CN106650802B - A kind of seed classification recognition methods and system based on X-ray digital image - Google Patents
A kind of seed classification recognition methods and system based on X-ray digital image Download PDFInfo
- Publication number
- CN106650802B CN106650802B CN201611129352.2A CN201611129352A CN106650802B CN 106650802 B CN106650802 B CN 106650802B CN 201611129352 A CN201611129352 A CN 201611129352A CN 106650802 B CN106650802 B CN 106650802B
- Authority
- CN
- China
- Prior art keywords
- seed
- area
- interior
- cavity
- average value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
- G01N23/02—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material
- G01N23/04—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material and forming images of the material
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2223/00—Investigating materials by wave or particle radiation
- G01N2223/03—Investigating materials by wave or particle radiation by transmission
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2223/00—Investigating materials by wave or particle radiation
- G01N2223/10—Different kinds of radiation or particles
- G01N2223/101—Different kinds of radiation or particles electromagnetic radiation
- G01N2223/1016—X-ray
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2223/00—Investigating materials by wave or particle radiation
- G01N2223/40—Imaging
- G01N2223/401—Imaging image processing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2223/00—Investigating materials by wave or particle radiation
- G01N2223/40—Imaging
- G01N2223/421—Imaging digitised image, analysed in real time (recognition algorithms)
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2223/00—Investigating materials by wave or particle radiation
- G01N2223/60—Specific applications or type of materials
- G01N2223/635—Specific applications or type of materials fluids, granulates
-
- 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
- G06T2207/10116—X-ray image
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Biochemistry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of seed classification recognition methods and system based on X-ray digital image, method include: to obtain the X-ray digital image of seed to be identified;And be filtered, denoise and flat field processing, obtain the bianry image of X-ray digital image;Acquire the area of the area of seed to be identified and Interior Seed cavity to be identified in bianry image;According to the average value and seed cavity area percentage of the area of seed and the areal calculation seed area of internal cavities;And calculate average value, variance and the standard deviation of seed area and seed cavity area percentage;Classified according to average value, variance and the standard deviation of seed area, seed cavity area percentage to seed to be identified.The present invention, which is realized, to be accounted for the size judgement identification seed vitality of seed area ratio and seed by cavity area between embryo and endosperm and classifies, improve the identification accuracy of seed vitality, according to the automatic discrimination mode of radioscopic image, the speed for identifying the seed that flushes is improved.
Description
Technical field
The present invention relates to image identification technical fields, and in particular to a kind of seed classification knowledge based on X-ray digital image
Other method and system.
Background technique
Seed vitality is the total of germination and emergence rate, the potentiality of growth of seedling, plant anti-adversity ability and productive potentialities
Be the important indicator of seed quality.Choosing the seed to flush becomes an important ring for agriculture, forest development, reasonably selects
It takes and accurately application has pushed entire agriculture, forestry and its development of derivative industry indirectly.
Currently, the method for choosing the seed that flushes is gradually quick, lossless from traditional conventional method towards digital imagery etc.
Direction develop.The X-ray procedure number of seed vitality is analyzed it has been found that the embryo measured from photo is long, endosperm is wide and the energy that germinates
Power has significant correlation with seed vitality, and according to the embryo of Interior Seed is long, endosperm is wide etc., seed that structures are sorted is used
Surviving probability and will improve in transplanting.
The seed that the existing selection using radioscopic image flushes is carried out according to the area of the free cavity of Interior Seed
Focus, is usually concentrated on internal cavities area by analysis, and ignores seeds self size, causes identification seed vitality accuracy rate
Low problem
Summary of the invention
In order to solve the above technical problems, the present invention provides a kind of seed classification recognition methods based on X-ray digital image
And system, seed vitality is identified by the ratio that seed size and Interior Seed cavity account for seed area in the picture, is realized
Quick and precisely identify seed vitality.
To achieve the above object, the present invention the following technical schemes are provided:
On the one hand, the seed classification recognition methods based on X-ray digital image that the present invention provides a kind of, method include such as
Lower step:
Obtain the X-ray digital image of seed to be identified;
The X-ray digital image is filtered, denoise and flat field processing, obtain the two of the X-ray digital image
It is worth image;
Acquire the area S of seed to be identified in the bianry image1And the area S of Interior Seed cavity to be identified2;
According to the area S of seed1With the area S of internal cavities2Calculate seed area and Interior Seed cavity area percentage
Average value, variance and standard deviation than r;
According to seed area, Interior Seed cavity area percentage r average value, variance and standard deviation to be identified kind
Son carries out Classification and Identification.
Further, the area of the seed is the total pixel number of seed contoured interior in treated radioscopic image;Institute
The area for stating internal cavities is total pixel number inside treated radioscopic image hollow cavity exterior feature.
Further, the internal cavities that the Interior Seed cavity area percentage is formed between embryo and endosperm account for seed
The percentage of area, is calculated using following formula:
Wherein, S1For the area of seed in bianry image, S2For the area of Interior Seed cavity in bianry image.
Further, average value, variance and the standard according to seed area, Interior Seed cavity area percentage r
The step of difference carries out Classification and Identification to seed to be identified, specifically comprises the following steps:
Seed to be identified is grouped according to the average value of Interior Seed cavity area percentage r and variance;
According to the average value of seed areaClassify with seed of the standard deviation to above-mentioned classification.
Further, the average value and method according to Interior Seed cavity area percentage r is to seed to be identified
The step of being grouped, comprising:
Interior Seed cavity area percentage is less than the seed of the difference between average value and variance, is third group seed;
Interior Seed cavity area percentage is greater than the seed of average value, is first group of seed;
Seed except above-mentioned two situations is second group of seed.
Further, the average value according to seed areaClassify with seed of the standard deviation to above-mentioned classification
The step of, comprising:
The seed that seed area is greater than the average value of seed area is the first kind;
It is third class that seed area, which is less than the average value of seed area and the seed of the difference of twice of standard deviation,;
Seed except above-mentioned two situations is the second class.
On the other hand, the seed classification identifying system based on X-ray digital image that the present invention provides a kind of, comprising: place
Manage device, controller and image composer;
The processor is connected with the controller and image composer respectively, and the controller and described image generate
Device is connected;
Described image generator includes: the x-ray source being connected with controller and the receiver that is connected with processor;
The side of the x-ray source is equipped with crane, and the upper surface of described x-ray source is equipped with objective table, the objective table peace
It is moved up and down on crane and with crane;
The receiver is arranged by bracket in the upper surface of described objective table.
Further, the receiver includes: to obtain the ray camera of radioscopic image and be connected with ray camera,
It is used for transmission the transmitting device of the radioscopic image of acquisition.
Further, the system also includes:
For the shield of X-ray to be isolated, ray camera, objective table and x-ray source are equipped in the shield.
Further, the objective table is polyvinyl chloride panel or aluminium-foil paper.
As shown from the above technical solution, a kind of seed classification identification side based on X-ray digital image provided by the invention
Method and system account for the size judgement identification seed of seed area ratio and seed by the internal cavities formed between embryo and endosperm
Vigor is simultaneously classified, and the identification accuracy of seed vitality is improved, and according to the automatic discrimination mode of radioscopic image, improves identification
Flush the speed of seed.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is the present invention
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is a kind of flow diagram of seed classification recognition methods based on X-ray digital image of the invention;
Fig. 2 is the flow diagram classified in classifying identification method step S105 of the invention;
Fig. 3 is the flow diagram being grouped in classifying identification method step S105 of the invention;
Fig. 4 is a kind of structural schematic diagram of seed classification identifying system based on X-ray digital image of the invention;
Fig. 5 is the structural schematic diagram of image composer in classifying and identifying system of the invention;
Fig. 6 is seed X-ray digital image of the invention;
Fig. 7 is the extraction image of seed area of the invention;
Fig. 8 is that internal cavities of the invention extract image.
Wherein, 1- receiver, 2-X radiographic source, 3- crane, 4- objective table, 5- bracket.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, the technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Currently, choosing the seed to flush is the important ring for developing agriculture, forestry, the method for choosing the seed that flushes
Gradually the direction quick, lossless from traditional conventional method towards digital imagery etc. is developed.The existing selection using radioscopic image is living
The vigorous seed of power is analyzed according to the area of the free cavity of Interior Seed, focus is usually concentrated on internal cavities area,
And seeds self size is ignored, the problem for causing seed vitality recognition accuracy low.In order to solve the above technical problems, of the invention
A kind of seed classification recognition methods and system based on X-ray digital image is provided.
The embodiment of the present invention one provides a kind of seed classification recognition methods based on X-ray digital image, should referring to Fig. 1
Method specifically comprises the following steps:
S101: the X-ray digital image of seed to be identified is obtained;
In this step, seed to be identified is irradiated using x-ray source, is taken pictures by ray camera, obtain X-ray number
Image.
S102: the X-ray digital image is filtered, denoise and flat field processing, obtain the X-ray digital image
Bianry image;
In this step, since X-ray digital image resolution ratio is very high, grayscale value 16bit, regular display can not be straight
Display is connect, in order to show this high-precision image in regular display, image gray levels can be completed by windowing technology
Compression, the tonal range of high-precision image is compressed to 256 grades, and compressed image is filtered, denoise and flat field at
Reason.
S103: the area S of seed to be identified in the bianry image is acquired1And the area S of Interior Seed cavity to be identified2;
In this step, image is handled through step S102, the seed characteristics after extraction process in image, statistics kind
Area of the contoured interior total pixel number of son as seed, face of the total pixel number of Interior Seed cavity as Interior Seed cavity
Product.
S104: according to the area S of seed1With the area S of internal cavities2Calculate seed area and Interior Seed cavity face
Average value, variance and the standard deviation of product percentage r;
In this step, seed area percentage is the percent value that embryo and endosperm account for seed area jointly, using formulaIt is calculated, wherein S1For the area of seed in bianry image, S2For the face of Interior Seed cavity in bianry image
Product.
S105: knowledge is treated according to average value, variance and the standard deviation of seed area, Interior Seed cavity area percentage r
Other seed carries out Classification and Identification.
In this step, using the calculated result in step S104, according to the average value of Interior Seed cavity area percentage
Three groups are divided into seed to be identified with method,
It is divided into three classes according to seed of the average and standard deviation of seed area to classification.
As can be seen from the above description, a kind of seed classification recognition methods based on X-ray digital image provided by the invention, leads to
It crosses cavity area between embryo and endosperm to account for the size judgement identification seed vitality of seed area ratio and seed and classify, improve
The identification accuracy of seed vitality.
The embodiment of the present invention two provides the specific implementation that classification is divided in above-mentioned steps S105, referring to fig. 2, specific real
It is existing that steps are as follows:
S201: Interior Seed cavity area percentage is less than the seed of the difference between average value and variance, is third group
Seed;
S202: Interior Seed cavity area percentage is greater than the seed of average value, is first group of seed;
S203: the seed in addition to two kinds of situations of step S201 and step S202 is second group of seed.
The embodiment of the present invention three provides the specific implementation that classification is divided in above-mentioned steps S105, specific real referring to Fig. 3
It is existing that steps are as follows:
S301: the seed that seed area is greater than the average value of seed area is the first kind;
S302: it is third class that seed area, which is less than the average value of seed area and the seed of the difference of twice of standard deviation,;
S303: the seed in addition to two kinds of situations of step S301 and step S302 is the second class.
The embodiment of the present invention four provides a kind of seed classification identifying system based on X-ray digital image, referring to fig. 4, should
System specifically includes: processor, controller and image composer;
The processor is connected with the controller and image composer respectively, and the controller and described image generate
Device is connected;
Referring to Fig. 5, described image generator includes: the x-ray source being connected with controller and is connected with processor
Receiver;
The side of the x-ray source is equipped with crane, and the upper surface of described x-ray source is equipped with objective table, the objective table peace
It is moved up and down on crane and with crane;
The crane has the function of distance between adjusting objective table and receiver, can obtain difference by changing spacing
Visual field size, suitable spacing is selected according to actual visual field demand.
The receiver is arranged by bracket in the upper surface of described objective table.
The processor is preferably computer.
Further, the receiver includes: to obtain the ray camera of radioscopic image and be connected with ray camera,
It is used for transmission the transmitting device of the radioscopic image of acquisition.
Further, the system also includes:
For the shield of X-ray to be isolated, ray camera, objective table and x-ray source are equipped in the shield.
Further, the objective table is polyvinyl chloride panel or aluminium-foil paper.
As shown from the above technical solution, a kind of seed classification based on X-ray digital image provided by the invention identifies system
System improves the speed of identification seed vitality according to the automatic discrimination mode of radioscopic image.And the system structure is simple, behaviour
Facilitate.
The present invention is illustrated for using X-ray digital image analysis seed internal structure identification tomato seeds.Kind
Subsample is tomato seeds, kind Jin Di.More detections, share 200 seeds, point 10 groups of progress.
Tomato seeds are smaller, in order to obtain the in-built clear image of seed, tomato seeds pre-process-
Vernalization, the seed for not carrying out vernalization is not easy to be formed clearly internal cavities, while the degree of vernalization influences Interior Seed construction.For
It is qualitative it is lossless vigor judgement is carried out by Interior Seed structure, need stringent, unified control vernalization condition.If when vernalization
Between too long excessive, the vigor for the seed that cannot correctly reflect that will cause the free cavity that Interior Seed is formed by embryo and endosperm.
If germination time is too short, seed will be unable to be formed clearly free cavity structure, can not carry out the judgement of seed vitality.
Identifying system camera selects digital radial camera (model pxs11), resolution ratio 4008 × 2670, x-ray source transmitting
Point receives to be 110mm at a distance from plane with camera, and x-ray source (model vhr11) is connect with controller, controls X by controller
Voltage, the electric current of radiographic source ray tube, ray tube voltage 15.4kV, tube current 12.6uA, support board uses aluminium-foil paper, away from ray
The distance in source is 52mm.It was preheated when radiographic source uses by 25 minutes, stable ray can be generated, the setting time for exposure sets
It is set to 1s.Processor is computer, and radiographic source, ray camera, objective table are installed in shield, and ray camera obtains X and penetrates
Computer is passed back after line digital picture, and the image passed back extracts software using seed characteristics and handled.Due to radioscopic image point
Resolution is very high, and grayscale value 16bit, regular display can not directly display, this in order to show in regular display
High-precision image can complete the compression of image gray levels by windowing technology, and the tonal range of image is compressed to 256 grades.Fig. 6
For the X-ray digital image of tomato seeds.
Image is filtered, denoise and flat field processing, count nomospermous contoured interior total pixel number as seed
Area, the result that the extraction of seed area and internal cavities extract is as shown in Figure 7,8, counts area, the seed of ten groups of seeds
Internal cavities area and ratio between the two.It calculates between every group of tomato seeds area, embryo and endosperm shared by internal cavities
The internal standard of the mean value of seed area percentage and every group of data is poor.Seed is divided into 3 classes according to this result, such as table 1
It is shown.The present invention compare only by embryo and endosperm account for seed area ratio judge seed vitality and consider seed size in the case of
Account for seed area ratio by embryo and endosperm and judge seed vitality recognition accuracy, recognition accuracy as shown in table 2 (wherein V1,
V2, V3 are classification results), the recognition accuracy of vigor is determined by seed germination experiment.
1 seed classification result of table
The recognition accuracy of 2 two kinds of classification methods of table
As can be seen from the above description, using digital imaging technology in Image Acquisition, enable the X-ray digital image obtained
Computer Image Processing is carried out, qualitatively to carry out vigor signature analysis;By seeds self size information and Interior Seed cavity
It accounts for seed area percent information and is combined together progress seed vitality judgement, accuracy rate is higher;Identifying system has quick, lossless
The characteristics of detection, structure are simple and convenient to operate.
The above examples are only used to illustrate the technical scheme of the present invention, rather than its limitations;Although with reference to the foregoing embodiments
Invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each implementation
Technical solution documented by example is modified or equivalent replacement of some of the technical features;And these are modified or replace
It changes, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.
Claims (4)
1. a kind of seed classification recognition methods based on X-ray digital image, which is characterized in that the method includes walking as follows
It is rapid:
Obtain the X-ray digital image of seed to be identified;
The X-ray digital image is filtered, denoise and flat field processing, obtain the binary map of the X-ray digital image
Picture;
Acquire the area S of seed to be identified in the bianry image1And the area S of Interior Seed cavity to be identified2;
According to the area S of seed1With the area S of internal cavities2Calculate seed area, Interior Seed cavity area percentage r it is flat
Mean value, variance and standard deviation;
According to seed area, Interior Seed cavity area percentage r average value, variance and standard deviation to seed to be identified into
Row Classification and Identification;
It is described according to seed area, Interior Seed cavity area percentage r average value, variance and standard deviation to be identified kind
Son carries out the step of Classification and Identification, specifically comprises the following steps:
Seed to be identified is grouped according to the average value of Interior Seed cavity area percentage r and variance;
According to the average value of seed areaClassify with seed of the standard deviation to above-mentioned grouping;
The average value according to seed areaThe step of classifying with seed of the standard deviation to above-mentioned grouping, comprising:
The seed that seed area is greater than the average value of seed area is the first kind;
It is third class that seed area, which is less than the average value of seed area and the seed of the difference of twice of standard deviation,;
Seed except above-mentioned two situations is the second class.
2. the method according to claim 1, wherein the area of the seed is in treated radioscopic image
The total pixel number of seed contoured interior;The area of the internal cavities is total inside treated radioscopic image hollow cavity exterior feature
Pixel number.
3. the method according to claim 1, wherein the Interior Seed cavity area percentage is embryo and endosperm
Between the internal cavities that are formed account for the percentage of seed area, calculated using following formula:
Wherein, S1For the area of seed in bianry image, S2For the area of Interior Seed cavity in bianry image.
4. the method according to claim 1, wherein described according to the flat of Interior Seed cavity area percentage r
The step of mean value and variance are grouped seed to be identified, comprising:
Interior Seed cavity area percentage is less than the seed of the difference between average value and variance, is third group seed;
Interior Seed cavity area percentage is greater than the seed of average value, is first group of seed;
Seed except above-mentioned two situations is second group of seed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611129352.2A CN106650802B (en) | 2016-12-09 | 2016-12-09 | A kind of seed classification recognition methods and system based on X-ray digital image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611129352.2A CN106650802B (en) | 2016-12-09 | 2016-12-09 | A kind of seed classification recognition methods and system based on X-ray digital image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106650802A CN106650802A (en) | 2017-05-10 |
CN106650802B true CN106650802B (en) | 2019-07-02 |
Family
ID=58823941
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611129352.2A Active CN106650802B (en) | 2016-12-09 | 2016-12-09 | A kind of seed classification recognition methods and system based on X-ray digital image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106650802B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
BR112020017937A2 (en) | 2018-03-14 | 2020-12-22 | Monsanto Technology Llc | SEED IMAGEING SYSTEM AND METHOD |
CA3100922A1 (en) | 2018-06-11 | 2019-12-19 | Monsanto Technology Llc | Seed sorting |
CN110352660B (en) * | 2019-07-12 | 2021-08-27 | 塔里木大学 | Method and device for processing information of rapid nondestructive testing of vitality of delinted cotton seeds |
WO2021097093A1 (en) * | 2019-11-13 | 2021-05-20 | Monsanto Technology Llc | X-ray seed imaging system, cabinet x-ray device, and methods of evaluating seeds |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104137148A (en) * | 2011-12-30 | 2014-11-05 | 先锋国际良种公司 | Immature ear photometry in maize |
CN104619254A (en) * | 2012-08-17 | 2015-05-13 | 皇家飞利浦有限公司 | Camera-based visual adustment of a movable x-ray imaging system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2620909B1 (en) * | 2012-01-24 | 2014-12-24 | General Electric Company | Method, system and computer readable medium for automatic segmentation of a medical image |
-
2016
- 2016-12-09 CN CN201611129352.2A patent/CN106650802B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104137148A (en) * | 2011-12-30 | 2014-11-05 | 先锋国际良种公司 | Immature ear photometry in maize |
CN104619254A (en) * | 2012-08-17 | 2015-05-13 | 皇家飞利浦有限公司 | Camera-based visual adustment of a movable x-ray imaging system |
Also Published As
Publication number | Publication date |
---|---|
CN106650802A (en) | 2017-05-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106650802B (en) | A kind of seed classification recognition methods and system based on X-ray digital image | |
CN106875373B (en) | Mobile phone screen MURA defect detection method based on convolutional neural network pruning algorithm | |
CN102096917B (en) | Automatic eliminating method for redundant image data of capsule endoscope | |
US6356651B2 (en) | Method and apparatus for recognizing irradiation fields on radiation images | |
CN109662686B (en) | Fundus macular positioning method, device, system and storage medium | |
US8787620B2 (en) | Automated crystal identification achieved via watershed segmentation | |
CN109738442B (en) | Full-automatic rice ear character extraction system based on large-field X-ray visible light registration imaging | |
CN108480239B (en) | Workpiece quick sorting method and device based on stereoscopic vision | |
CN112261361B (en) | Microphone array and dome camera linked abnormal sound source monitoring method and system | |
CN109919908A (en) | The method and apparatus of light-emitting diode chip for backlight unit defects detection | |
CN110555836A (en) | Automatic identification method and system for standard fetal section in ultrasonic image | |
CN109086763B (en) | Pointer instrument reading method and device | |
CN106875404A (en) | The intelligent identification Method of epithelial cell in a kind of leukorrhea micro-image | |
WO2021031711A1 (en) | Method and apparatus for identifying location spectrum, and computer storage medium | |
CN115131346B (en) | Fermentation tank processing procedure detection method and system based on artificial intelligence | |
CN112598054B (en) | Power transmission and transformation project quality common disease prevention and detection method based on deep learning | |
JP2016191589A (en) | Defect classification device defect classification method | |
CN107064751A (en) | A kind of dual-waveband imaging discharge detector and its application method for high ferro | |
CN114898327A (en) | Vehicle detection method based on lightweight deep learning network | |
CN113255434A (en) | Apple identification method fusing fruit features and deep convolutional neural network | |
CN110619297B (en) | Bean fruiting body image batch acquisition and recognition method and device | |
CN116682106A (en) | Deep learning-based intelligent detection method and device for diaphorina citri | |
CN105405145A (en) | Image segmentation technology based granule counting method | |
CN104516170B (en) | Three-dimensional focusing method and system thereof | |
CN114468973A (en) | Intelligent vision detection system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |