CN105761259A - Wheat leaf stoma density measurement method based on microscopic image - Google Patents
Wheat leaf stoma density measurement method based on microscopic image Download PDFInfo
- Publication number
- CN105761259A CN105761259A CN201610085012.8A CN201610085012A CN105761259A CN 105761259 A CN105761259 A CN 105761259A CN 201610085012 A CN201610085012 A CN 201610085012A CN 105761259 A CN105761259 A CN 105761259A
- Authority
- CN
- China
- Prior art keywords
- image
- wheat leaf
- leaf blade
- pore
- gray
- 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.)
- Granted
Links
Classifications
-
- 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
- G06T7/0004—Industrial image inspection
-
- 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
- G06T2207/10061—Microscopic image from scanning electron microscope
-
- 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
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a wheat leaf stoma density measurement method based on a microscopic image, and belongs to the technical field of computer vision. A wheat leaf image is acquired by adopting a digital microscope, and gray processing is performed on the acquired image by adopting a mixed gray processing method so that a gray scale image of the wheat leaf is obtained; image binarization processing is self-adaptively performed by adopting a maximum between-class variance method; linear structural elements are self-adaptively selected to perform morphological opening operation according to the arrangement direction of the wheat leaf stomata so as to eliminate influence of background noise; and connected area detection is performed so that position influence of the wheat leaf stomata in the image is obtained, statistics of the number of the stomata in the field of view is performed, and stoma density calculation is performed according to the size of calibration of the microscope. Density of the wheat leaf stomata in the microscopic image can be detected in real time so that the problems of time consumption and labor consumption of manual calculation of the existing system can be effectively solved, and the method can be applied to the influence study of the characteristics of the wheat leaf stomata and the study of wheat growth models under different stress or different growing environments.
Description
Technical field
The invention belongs to technical field of computer vision, be specifically related to a kind of wheat leaf blade stomatal frequency measuring method based on micro-image.
Background technology
In recent years, the pore character of crop has become the important research content of the basic research such as crop yield physiology and stress physiology.The density of pore can affect photosynthesis and the transpiration of plant, is one of important parameter characterizing wheat leaf blade stomatal properties.Major part research at present is all the measurement being carried out stomatal frequency by artificial counting, the method not only lavishes labor on, and when data volume is very big, is manually easy to because mistake occurs in fatigue, also can be subject to the impact of outside environmental elements, it is impossible in time the data gathered are processed.Along with the development of computer technology, image processing techniques, due to its environmental protection, not by advantages such as external environment are limited, is widely used in multiple links of agriculture field, including the visual system of the detection of agricultural product, crop growth conditions monitoring and agricultural robot.
Summary of the invention
It is an object of the invention to provide a kind of method of wheat leaf blade stomatal frequency in automatic calculating visual field.Processed by the wheat leaf blade image that digital microscope is collected, obtain the quantity of wheat leaf blade pore in visual field, thus calculating the density obtaining wheat leaf blade pore.In order to realize above-mentioned target, the present invention mainly adopts the following technical scheme that:
A kind of wheat leaf blade stomatal frequency measuring method based on micro-image, carries out as steps described below:
(1) image acquisition and gray processing process
Using digital microscope to gather the image of wheat leaf blade pore, computer reads the image gathered and processes.Consider that in the coloured image of wheat leaf blade, G component is higher, in order to isolate air cap preferably, the image gathered is carried out gray processing by the gray processing method adopting mixing, then by regular for gray value be double (double-precision floating point type) type in 0 to 1 scope, obtain the gray level image of wheat leaf blade.
(2) image segmentation
Adopt maximum variance between clusters that the image of gray processing is carried out binary conversion treatment, obtain image segmentation result.Maximum variance between clusters divides the image into background and target two parts by the gamma characteristic of image, inter-class variance between background and target is more big, illustrating that the two-part difference of pie graph picture is more big, therefore, the segmentation making inter-class variance maximum means that misclassification probability is minimum.
(3) image denoising
Choose linear structure element according to wheat leaf blade pore orientation self adaptation and carry out morphology opening operation, eliminate the impact of background noise.The arrangement of wheat leaf blade pore aligns mutually, and the process of adaptive detection pore orientation is as follows:
A. arranging horizontal direction is 0 degree of angular direction, and respectively to 0 °, 45 ° clockwise, 90 ° clockwise, 135 ° of four directions clockwise carry out row gray average statistics, obtain the gray average variance in each direction, the maximum direction of variance be image differentiate direction in advance；
B. carry out the opening operation of the linear structure element vertical with differentiating direction in advance according to the other direction of anticipation, eliminate tiny effect of noise；
C. direction is the image of 0 ° and 45 ° clockwise, seeks the abscissa average of the element that its each column is not zero, and carries out fitting a straight line, obtains the direction of accurate wheat leaf blade pore.Direction is the image of 90 ° and 135 ° clockwise, seeks the abscissa average of the element that its each row is not zero, and carries out fitting a straight line, obtains the direction of accurate wheat leaf blade pore；
D. carry out overall situation straight-line detection according to the direction of accurate wheat leaf blade pore, obtain meeting the parameter of all straight lines of wheat leaf blade pore orientation.
(4) connected region detection
Image segmentation result is carried out connected region detection, all connected regions detected are detected, be think hole area in fact when it meets stomatal parameters, obtain the positional information of Semen Tritici aestivi Stoma of Leaves in image.The parameter of pore includes the distance etc. of area, length-width ratio and the straight line from its nearest neighbours.
(5) statistics connected region quantity, obtains stomatal frequency
Finally statistics visual field inner air vent quantity, the actual size according to the Size calculation visual field that microscope is demarcated, obtain the stomatal frequency of reality.
The outstanding feature of the present invention is the process and the analysis that adopt the method for image procossing to replace manually carrying out micro-image.Image processing process is considered the impact of noise and background, the impact of most noise and background can be removed according to the method for the orientation of detection wheat leaf blade pore.The method that the present invention proposes has good robustness, and the accuracy that the micro-image gathered carries out density measure is higher.
Accompanying drawing explanation
Fig. 1 is the flow chart of the present invention.
Fig. 2 is the schematic diagram differentiating direction in advance.
Fig. 3 is the angle detecting process of wheat leaf blade pore arrangement.
Fig. 4 is the interpretation of result of the wheat leaf blade stomatal frequency that the present invention obtains.
Detailed description of the invention
The implementation process of the present invention is described in detail below in conjunction with embodiment and accompanying drawing.As shown in Figure 1, a kind of wheat leaf blade stomatal frequency measuring method based on micro-image, carry out as steps described below:
(1) read the image of digital microscope collection and carry out gray processing process
Consider that in the coloured image of wheat leaf blade, G component (green component) is higher, in order to isolate air cap preferably, the image gathered is carried out gray processing by the gray processing method adopting mixing, then by regular for gray value be double type in 0 to 1 scope, obtain the gray level image of wheat leaf blade.Fig. 4 (b) gives the design sketch obtained after the coloured image of collection carries out gray processing, Fig. 4 (a) is the design sketch that ordinary gamma method obtains, it can be seen that Fig. 4 (b) has targets improvement effect in contrast, it is easier to target is split.
The mathematical formulae that gray processing processes is as follows:
Wherein, T1And T2For the threshold value of segmentation, the red component of R, G, B respectively coloured image, green component and blue component.
(2) image segmentation
Adopt maximum variance between clusters that the image of gray processing is carried out binary conversion treatment, obtain image segmentation result.Maximum variance between clusters divides the image into background and target two parts by the gamma characteristic of image, inter-class variance between background and target is more big, illustrating that the two-part difference of pie graph picture is more big, therefore, the segmentation making inter-class variance maximum means that misclassification probability is minimum.
(3) image denoising
Choose linear structure element according to wheat leaf blade pore orientation self adaptation and carry out morphology opening operation, eliminate the impact of background noise.The arrangement of wheat leaf blade pore aligns mutually, and the process of adaptive detection pore orientation is as follows:
A. arranging horizontal direction is 0 degree of angular direction, and respectively to 0 °, 45 ° clockwise, 90 ° clockwise, 135 ° of four directions clockwise carry out row gray average statistics, obtain the gray average variance in each direction, the maximum direction of variance be image differentiate direction in advance.Accompanying drawing 2 is pre-differentiation direction schematic diagram, a1、a2、a3、a4Represent the direction of 0 °, 45 ° clockwise, 90 ° and 135 ° clockwise clockwise respectively；
B. carrying out the opening operation of the linear structure element vertical with differentiating direction in advance according to the other direction of anticipation, eliminate tiny effect of noise, Fig. 4 (c) gives the design sketch obtained after embodiment Fig. 4 (b) carries out morphology operations；
C. direction is the image of 0 ° and 45 ° clockwise, seeks the abscissa average of the element that its each column is not zero, and carries out fitting a straight line, obtains the direction of accurate wheat leaf blade pore.Direction is the image of 90 ° and 135 ° clockwise, seeks the abscissa average of the element that its each row is not zero, and carries out fitting a straight line, obtains the direction of accurate wheat leaf blade pore；
D. carrying out overall situation straight-line detection according to the direction of accurate wheat leaf blade pore, obtain meeting the parameter of all straight lines of wheat leaf blade pore orientation, in Fig. 3, black line is the design sketch that this embodiment carries out straight-line detection.
(4) connected region detection
Image segmentation result is carried out connected region detection, all connected regions detected are detected, be think hole area in fact when it meets stomatal parameters, obtain the positional information of Semen Tritici aestivi Stoma of Leaves in image.The parameter of pore includes the distance etc. of area, length-width ratio and the straight line from its nearest neighbours.Fig. 4 (d) gives the result of embodiment Fig. 4 (b) connected region detection, and black rectangle frame is the minimum enclosed rectangle of the connected region detected.
(5) statistics connected region quantity, obtains stomatal frequency
Finally statistics visual field inner air vent quantity, the actual size according to the Size calculation visual field that microscope is demarcated, obtain the stomatal frequency of reality, wherein the formula of stomatal frequency is as follows:
Claims (1)
1. the wheat leaf blade stomatal frequency measuring method based on micro-image, it is characterised in that carry out as steps described below:
(1) image acquisition and gray processing process
Using digital microscope to gather the image of wheat leaf blade pore, computer reads the image gathered and processes；Consider that in the coloured image of wheat leaf blade, G component is higher, in order to isolate air cap preferably, the image gathered is carried out gray processing by the gray processing method adopting mixing, then by regular for gray value be double(double-precision floating point type in 0 to 1 scope) type, obtain the gray level image of wheat leaf blade；
(2) image segmentation
Adopt maximum variance between clusters that the image of gray processing is carried out binary conversion treatment, obtain image segmentation result；Maximum variance between clusters divides the image into background and target two parts by the gamma characteristic of image, inter-class variance between background and target is more big, illustrating that the two-part difference of pie graph picture is more big, therefore, the segmentation making inter-class variance maximum means that misclassification probability is minimum；
(3) image denoising
Choose linear structure element according to wheat leaf blade pore orientation self adaptation and carry out morphology opening operation, eliminate the impact of background noise；The arrangement of wheat leaf blade pore aligns mutually, and the process of adaptive detection pore orientation is as follows:
A, to arrange horizontal direction be 0 degree of angular direction, and respectively to 0 °, 45 ° clockwise, 90 ° clockwise, 135 ° of four directions clockwise carry out row gray average statistics, obtain the gray average variance in each direction, the maximum direction of variance be image differentiate direction in advance；
B, carry out the opening operation of the linear structure element vertical with differentiating direction in advance according to the other direction of anticipation, eliminate tiny effect of noise；
C, direction are the image of 0 ° and 45 ° clockwise, seek the abscissa average of the element that its each column is not zero, and carry out fitting a straight line, obtain the direction of accurate wheat leaf blade pore；Direction is the image of 90 ° and 135 ° clockwise, seeks the abscissa average of the element that its each row is not zero, and carries out fitting a straight line, obtains the direction of accurate wheat leaf blade pore；
D, direction according to accurate wheat leaf blade pore carry out overall situation straight-line detection, obtain meeting the parameter of all straight lines of wheat leaf blade pore orientation；
(4) connected region detection
Image segmentation result is carried out connected region detection, all connected regions detected are detected, be think hole area in fact when it meets stomatal parameters, obtain the positional information of Semen Tritici aestivi Stoma of Leaves in image；The parameter of pore includes the distance etc. of area, length-width ratio and the straight line from its nearest neighbours；
(5) statistics connected region quantity, obtains stomatal frequency
Finally statistics visual field inner air vent quantity, the actual size according to the Size calculation visual field that microscope is demarcated, obtain the stomatal frequency of reality.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610085012.8A CN105761259B (en) | 2016-02-15 | 2016-02-15 | A kind of wheat leaf blade stomatal frequency measurement method based on micro-image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610085012.8A CN105761259B (en) | 2016-02-15 | 2016-02-15 | A kind of wheat leaf blade stomatal frequency measurement method based on micro-image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105761259A true CN105761259A (en) | 2016-07-13 |
| CN105761259B CN105761259B (en) | 2018-08-21 |
Family
ID=56330747
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610085012.8A Active CN105761259B (en) | 2016-02-15 | 2016-02-15 | A kind of wheat leaf blade stomatal frequency measurement method based on micro-image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105761259B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106886624A (en) * | 2016-12-27 | 2017-06-23 | 克康(上海)排气控制系统有限公司 | A kind of dividing plate number hole and the computational methods of opening area equivalent section hole count |
| CN106909906A (en) * | 2017-03-03 | 2017-06-30 | 河南科技学院 | A kind of wheat leaf blade stomatal frequency measuring method based on micro-image |
| CN110428401A (en) * | 2019-07-16 | 2019-11-08 | 南京农业大学 | A kind of measurement and analysis method of pears germ plasm resource phenotype fruit dot data |
| CN111860459A (en) * | 2020-08-05 | 2020-10-30 | 武汉理工大学 | Gramineous plant leaf stomata index measuring method based on microscopic image |
| CN112950700A (en) * | 2021-02-25 | 2021-06-11 | 安徽农业大学 | Plant leaf stomatal conductance measuring method based on deep learning and image processing |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101807252A (en) * | 2010-03-24 | 2010-08-18 | 中国农业大学 | Crop row center line extraction method and system |
| CN102221347A (en) * | 2011-03-29 | 2011-10-19 | 中国计量学院 | Three-dimension microscopic observation method of plant leaf stoma in vivo |
| CN104992439A (en) * | 2015-06-26 | 2015-10-21 | 广州铁路职业技术学院 | Device and method for detecting insect pests of leaves of crops |
-
2016
- 2016-02-15 CN CN201610085012.8A patent/CN105761259B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101807252A (en) * | 2010-03-24 | 2010-08-18 | 中国农业大学 | Crop row center line extraction method and system |
| CN102221347A (en) * | 2011-03-29 | 2011-10-19 | 中国计量学院 | Three-dimension microscopic observation method of plant leaf stoma in vivo |
| CN104992439A (en) * | 2015-06-26 | 2015-10-21 | 广州铁路职业技术学院 | Device and method for detecting insect pests of leaves of crops |
Non-Patent Citations (6)
| Title |
|---|
| ALISTAIR M. HETHERINGTON1 ET AL: "The role of stomata in sensing and driving environmental change", 《NATURE》 * |
| I.TARI: "Abaxial and adaxial stomatal density,stomatal conductances and water status of bean primary leaves as affected by paclobutrazol", 《BIOLOGIA PLANTARUM》 * |
| ZHENZHU XU ET AL: "Responses of leaf stomatal density to water status and its relationship with photosynthesis in a grass", 《JOURNAL OF EXPERIMENTAL BOTANY》 * |
| 王曙光 等: "小麦叶片气孔性状与产量和抗旱性的关系", 《应用生态学报》 * |
| 罗春梅: "几种无机元素及植物生长调节剂对小麦叶片气孔分化及密度的影响", 《植物生理学学讯》 * |
| 茹振钢 等: "黄淮麦区小麦品种的高产潜力与实现途径", 《中国农业科学》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106886624A (en) * | 2016-12-27 | 2017-06-23 | 克康(上海)排气控制系统有限公司 | A kind of dividing plate number hole and the computational methods of opening area equivalent section hole count |
| CN106909906A (en) * | 2017-03-03 | 2017-06-30 | 河南科技学院 | A kind of wheat leaf blade stomatal frequency measuring method based on micro-image |
| CN110428401A (en) * | 2019-07-16 | 2019-11-08 | 南京农业大学 | A kind of measurement and analysis method of pears germ plasm resource phenotype fruit dot data |
| CN111860459A (en) * | 2020-08-05 | 2020-10-30 | 武汉理工大学 | Gramineous plant leaf stomata index measuring method based on microscopic image |
| CN111860459B (en) * | 2020-08-05 | 2024-02-20 | 武汉理工大学 | Gramineae plant leaf pore index measurement method based on microscopic image |
| CN112950700A (en) * | 2021-02-25 | 2021-06-11 | 安徽农业大学 | Plant leaf stomatal conductance measuring method based on deep learning and image processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105761259B (en) | 2018-08-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105761259A (en) | Wheat leaf stoma density measurement method based on microscopic image | |
| CN108985260B (en) | Remote sensing and meteorological integrated rice yield estimation method | |
| CN109447945B (en) | Quick counting method for basic wheat seedlings based on machine vision and graphic processing | |
| CN112699876B (en) | Automatic reading method for various meters of gas collecting station | |
| Chen et al. | Diagnosing of rice nitrogen stress based on static scanning technology and image information extraction | |
| CN102855485B (en) | The automatic testing method of one grow wheat heading | |
| CN112819846B (en) | Multi-load remote sensing image-based rice yield estimation method for cloudy and rainy areas | |
| Hu et al. | Coupling of machine learning methods to improve estimation of ground coverage from unmanned aerial vehicle (UAV) imagery for high-throughput phenotyping of crops | |
| Liu et al. | Estimating maize seedling number with UAV RGB images and advanced image processing methods | |
| CN110188657A (en) | Corn arid recognition methods based on crimping blade detection | |
| CN112861712B (en) | Agricultural pest and disease monitoring method based on artificial intelligence and multi-temporal remote sensing | |
| Li et al. | Comparison of deep learning methods for detecting and counting sorghum heads in UAV imagery | |
| CN111967441A (en) | Crop disease analysis method based on deep learning | |
| Long et al. | Row and water front detection from UAV thermal-infrared imagery for furrow irrigation monitoring | |
| CN107818565B (en) | Method for investigating quantity of wheat seedlings in one-to-three-leaf period of wheat | |
| Yang et al. | Unmanned aerial vehicle-scale weed segmentation method based on image analysis technology for enhanced accuracy of maize seedling counting | |
| Chen et al. | Identifying of rice phosphorus stress based on machine vision technology | |
| CN112488230A (en) | Crop water stress degree judging method and device based on machine learning | |
| CN112950700B (en) | Plant leaf stomatal conductance measuring method based on deep learning and image processing | |
| Feng et al. | Calculating the leaf-area based on non-loss correction algorithm | |
| CN111968075B (en) | Hyperspectrum-based plant maturity detection system and method | |
| CN111860038B (en) | Crop front end recognition device and method | |
| Wu et al. | Field crop extraction based on machine vision | |
| CN111886982A (en) | Real-time detection system and detection method for dry land planting operation quality | |
| Fan et al. | Method of Prediction on Vegetables Maturity Based on Kalman Filtering Fusion and Improved Neural Network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |