CN109536570A - A kind of grain storage two Methods for Fungi Detection - Google Patents

A kind of grain storage two Methods for Fungi Detection Download PDF

Info

Publication number
CN109536570A
CN109536570A CN201811383953.5A CN201811383953A CN109536570A CN 109536570 A CN109536570 A CN 109536570A CN 201811383953 A CN201811383953 A CN 201811383953A CN 109536570 A CN109536570 A CN 109536570A
Authority
CN
China
Prior art keywords
fungal spore
spore suspension
grain storage
fungal
storage sample
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201811383953.5A
Other languages
Chinese (zh)
Inventor
唐芳
张海洋
祁智慧
程树峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Academy Of Sciences State Bureau Of Food And Materials Reserve
Original Assignee
Academy Of Sciences State Bureau Of Food And Materials Reserve
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 Academy Of Sciences State Bureau Of Food And Materials Reserve filed Critical Academy Of Sciences State Bureau Of Food And Materials Reserve
Priority to CN201811383953.5A priority Critical patent/CN109536570A/en
Publication of CN109536570A publication Critical patent/CN109536570A/en
Pending legal-status Critical Current

Links

Classifications

    • 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
    • C12Q1/06—Quantitative determination
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2333/00—Assays involving biological materials from specific organisms or of a specific nature
    • G01N2333/37—Assays involving biological materials from specific organisms or of a specific nature from fungi
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10056—Microscopic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30242—Counting objects in image

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Organic Chemistry (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Wood Science & Technology (AREA)
  • Physics & Mathematics (AREA)
  • Proteomics, Peptides & Aminoacids (AREA)
  • General Health & Medical Sciences (AREA)
  • Zoology (AREA)
  • General Engineering & Computer Science (AREA)
  • Analytical Chemistry (AREA)
  • Molecular Biology (AREA)
  • Immunology (AREA)
  • Toxicology (AREA)
  • Biotechnology (AREA)
  • Biochemistry (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Biophysics (AREA)
  • Microbiology (AREA)
  • Genetics & Genomics (AREA)
  • Medical Informatics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
  • Apparatus Associated With Microorganisms And Enzymes (AREA)

Abstract

The present invention discloses a kind of grain storage two Methods for Fungi Detection, and a specific embodiment of this method includes: to be impregnated with distilled water to grain storage sample, obtains the fungal spore suspension of grain storage sample after successively carrying out oscillation and contaminant filter to soak；Shooting is amplified to fungal spore suspension by preset amplification factor, obtains fungal spore suspension image；The fungal spore in fungal spore suspension image is identified and counted using the convolutional neural networks Fast Recognition Algorithm based on region, the fungal spore number in fungal spore suspension image is obtained, the fuugal spores counts of grain storage sample are calculated according to the fungal spore number in fungal spore suspension image.The embodiment can fast and accurately realize the automatic detection of grain storage fungi.

Description

A kind of grain storage two Methods for Fungi Detection
Technical field
The present invention relates to technical field of food science.More particularly, to a kind of grain storage two Methods for Fungi Detection.
Background technique
The harm of fungi is the stored grain safety problem of global facing.It is counted according to FAO, every year because of grain caused by fungal attack The loss of food accounts for the 25% of the yield of grain, and the grain loss as caused by the harm of fungi occupies quite big in storage Ratio, about 1,000,000,000 dollars of direct economic loss caused by the U.S. is therefore annual, some areas in China, grain is in storage Middle part appearance fever, mildew phenomena happen occasionally, and this phenomenon is in individual regional even also than more serious, serious threat The grain safety in China.
The detection method of common grain storage fungi mainly uses the method for plate culture count, is the one of Food microbe testing Kind classical way, can be used for the detection of most of fungies.But this method it is cumbersome, need to be by professional sterile Under the conditions of operate.And the time that this method needs is long, it usually needs seven day time.In addition, this method is endangered for grain storage When the detection of fungi, since the growth characteristic of important fungi Aspergillus glaucus a kind of in these fungies is even if in most suitable height In the high salt culture medium of sugar, growth also very slowly, cultivates the bacterium that spore can not all be sprouted, and be grown in sometimes more than 10 days Silk is unable to the bacterium colony of formation rule, brings very big difficulty to bacterium colony counting, can directly result in the increase of detection error.
" detection of grain and oil detection grain storage fungi-spore count method " professional standard is issued and implemented in March, 2018, is filled up The blank of China's grain storage fungal detection.This method needs testing staff by microscope amplification effect, observes by the naked eye to fungi Spore is identified and is counted.This requires testing staff certain microbiological manipulations basis, and grain depot base testing staff is general All over not having microorganism professional knowledge, therefore the popularization and application of this method are limited to a certain extent.
Accordingly, it is desirable to provide it is a kind of quickly, it is accurate and can realize the grain storage two Methods for Fungi Detection detected automatically.
Summary of the invention
The purpose of the present invention is to provide it is a kind of quickly, it is accurate and can realize the grain storage two Methods for Fungi Detection detected automatically.
In order to achieve the above objectives, the present invention adopts the following technical solutions:
The present invention provides a kind of grain storage two Methods for Fungi Detection, comprising:
Grain storage sample is impregnated with distilled water, obtains grain storage sample after successively carrying out oscillation and contaminant filter to soak The fungal spore suspension of product；
Shooting is amplified to fungal spore suspension by preset amplification factor, obtains fungal spore suspension image；
Using the convolutional neural networks Fast Recognition Algorithm based on region to the allergenic in fungal spore suspension image Son is identified and is counted, and the fungal spore number in fungal spore suspension image is obtained, according to fungal spore suspension figure The fuugal spores counts of grain storage sample are calculated in fungal spore number as in.
Preferably, described that grain storage sample is impregnated with distilled water, oscillation and contaminant filter are successively carried out to soak The fungal spore suspension for obtaining grain storage sample afterwards further comprises:
Grain storage sample is placed in test tube, distilled water immersion is added；
Filter-cloth filtering soak is used after vibrating test tube, obtains the fungal spore suspension of grain storage sample.
Preferably, described that shooting is amplified to fungal spore suspension by preset amplification factor, obtain fungal spore Suspension image further comprises:
Coverslip is covered on the count block of blood counting chamber, is drawn after fungal spore suspension is shaken up with rubber head dropper Fungal spore suspension adds fungal spore suspension in coverslip marginal point, by siphon mode make fungal spore suspension into Enter count block；
After the duration for standing setting, shooting is amplified to fungal spore suspension by preset amplification factor, is obtained true Bacterium spore suspension image.
Preferably, this method further include:
Count block is divided into multiple viewing areas, it is suspended by fungal spore of the preset amplification factor to each viewing area Liquid amplifies shooting, obtains the corresponding fungal spore suspension subgraph of each viewing area；
Using the convolutional neural networks Fast Recognition Algorithm based on region to true in each fungal spore suspension subgraph Bacterium spore is identified and is counted, and regard the sum of the fungal spore number in each fungal spore suspension subgraph as fungal spore Fungal spore number in suspension image.
Preferably, the amplification factor is 600 times.
Preferably, described to use the convolutional neural networks Fast Recognition Algorithm based on region to fungal spore suspension image In fungal spore identified and counted and further comprise:
By the more of the vector form of the row pixel number of fungal spore suspension image table diagram picture, column pixel number and port number Dimension group carries out feature extraction to Multidimensional numerical using the convolutional neural networks model by fungal spore shape up exercise, obtains Convolution characteristic pattern；
Region is carried out to convolution characteristic pattern and suggests network processes, to find related objective and predefining comprising related objective The bounding box of quantity, the related objective are fungal spore；
Obtain related objective and its in fungal spore suspension image behind corresponding position, to convolutional neural networks model The feature of extraction and bounding box comprising related objective carry out the processing of interest pool areaization, and extract the feature of related objective；
Using the convolutional neural networks model based on region, the object in bounding box is carried out based on the feature of related objective Classification and Identification, and then realize and the fungal spore in region observed by fungal spore suspension is identified and counted.
Preferably, the true of grain storage sample is calculated in the fungal spore number according in fungal spore suspension image Bacterium spore count further comprises:
The fuugal spores counts of grain storage sample: B=A* α * M/G are calculated based on following formula, wherein B is grain storage sample Fungal infection rate, A is the fungal spore number in fungal spore suspension image, and α is the conversion coefficient of amplification factor, and M is The volume of fungal spore suspension, G are the quality of grain storage sample.
Beneficial effects of the present invention are as follows:
Technical solution of the present invention can fast and accurately realize the automatic detection of grain storage fungi, and detection speed is fast, fungi The accuracy rate of spore identification is high, is particularly suitable for the early detection of grain storage fungal attack.
Detailed description of the invention
Specific embodiments of the present invention will be described in further detail with reference to the accompanying drawing；
Fig. 1 shows the flow chart of grain storage two Methods for Fungi Detection provided in an embodiment of the present invention.
Specific embodiment
In order to illustrate more clearly of the present invention, the present invention is done further below with reference to preferred embodiments and drawings It is bright.Similar component is indicated in attached drawing with identical appended drawing reference.It will be appreciated by those skilled in the art that institute is specific below The content of description is illustrative and be not restrictive, and should not be limited the scope of the invention with this.
The embodiment provides a kind of grain storage two Methods for Fungi Detection, comprising:
Grain storage sample is impregnated with distilled water, obtains grain storage sample after successively carrying out oscillation and contaminant filter to soak The fungal spore suspension of product；
Shooting is amplified to fungal spore suspension by preset amplification factor, obtains fungal spore suspension image；
Using the convolutional neural networks Fast Recognition Algorithm based on region to the allergenic in fungal spore suspension image Son is identified and is counted, and the fungal spore number in fungal spore suspension image is obtained, according to fungal spore suspension figure The fuugal spores counts of grain storage sample are calculated in fungal spore number as in, and the fuugal spores counts of grain storage sample can characterize grain storage Fungus infestation, can be used as grain storage fungal detection result.
Grain storage two Methods for Fungi Detection provided in this embodiment can carry out specific factor amplification by microscope and realize that amplification is clapped Fungal spore suspension image is taken the photograph, identifies the fungal spore for counting and calculating grain storage sample to fungal spore automatically by algorithm Number, and then fast and accurately realize the automatic detection of grain storage fungi, detection speed is fast, and the accuracy rate of fungal spore identification is high, especially It is suitable for the early detections of grain storage fungal attack.
In some optional implementations of the present embodiment, obtained after successively carrying out oscillation and contaminant filter to soak The fungal spore suspension of grain storage sample further comprises:
Grain storage sample is placed in test tube, distilled water immersion is added；
Filter-cloth filtering soak is used after vibrating test tube, obtains the fungal spore suspension of grain storage sample.
One specific example of this implementation are as follows: weigh 10g grain storage sample and be placed in capacity 80mL tool plug test tube, add Enter 30mL distilled water, jump a queue, acutely concussion 180~200 times, timing 1min collects allergenic with 300 mesh filter-cloth filterings up and down Sub- suspension.
In some optional implementations of the present embodiment, fungal spore suspension is carried out by preset amplification factor Bust shot, obtaining fungal spore suspension image further comprises:
Coverslip is covered on the count block of blood counting chamber, is drawn after fungal spore suspension is shaken up with rubber head dropper Fungal spore suspension adds fungal spore suspension in coverslip marginal point, by siphon mode make fungal spore suspension into Enter count block；
After the duration for standing setting, shooting is amplified to fungal spore suspension by preset amplification factor, is obtained true Bacterium spore suspension image.
One specific example of this implementation are as follows: blood counting chamber is rinsed well with distilled water, it is quick with ear washing bulb Dry up the count block of blood counting chamber.Later, coverslip first is covered on blood counting chamber count block, by fungal spore suspension After shaking up, fungal spore suspension is drawn with rubber head dropper immediately, adds fungal spore suspension in coverslip marginal point, by rainbow Suction mode makes fungal spore suspension enter count block, after standing 10s, blood counting chamber is placed on objective table, by micro- Mirror carries out specific factor amplification and realizes bust shot fungal spore suspension image.
In some optional implementations of the present embodiment, this method further include:
Count block is divided into multiple viewing areas, it is suspended by fungal spore of the preset amplification factor to each viewing area Liquid amplifies shooting, obtains the corresponding fungal spore suspension subgraph of each viewing area；
Using the convolutional neural networks Fast Recognition Algorithm based on region to true in each fungal spore suspension subgraph Bacterium spore is identified and is counted, and regard the sum of the fungal spore number in each fungal spore suspension subgraph as fungal spore Fungal spore number in suspension image.
This implementation can further improve the standard counted to the identification of the fungal spore in fungal spore suspension image True property.
In some optional implementations of the present embodiment, amplification factor is chosen for 600 times.Amplification factor is chosen for 600 times are suitable for identifying and a variety of fungal spores such as the Aspergillus glaucus, mould, aspergillus albicans, the aspergillus flavus that count 2 to 12 micrometer lengths. In addition, amplification factor is chosen for 200 times of sickle-like bacteria spores for being suitable for identifying and counting 30 to 60 micrometer lengths.
In some optional implementations of the present embodiment, calculation is quickly identified using the convolutional neural networks based on region Method is identified and is counted to the fungal spore in fungal spore suspension image:
By the row pixel number, column pixel number and the port number (port number of image of fungal spore suspension image table diagram picture Usually 3, i.e. RGB primary display channels) vector form Multidimensional numerical, utilize by fungal spore shape up exercise convolution mind Feature extraction is carried out to Multidimensional numerical through network model (CNN model), obtains convolution characteristic pattern (conv feature map)；
Region is carried out to convolution characteristic pattern and suggests network (RPN) processing, to find related objective (objects) and comprising phase The bounding box (region in other words, regions) of the predefined quantity of target is closed, related objective is fungal spore (predefined quantity Refer to and pre-define a certain number of frames, train these frames to find spore, the quantity of these frames is exactly predefined quantity)；
Obtain related objective and its in fungal spore suspension image behind corresponding position, to convolutional neural networks model The feature of extraction and bounding box comprising related objective carry out interest pool area (RoI Pooling) processing, and extract correlation Clarification of objective；
Using convolutional neural networks (R-CNN) model based on region, based on the feature of related objective in bounding box Object carries out Classification and Identification, and then realizes and the fungal spore in fungal spore suspension image is identified and counted.
In some optional implementations of the present embodiment, according to the fungal spore in fungal spore suspension image The fuugal spores counts that grain storage sample is calculated in number further comprise:
The fuugal spores counts of grain storage sample: B=A* α * M/G are calculated based on following formula, wherein B is grain storage sample Fungal infection rate, A is the fungal spore number in fungal spore suspension image, and α is the conversion coefficient of amplification factor, and M is The volume of fungal spore suspension, G are the quality of grain storage sample.
It is 10g with the quality of grain storage sample, the distilled water of addition is 30mL (i.e. fungal spore suspension is 30mL), amplification The conversion coefficient of multiple is 104mL-1For, the formula are as follows: B=A*104mL-1* 30mL/10g, the fungal infection rate of grain storage sample The unit of B is a/g.
In the description of the present invention, it should be noted that the orientation or positional relationship of the instructions such as term " on ", "lower" is base In orientation or positional relationship shown in the drawings, it is merely for convenience of description of the present invention and simplification of the description, rather than indication or suggestion Signified device or element must have a particular orientation, be constructed and operated in a specific orientation, therefore should not be understood as to this The limitation of invention.Unless otherwise clearly defined and limited, term " installation ", " connected ", " connection " shall be understood in a broad sense, example Such as, it may be fixed connection or may be dismantle connection, or integral connection；It can be mechanical connection, be also possible to be electrically connected It connects；It can be directly connected, the connection inside two elements can also be can be indirectly connected through an intermediary.For this For the those of ordinary skill in field, the specific meanings of the above terms in the present invention can be understood according to specific conditions.
It should also be noted that, in the description of the present invention, relational terms such as first and second and the like are only used Distinguish one entity or operation from another entity or operation, without necessarily requiring or implying these entities or There are any actual relationship or orders between operation.Moreover, the terms "include", "comprise" or its any other change Body is intended to non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wrapped Those elements are included, but also including other elements that are not explicitly listed, or further includes for this process, method, article Or the element that equipment is intrinsic.In the absence of more restrictions, the element limited by sentence "including a ...", and It is not excluded in process, method, article or equipment in the process, method, article or apparatus that includes the element that there is also other identical elements.
Obviously, the above embodiment of the present invention be only to clearly illustrate example of the present invention, and not be pair The restriction of embodiments of the present invention for those of ordinary skill in the art on the basis of the above description can be with It makes other variations or changes in different ways, all embodiments can not be exhaustive here, it is all to belong to the present invention The obvious changes or variations extended out of technical solution still in the scope of protection of the present invention.

Claims (7)

1. a kind of grain storage two Methods for Fungi Detection characterized by comprising
Grain storage sample is impregnated with distilled water, obtains grain storage sample after successively carrying out oscillation and contaminant filter to soak Fungal spore suspension；
Shooting is amplified to fungal spore suspension by preset amplification factor, obtains fungal spore suspension image；
Using the convolutional neural networks Fast Recognition Algorithm based on region to the fungal spore in fungal spore suspension image into Row is identified and is counted, and the fungal spore number in fungal spore suspension image is obtained, according in fungal spore suspension image Fungal spore number the fuugal spores counts of grain storage sample are calculated.
2. the method according to claim 1, wherein described impregnate grain storage sample with distilled water, to leaching The fungal spore suspension that bubble liquid successively carries out vibrating with obtaining grain storage sample after contaminant filter further comprises:
Grain storage sample is placed in test tube, distilled water immersion is added；
Filter-cloth filtering soak is used after vibrating test tube, obtains the fungal spore suspension of grain storage sample.
3. the method according to claim 1, wherein described press preset amplification factor to fungal spore suspension Shooting is amplified, obtaining fungal spore suspension image further comprises:
Coverslip is covered on the count block of blood counting chamber, draws fungi with rubber head dropper after fungal spore suspension is shaken up Spore suspension adds fungal spore suspension in coverslip marginal point, so that fungal spore suspension is entered meter by siphon mode Number area；
After the duration for standing setting, shooting is amplified to fungal spore suspension by preset amplification factor, obtains allergenic Sub- suspension image.
4. according to the method described in claim 3, it is characterized in that, this method further include:
Count block is divided into multiple viewing areas, by preset amplification factor to the fungal spore suspension of each viewing area into Row bust shot obtains the corresponding fungal spore suspension subgraph of each viewing area；
Using the convolutional neural networks Fast Recognition Algorithm based on region to the allergenic in each fungal spore suspension subgraph Son is identified and is counted, and is used as fungal spore suspended the sum of fungal spore number in each fungal spore suspension subgraph Fungal spore number in region observed by liquid.
5. according to the method described in claim 4, it is characterized in that, the amplification factor is 600 times.
6. the method according to claim 1, wherein described quickly known using the convolutional neural networks based on region Other algorithm is identified and is counted to the fungal spore in fungal spore suspension image:
By the multidimensional number of the vector form of the row pixel number of fungal spore suspension image table diagram picture, column pixel number and port number Group carries out feature extraction to Multidimensional numerical using the convolutional neural networks model by fungal spore shape up exercise, obtains convolution Characteristic pattern；
Region is carried out to convolution characteristic pattern and suggests network processes, to find related objective and the predefined quantity comprising related objective Bounding box, the related objective be fungal spore；
Obtain related objective and its in fungal spore suspension image behind corresponding position, to convolutional neural networks model extraction Feature and bounding box comprising related objective carry out the processing of interest pool areaization, and extract the feature of related objective；
Using the convolutional neural networks model based on region, classified based on the feature of related objective to the object in bounding box Identification, and then realize and the fungal spore in fungal spore suspension image is identified and counted.
7. the method according to claim 1, wherein the allergenic according in fungal spore suspension image The fuugal spores counts that grain storage sample is calculated in sub- number further comprise:
The fuugal spores counts of grain storage sample: B=A* α * M/G are calculated based on following formula, wherein B is the true of grain storage sample Bacterium spore count, A are the fungal spore number in fungal spore suspension image, and α is the conversion coefficient of amplification factor, and M is fungi The volume of spore suspension, G are the quality of grain storage sample.
CN201811383953.5A 2018-11-20 2018-11-20 A kind of grain storage two Methods for Fungi Detection Pending CN109536570A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811383953.5A CN109536570A (en) 2018-11-20 2018-11-20 A kind of grain storage two Methods for Fungi Detection

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811383953.5A CN109536570A (en) 2018-11-20 2018-11-20 A kind of grain storage two Methods for Fungi Detection

Publications (1)

Publication Number Publication Date
CN109536570A true CN109536570A (en) 2019-03-29

Family

ID=65848521

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811383953.5A Pending CN109536570A (en) 2018-11-20 2018-11-20 A kind of grain storage two Methods for Fungi Detection

Country Status (1)

Country Link
CN (1) CN109536570A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112226356A (en) * 2020-11-02 2021-01-15 国家粮食和物资储备局科学研究院 Automatic detection system and method for grain storage fungi
CN112381776A (en) * 2020-11-09 2021-02-19 深圳前海微众银行股份有限公司 Method and device for determining impurities of contents in transparent container

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108520206A (en) * 2018-03-22 2018-09-11 南京大学 A kind of fungi microscopic image identification method based on full convolutional neural networks

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108520206A (en) * 2018-03-22 2018-09-11 南京大学 A kind of fungi microscopic image identification method based on full convolutional neural networks

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
ALVARO FUENTES等: "a robust deep-learning-based detector for real-time tomato plant diseases and pests recognition", 《SENSORS》 *
岳路路: "基于机器学习的真菌孢子显微图像的特征提取与识别", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *
沈驭风: "基于深度学习的储粮害虫检测算法的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112226356A (en) * 2020-11-02 2021-01-15 国家粮食和物资储备局科学研究院 Automatic detection system and method for grain storage fungi
CN112381776A (en) * 2020-11-09 2021-02-19 深圳前海微众银行股份有限公司 Method and device for determining impurities of contents in transparent container

Similar Documents

Publication Publication Date Title
Wolfe et al. The use of virulence analysis in cereal mildews.
CN105181912B (en) A kind of Noninvasive Measuring Method of Freshness in rice storage
CN107580715A (en) Method and system for automatic counting microbial colonies
CN109536570A (en) A kind of grain storage two Methods for Fungi Detection
CN109001407B (en) Lake water quality analysis system
US10870876B2 (en) Method for detecting a presence or absence of at least one first zone of inhibition
AU2017220648A1 (en) Microscope assembly
CN103745478A (en) Machine vision determination method for wheat germination rate
CN107832801B (en) Model construction method for cell image classification
CN105335982B (en) A kind of dividing method of adhesion bacterium colony
CN112362553B (en) Compact sandstone micro-pore structure characterization method
CN106215499A (en) A kind of zooplankton classified filtering device and application thereof
CN105320970A (en) Potato disease diagnostic device, diagnostic system and diagnostic method
CN103270893B (en) Method for appraising resistance of strawberries to gray mold
CN111881864A (en) Wisdom farming crops growth full-period full-dynamic monitoring management system
CN116797529A (en) Rice setting rate measuring and calculating method
CN105574516B (en) The ornamental pine apple chlorophyll detection method returned based on logistic in visible images
CN111141332A (en) Flow guide device for liquor picking process of distilled liquor and online measurement system and method
CN110199711A (en) A kind of mould accurate identification method of Resistance To Root Rot Disease resource of big bean curd
Savino et al. Airborne fungi in an Italian rice mill
Pei et al. Quantitative relationships between inoculum of Melampsora larici‐epitea and corresponding disease on Salix
Pei et al. Quantitative inoculations of poplars with Melampsora larici-populina
JP5658902B2 (en) Bacteria imaging device and bacterial liquid adjustment device
Dreiseitl Rare virulences of barley powdery mildew found in aerial populations in the Czech Republic from 2009 to 2014.
CN113610048A (en) Automatic litchi frost blight identification method and system based on image identification and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20190329

RJ01 Rejection of invention patent application after publication