匹配度最高的菌落特征后，确定模块S3根据菌落图像与菌种信息的对应关系，将包含匹配度最高的菌落特征的菌落图像对应的菌种信息，确定为待鉴定菌落对应的菌种信息。
在本发明实施例中，在鉴定待鉴定菌落的菌种信息时，只需获取待鉴定菌落的图像，鉴定人员不需要实际接触待鉴定菌落，避免了与待鉴定菌落接触而引发的细菌感染，从而提高了鉴定人员的安全性；在整个鉴定过程中，鉴定人员不需要掌握非常专业的细菌和医疗知识，只需要掌握相关设备和相关软件的操作即可，对鉴定人员的专业性要求很低；通过本发明提供的方法鉴定菌落的菌种信息，可以快速地获取到待鉴定菌落的图像，并通过自动化的信息处理设备和软件快速地完成鉴定过程，因此可以快速地得到鉴定结果，大大提高了鉴定效率，且鉴定结果准确性很高；本发明中，可以通过多种方式获取待鉴定菌落的图像，整个鉴定过程不需要对待鉴定菌落进行保藏、运输和管理等支付的费用，鉴定人员所需支付的费用也很低，细菌鉴定装置的成本很低，从而大大降低了鉴定成本。
在本发明实施例中，细菌鉴定装置包括第一获取模块，被配置成或用于获取待鉴定菌落的图像；提取模块，被配置成或用于从待鉴定菌落的图像中提取菌落特征信息；确定模块，被配置成或用于根据提取的菌落特征信息和预先建立的菌落特征库，确定待鉴定菌落对应的菌种信息。实现了通过非接触式的方式对菌落进行菌种鉴定，提高了鉴定人员的安全性；该细菌鉴定方法及装置对鉴定人员的细菌及医疗方面的专业性要求很低；通过自动化的信息处理过程可以快速地完成鉴定过程，以及快速地得到鉴定结果，大大提高了鉴定效率，且鉴定结果准确性很高；可以通过多种方式获取待鉴定菌落的图像，且细菌鉴定装置较传统鉴定仪器轻便、费用低，从而大大降低了鉴定成本和对场地的要求，有利于细菌鉴定技术开展推广，发挥更大作用，使该项技术能惠及更多人。
以上所述，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应以所述权利要求的保护范围为准。

Claims (16)

  1. 一种细菌鉴定方法，其特征在于，所述方法包括如下步骤：
    获取待鉴定菌落的图像；
    从所述待鉴定菌落的图像中提取菌落特征信息；
    根据提取的所述菌落特征信息和预先建立的菌落特征库，确定所述待鉴定菌落对应的菌种信息。
  2. 根据权利要求1所述的方法，其特征在于，从所述待鉴定菌落的图像中提取菌落特征信息的所述步骤包括：
    从所述待鉴定菌落的图像中提取所述待鉴定菌落的大小、颜色、形状、光泽度、立体特征及干湿程度；
    根据所述待鉴定菌落的大小、颜色、形状、光泽度、立体特征和干湿程度生成所述待鉴定菌落的菌落特征信息。
  3. 根据权利要求1所述的方法，其特征在于，根据提取的所述菌落特征信息和预先建立的菌落特征库而确定所述待鉴定菌落对应的菌种信息的所述步骤包括：
    根据预设的菌落特征信息与菌落信息集合标识的对应关系，从所述预先建立的菌落特征库中确定包括所述待鉴定菌落的菌落特征信息的菌落信息集合，其中，所述菌落特征库包括多个菌落信息集合，所述多个菌落信息集合分别包括各个菌落信息集合对应的菌落信息集合标识、和多种菌落的菌落特征；
    从包括所述待鉴定菌落的菌落特征信息的菌落信息集合中，确定出与所述待鉴定菌落的菌落特征信息匹配度最高的菌落特征；
    将所述匹配度最高的菌落特征对应的菌种信息，确定为所述待鉴定菌落对应的菌种信息。
  4. 根据权利要求1所述的方法，其特征在于，获取待鉴定菌落的图像的所述步骤包括：
    通过终端自带的菌落图片采集器采集待鉴定菌落的图像，或者接收除所述终端外的设备传输的待鉴定菌落的图像，或者从本地调取存储的待鉴定菌落的图像。
  5. 根据权利要求3所述的方法，其特征在于，所述方法还包括：
    获取各个种类菌落对应的菌种信息，所述菌种信息包括菌落种类和所述菌落种类对应的菌落特征信息；
    根据所述各个种类菌落对应的菌种信息，确定所述各个种类菌落分别对应的菌落信息集合；
    生成所述各个种类菌落的菌落特征信息与对应的菌落信息集合标识的对应关系，建立菌落特征库。
  6. 根据权利要求1所述的方法，其特征在于，从所述待鉴定菌落的图像中提取菌落特征信息的所述步骤包括：
    从所述待鉴定菌落的图像中提取所述待鉴定菌落的大小、颜色、形状、光泽度及干湿程度；
    根据所述待鉴定菌落的大小、颜色、形状、光泽度和干湿程度生成所述待鉴定菌落的菌落特征信息。
  7. 根据权利要求1所述的方法，其特征在于，根据提取的所述菌落特征信息和预先建立的菌落特征库而确定所述待鉴定菌落对应的菌种信息的所述步骤包括：
    从所述预先建立的菌落特征库中，确定出与所述待鉴定菌落的菌落特征信息匹配度最高的菌落特征；
    将所述匹配度最高的菌落特征对应的菌种信息，确定为所述待鉴定菌落对应的菌种信息。
  8. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    获取各个种类菌落对应的菌种信息，所述菌种信息包括菌落种类和所述菌落种类对应的菌落特征；
    根据所述各个种类菌落对应的菌种信息建立菌落特征库。
  9. 一种细菌鉴定装置，其特征在于，所述装置包括：
    第一获取模块，被配置成获取待鉴定菌落的图像；
    提取模块，被配置成从所述待鉴定菌落的图像中提取菌落特征信息；
    确定模块，被配置成根据提取的所述菌落特征信息和预先建立的菌落特征库，确定所述待鉴定菌落对应的菌种信息。
  10. 根据权利要求9所述的装置，其特征在于，所述提取模块包括：
    提取单元，被配置成从所述待鉴定菌落的图像中提取所述待鉴定菌落的大小、颜色、形状、光泽度、立体特征及干湿程度；
    生成单元，被配置成根据所述待鉴定菌落的大小、颜色、形状、光泽度、立体特征和干湿程度生成所述待鉴定菌落的菌落特征信息。
  11. 根据权利要求9所述的装置，其特征在于，所述确定模块包括：
    第一确定单元，被配置成根据预设的菌落特征信息与菌落信息集合标识的对应关系，从所述预先建立的菌落特征库中确定包括所述待鉴定菌落的菌落特征信息的菌落信息集合，其中，所述菌落特征库包括多个菌落信息集合，所述多个菌落信息集合分别包括各个菌落信息集合对应的菌落信息集合标识和多种菌落的菌落特征；
    第二确定单元，被配置成从包括所述待鉴定菌落的菌落特征信息的菌落信息集合中，确定出与所述待鉴定菌落的菌落特征信息匹配度最高的菌落特征；
    第三确定单元，被配置成将所述匹配度最高的菌落特征对应的菌种信息，确定为所述待鉴定菌落对应的菌种信息。
  12. 根据权利要求9所述的装置，其特征在于，所述第一获取模块包括：
    采集单元，被配置成通过终端自带的菌落图片采集器采集待鉴定菌落的图像；
    接收单元，被配置成接收除所述终端外的设备传输的待鉴定菌落的图像；
    调取单元，被配置成从本地调取存储的待鉴定菌落的图像。
  13. 根据权利要求11所述的装置，其特征在于，所述装置还包括：
    第二获取模块，被配置成获取各个种类菌落对应的菌种信息，所述菌种信息包括菌落种类和所述菌落种类对应的菌落特征信息；
    集合确定模块，被配置成根据所述各个种类菌落对应的菌种信息，确定所述各个种类菌落对应的菌落信息集合；
    建立模块，被配置成生成所述各个种类菌落的菌落特征信息与对应的菌落信息集合标识的对应关系，建立菌落特征库。
  14. 根据权利要求9所述的装置，其特征在于，所述提取模块包括：
    提取单元，被配置成从所述待鉴定菌落的图像中提取所述待鉴定菌落的大小、颜色、形状、光泽度及干湿程度；
    生成单元，被配置成根据所述待鉴定菌落的大小、颜色、形状、光泽度和干湿程度生成所述待鉴定菌落的菌落特征信息。
  15. 根据权利要求9所述的装置，其特征在于，所述确定模块包括：
    第一确定单元，被配置成从所述预先建立的菌落特征库中，确定出与所述待鉴定菌落的菌落特征信息匹配度最高的菌落特征；
    第二确定单元，被配置成将所述匹配度最高的菌落特征对应的菌种信息，确定为所述待鉴定菌落对应的菌种信息。
  16. 根据权利要求9所述的装置，其特征在于，所述装置还包括：
    第二获取模块，被配置成获取各个种类菌落对应的菌种信息，所述菌种信息包括菌落种类和所述菌落种类对应的菌落特征；
    建立模块，被配置成根据所述各个种类菌落对应的菌种信息建立菌落特征库。
PCT/CN2016/102094 2016-03-30 2016-10-14 细菌鉴定方法及装置 WO2017166778A1 (zh)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
CN201610188737.X 2016-03-30
CN201610188737.XA CN105671122A (zh) 2016-03-30 2016-03-30 细菌鉴定方法及装置
CN201610658843.XA CN106295572A (zh) 2016-03-30 2016-08-12 细菌鉴定方法及装置
CN201610658843.X 2016-08-12

Publications (1)

Publication Number Publication Date
WO2017166778A1 true WO2017166778A1 (zh) 2017-10-05

Family

ID=56225544

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/102094 WO2017166778A1 (zh) 2016-03-30 2016-10-14 细菌鉴定方法及装置

Country Status (2)

Country Link
CN (2) CN105671122A (zh)
WO (1) WO2017166778A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105671122A (zh) * 2016-03-30 2016-06-15 李辰 细菌鉴定方法及装置
CN106951843A (zh) * 2017-03-09 2017-07-14 深圳创维－Rgb电子有限公司 尘螨检测方法及装置
CN106872538A (zh) * 2017-03-28 2017-06-20 海南大学 一种基于智能手机的高通量电化学分析系统

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105115970A (zh) * 2015-06-30 2015-12-02 厦门质谱仪器仪表有限公司 一种表型学鉴定法与质谱法综合的微生物鉴定系统和方法
CN105671122A (zh) * 2016-03-30 2016-06-15 李辰 细菌鉴定方法及装置

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2004086941A2 (en) * 2003-03-27 2004-10-14 Bartron Medical Imaging, Llc System and method for rapidly identifying pathogens, bacteria and abnormal cells
US7616320B2 (en) * 2006-03-15 2009-11-10 Bahram Javidi Method and apparatus for recognition of microorganisms using holographic microscopy
CN102024259B (zh) * 2010-12-24 2012-06-20 刘安安 一种菌落自动检测方法
CN105593359A (zh) * 2013-09-24 2016-05-18 富士通株式会社 菌落检查程序、菌落检查装置以及菌落检查方法
CN105420107A (zh) * 2015-11-11 2016-03-23 上海大学 一种基于菌落形态特征的菌落自动筛选方法

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105115970A (zh) * 2015-06-30 2015-12-02 厦门质谱仪器仪表有限公司 一种表型学鉴定法与质谱法综合的微生物鉴定系统和方法
CN105671122A (zh) * 2016-03-30 2016-06-15 李辰 细菌鉴定方法及装置

Also Published As

Publication number Publication date
CN105671122A (zh) 2016-06-15
CN106295572A (zh) 2017-01-04

Similar Documents

Publication Publication Date Title
DK2973397T3 (en) Tissue-object-based machine learning system for automated assessment of digital whole-slide glass
Thiyaneswaran et al. Early detection of melanoma images using gray level co‐occurrence matrix features and machine learning techniques for effective clinical diagnosis
US9002083B2 (en) System, method, and software for optical device recognition association
WO2017166778A1 (zh) 细菌鉴定方法及装置
CN105139390A (zh) 一种检测胸透dr片中肺结核病灶的图像处理方法
JP6898955B2 (ja) 情報処理装置
CN110251079A (zh) 一种用于移动设备的病患疼痛检测方法及系统
WO2022267300A1 (zh) 用于自动提取图像中目标区域的方法、系统及存储介质
CN110556173A (zh) 一种检查报告单智能分类管理系统及方法
CN103870688B (zh) 一种移动互联网环境下头颈部浅表疾病初筛的远程诊疗系统
JP6761717B2 (ja) 情報処理装置及びプログラム
CN110232360A (zh) 一种利用神经网络对荧光镜检真菌阴阳性的判别方法
CN111816314A (zh) 一种用于人工智能筛查尘肺病胸片遴选、标注及验证方法
CN113130050B (zh) 一种医学信息显示方法及显示系统
CN103246888A (zh) 肺病的计算机诊断系统及方法
Ghosh et al. Automatic white blood cell measuring aid for medical diagnosis
CN105550520A (zh) 移动设备、移动外接设备及基于虹膜信息检测健康的系统
WO2021157405A1 (ja) 解析装置、解析方法、解析プログラム及び診断支援システム
GB2616921A (en) System and methods for classifying magnetic resonance imaging (MRI) image characteristics
CN114678108A (zh) 一种中医状态判断的方法及终端
CN112086193A (zh) 一种基于物联网的人脸识别健康预测系统及方法
TWI684995B (zh) 醫療資訊轉換裝置及其方法
Jose et al. Monocular depth level estimation for breast self-examination (BSE) using RGBD BSE dataset
TWM564201U (zh) 醫療資訊轉換裝置
CN116682526B (zh) 基于古籍知识单元处理的中医知识推荐系统

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16896548

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 16896548

Country of ref document: EP

Kind code of ref document: A1