CN116739968A - Corn leaf vein detection method, system and equipment - Google Patents
Corn leaf vein detection method, system and equipment Download PDFInfo
- Publication number
- CN116739968A CN116739968A CN202310206849.3A CN202310206849A CN116739968A CN 116739968 A CN116739968 A CN 116739968A CN 202310206849 A CN202310206849 A CN 202310206849A CN 116739968 A CN116739968 A CN 116739968A
- Authority
- CN
- China
- Prior art keywords
- corn
- image
- gray
- detected
- veins
- 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
Links
- 240000008042 Zea mays Species 0.000 title claims abstract description 128
- 235000002017 Zea mays subsp mays Nutrition 0.000 title claims abstract description 128
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 title claims abstract description 127
- 235000005822 corn Nutrition 0.000 title claims abstract description 127
- 210000003462 vein Anatomy 0.000 title claims abstract description 101
- 238000001514 detection method Methods 0.000 title claims abstract description 51
- 238000000034 method Methods 0.000 claims description 31
- 230000011218 segmentation Effects 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 208000003643 Callosities Diseases 0.000 claims description 3
- 206010020649 Hyperkeratosis Diseases 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 241001057636 Dracaena deremensis Species 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 238000011160 research Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 235000016383 Zea mays subsp huehuetenangensis Nutrition 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 235000009973 maize Nutrition 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
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
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- 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
- G06T2207/10024—Color 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
- G06T2207/20112—Image segmentation details
- G06T2207/20164—Salient point detection; Corner detection
-
- 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
- G06T2207/30172—Centreline of tubular or elongated structure
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Spectrometry And Color Measurement (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a corn leaf vein detection method, a corn leaf vein detection system and corn leaf vein detection equipment, wherein the corn leaf vein detection method comprises the steps of obtaining a color image of corn to be detected; gray scale and binarization processing are carried out on the color image; and determining the veins of the corn to be detected according to the gray level and the binarized image. The invention can improve the precision and speed of corn leaf vein detection.
Description
Technical Field
The invention relates to the field of automatic detection of corn leaf veins, in particular to a corn leaf vein detection method, a corn leaf vein detection system and corn leaf vein detection equipment.
Background
At present, the research of corn leaf veins is carried out by detecting crop leaf veins by applying two-dimensional color image information or detecting leaf veins by applying three-dimensional laser scanning point cloud data. The two-dimensional color image of the crop contains information such as pixels, colors, textures, gray values and the like of the crop; the three-dimensional point cloud data of the crops comprise laser reflection intensity of the crops, three-dimensional space point coordinate information and the like; by utilizing the specificity and distribution characteristics contained in the information of the crops, the automatic detection of the veins of the crops can be realized. However, in the process of actually acquiring the three-dimensional point cloud data of the crops, some non-hollow data are lost, so that the detection of the leaf vein information of the crops is incomplete. The extraction of the leaf area of the crop can be better realized by utilizing the color information of the crop, and then the global leaf vein of the crop is obtained, so that the detection of the leaf vein of the crop based on the color image is always a research hot spot.
Crop veins are automatically detected based on color images, and the crop veins are detected by detecting pixel areas where pixel gray values in the images jump and utilizing the extracted vein edge information. However, it is often difficult to achieve satisfactory results for images with smooth variation in the gray level of the vein pixels. Part of the study transformed the color image of the crop vein into the HIS (Hue, saturation) color space, then enhanced the image of one of the color components, and then detected the crop vein by binarization processing. However, under the condition of low resolution of the vein picture, the method is difficult to accurately and completely detect the vein. With the continuous development of the neural network, partial researches propose a crop vein extraction method based on the neural network, effective information in an image is automatically extracted by continuously learning and self-optimizing by means of the existing graphic features, and a good detection effect can be finally obtained. However, this method is relatively time-complex and requires a large amount of calculation time.
Disclosure of Invention
The invention aims to provide a corn leaf vein detection method, a corn leaf vein detection system and corn leaf vein detection equipment, which can improve the precision and the speed of corn leaf vein detection.
In order to achieve the above object, the present invention provides the following solutions:
a method for detecting corn veins, comprising:
acquiring a color image of corn to be detected;
gray scale and binarization processing are carried out on the color image;
and determining the veins of the corn to be detected according to the gray level and the binarized image.
Optionally, the gray scale and binarization processing on the color image specifically includes:
determining a first gray image according to the S component of the color image in the HSV color space;
determining a second gray level image and a third gray level image according to the components of the color image in the RGB color space;
performing segmentation processing of a segmentation threshold on the first gray level image to determine a first binary image;
and dividing the second gray level image by adopting a maximum inter-class variance method, and determining a second binary image.
Optionally, the determining the second gray level image and the third gray level image according to the components of the color image in the RGB color space specifically includes:
using formula I gray2 (i, j) =g (i, j) 1.262-R (i, j) 0.884-B (i, j) 0.311, determining a second gray scale image;
using formula I gray3 (i, j) =g (i, j) 0.587+r (i, j) 0.299+b (i, j) 0.114, a third gray scale image is determined;
where I, j are the row and column coordinates of the pixel, G (I, j), R (I, j) and B (I, j) are the gray values of the color component of pixel G, R, B at color image (I, j), respectively, I gray2 (I, j) is the gray value of the pixel at (I, j) of the converted second gray image, I gray3 (i, j) is the gray value of the pixel at (i, j) of the converted third gray image.
Optionally, the dividing the second gray level image by using a maximum inter-class variance method to determine a second binary image, and then further includes:
and denoising the second binary image.
Optionally, the determining the veins of the corn to be detected according to the gray level and the binarized image specifically comprises:
acquiring centroids of all pixel points with gray values of 1 in the first binary image, and taking the centroids as center points of corns to be detected;
determining the minimum convex polygon surrounding the corn to be detected by adopting a convex hull algorithm according to the second binary image, and obtaining each vertex of the convex polygon;
the maximum value of the distances between the center point and each vertex is the maximum distance from the center point of the corn to be detected to the blade;
performing logical AND operation according to the second binary image and the third gray level image to determine a fourth gray level image;
and carrying out circular scanning by taking the central point as the center of a circle according to the fourth gray level image of the corn to be detected, searching pixel points of the leaf veins of the corn to be detected, and determining the leaf veins of the corn to be detected.
Optionally, according to the fourth gray level image of the corn to be detected, circular scanning is performed with the center point as the center of a circle, and pixel points of the leaf veins of the corn to be detected are searched to determine the leaf veins of the corn to be detected, which specifically includes:
scanning the fourth gray level image clockwise by taking the center point as the center of a circle; setting an initial radius of scanning and the number of pixel points which are increased in each scanning, wherein the maximum radius of scanning is the maximum distance from a central point to a blade;
dividing the circular pixel point into a plurality of areas by using a pixel point with a gray value of 0 in the circular pixel point;
reserving the pixel point with the maximum gray value in each region; and is used as potential pixel points of the leaf veins of the corn to be detected;
and clustering potential pixel points of the leaf veins of the corn to be detected by adopting a DBSCAN algorithm based on density clustering, so as to realize the detection of the corn leaf veins.
A corn vein detection system comprising:
the color image acquisition module is used for acquiring a color image of corn to be detected;
the image processing module is used for carrying out gray scale and binarization processing on the color image;
and the leaf vein detection module is used for determining the leaf vein of the corn to be detected according to the gray level and the binarized image.
A corn vein detection apparatus comprising: at least one processor, at least one memory, and computer program instructions stored in the memory, which when executed by the processor, implement the method.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
according to the corn leaf vein detection method, system and equipment provided by the invention, the leaf veins of the corn to be detected are determined according to the gray level and the binarized image, so that the influence of irrelevant components such as background and leaf noise can be effectively eliminated, and the precision and speed of corn leaf vein detection are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for detecting corn veins;
FIG. 2 is a flow chart of a method for detecting corn veins according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a first gray scale image (gray scale image 1), a second gray scale image (gray scale image 2) and a third gray scale image (gray scale image 3) of a corn plant according to a corn leaf vein detection method of an embodiment of the present invention;
FIG. 4 is a first two-value image of a majority of pixels in a center region of a corn plant according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a second binary image extracted from a corn region after removing scattered noise in a corn vein detection method according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a minimum convex polygon surrounding corn calculated in a corn vein detection method according to an embodiment of the present invention;
fig. 7 is a schematic diagram of a fourth gray image extracted from a gray region of corn according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of a scan of circular pixels of corn in a method for detecting a corn vein according to an embodiment of the present invention;
FIG. 9 is a schematic diagram showing gray scale statistics of pixels in a corn region at a specified circular scan radius in a corn vein detection method according to an embodiment of the present invention;
FIG. 10 is a schematic diagram showing the initial detection result of the corn leaf vein in the corn leaf vein detection method according to the embodiment of the invention;
fig. 11 is a schematic diagram of the optimized corn vein detection result in the corn vein detection method according to an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention aims to provide a corn leaf vein detection method, a corn leaf vein detection system and corn leaf vein detection equipment, which can improve the precision and the speed of corn leaf vein detection.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
As shown in FIG. 1, the corn vein detection method provided by the invention comprises the following steps:
s101, acquiring a color image of corn to be detected;
s102, gray scale and binarization processing are carried out on the color image;
s102 specifically comprises the following steps:
s201, determining a first gray level image according to an S component of the color image in an HSV color space;
s202, determining a second gray level image and a third gray level image according to components of the color image in an RGB color space;
s202 specifically comprises:
using formula I gray2 (i, j) =g (i, j) 1.262-R (i, j) 0.884-B (i, j) 0.311, determining a second gray scale image;
using formula I gray3 (i, j) =g (i, j) 0.587+r (i, j) 0.299+b (i, j) 0.114, a third gray scale image is determined;
where I, j are the row and column coordinates of the pixel, G (I, j), R (I, j) and B (I, j) are the gray values of the color component of pixel G, R, B at color image (I, j), respectively, I gray2 (I, j) is the gray value of the pixel at (I, j) of the converted second gray image, I gray3 (i, j) is the gray value of the pixel at (i, j) of the converted third gray image.
As shown in fig. 2, as a specific embodiment, the method can effectively eliminate the influence of irrelevant components such as background and leaf noise and the like, and improve the precision and speed of corn vein detection. The method specifically comprises the following steps.
And adjusting the direction and the position of the color camera to enable the camera to shoot corn plants vertically from top to bottom, and acquiring color images of single corn plants.
In the color image RGB color space of corn, the gray value of the S component of the corn plant in the HSV color space is calculated by utilizing the gray values of the red (R), green (G) and blue (B) components, and the gray image 1 of the corn plant is obtained.
And (3) applying components of the corn color image in the RGB color space, and carrying out graying treatment on the original color image of the corn to obtain a gray image 2 and a gray image 3 of the corn.
S203, carrying out segmentation processing of a segmentation threshold on the first gray level image to determine a first binary image; segmentation threshold th=0.95.
S204, dividing the second gray level image by adopting a maximum inter-class variance method, and determining a second binary image.
Also included after S204 is:
and denoising the second binary image.
The denoising process comprises the following steps: the morphological "closing operation" is used to remove the interference of scattered point noise in the second binary image (binary image 2).
S103, determining the leaf veins of the corn to be detected according to the gray level and the binarized image.
S103 specifically comprises the following steps:
s301, the mass centers of all pixel points with gray values of 1 in the first binary image are obtained and used as center points of corns to be detected; the white pixel points are the pixel points in the central area of the corn plant, the gray value is 1, the black pixel points are the background, and the gray value is 0. And the white pixel point in the second binary image is a corn plant, the gray value is 1, the black pixel point is a background, and the gray value is 0.
S302, determining the minimum convex polygon surrounding the corn to be detected by adopting a convex hull algorithm according to the second binary image, and obtaining each vertex of the convex polygon;
s303, taking the maximum value of the distance between the central point and each vertex as the maximum distance between the central point of the corn to be detected and the blade;
s304, performing logical AND operation according to the second binary image and the third gray level image to determine a fourth gray level image; the black part is a non-corn area, and the gray value of the pixel point is 0.
S305, carrying out circular scanning by taking the central point as the center of a circle according to the fourth gray level image of the corn to be detected, searching pixel points of the leaf veins of the corn to be detected, and determining the leaf veins of the corn to be detected.
S305 specifically includes:
s501, scanning a fourth gray level image clockwise by taking a central point as a circle center; setting an initial radius of scanning and the number of pixel points which are increased in each scanning, wherein the maximum radius of scanning is the maximum distance from a central point to a blade;
s502, dividing the circular pixel point into a plurality of areas by using a pixel point with a gray value of 0 in the circular pixel point;
s503, reserving the pixel point with the maximum gray value in each region; and is used as potential pixel points of the leaf veins of the corn to be detected;
s504, clustering potential pixel points of the corn leaf veins to be detected by adopting a DBSCAN algorithm based on density clustering, reserving classes containing pixel points with the number larger than a threshold value, and finally realizing the detection of the corn leaf veins.
In another embodiment of the present invention, a method for detecting a corn vein is provided. Corn is used as a research object, and corn leaf vein detection is realized by utilizing a color image of corn in a field environment.
The color image collected in this embodiment only includes a single corn plant, and the gray level conversion is performed on the color image to obtain a gray level image 1, a gray level image 2, and a gray level image 3, as shown in fig. 3. The corn gray image 1 is subjected to segmentation processing, a segmentation threshold th=0.95 is set, and a binary image 1 of corn is obtained, and as shown in fig. 4, white pixels are most of pixels in the central area of corn plants. And (3) calculating the mass centers of all pixel points with gray values of 1 in the corn binary image 1, and taking the mass centers as the center points of the corn.
And calculating the segmentation threshold value of the corn gray image 2 to be 0.53 by using a maximum inter-class variance method, obtaining a binary image 2 of the gray image 2, wherein white part pixels are corn plants, and black part pixels are backgrounds, so that the extraction of corn areas is realized. In this embodiment, the square structural element is used to perform a closing operation on the binary image 2, wherein the square structural element with a side length of 5 pixels is used to perform an expansion operation on the image, and then the square structural element with a side length of 12 pixels is used to perform a corrosion operation on the image, so as to eliminate the interference of scattered point noise, and the result is shown in fig. 5.
The processed corn binary image 2 is used for calculating the minimum convex polygon surrounding the corn by adopting a convex hull algorithm, and the result is shown in fig. 6, so that each vertex of the convex polygon is obtained.
And calculating the distance between the positioned corn center point and each vertex of the convex polygon, and selecting the maximum value as the maximum distance between the corn center point and the blade, namely 245 pixel points in the embodiment.
The corn gray image 3 and the processed binary image 2 are subjected to logical AND operation to generate a new gray image 4, and as shown in fig. 7, the gray values of pixels in the corn area are reserved, and the gray value of pixels in the non-corn area is 0.
The located corn center point is used as a circle center, the gray image 4 is scanned clockwise, the initial radius of the circular scanning is set to be 50 th pixel point from the circle center, 3 pixel points are increased in each scanning, and the maximum radius of the circular scanning is 245 pixel points with the maximum distance from the obtained corn center point to the corn leaf convex polygon.
Fig. 8 is a schematic view of circular scanning at a specified radius of 100 pixels. The pixel points with the gray value of 0 in the circular pixel points divide the circular pixel points into four areas, the statistical result of the gray values of the corresponding circular scanning pixels is shown in fig. 9, the abscissa represents the sorting of the pixel points scanned in the circular scanning process, and the ordinate represents the gray values of the pixel points. In this embodiment, the threshold is set to 12 pixels, and the blade with too small detection width is removed by setting the threshold, and the gray values of three regions with pixel width greater than 12 are finally reserved in four regions in fig. 9.
And detecting the gray values of the reserved corn areas under all the circular scanning radiuses, and reserving the pixel points with the maximum gray values in each area as potential pixel points of corn veins under each circular scanning radius. The maize veins potential pixels are marked with asterisks as shown in figure 10.
As can be seen from fig. 10, the initial detection result includes some noise points of non-veins, and the potential pixel points of the corn veins are clustered by using a DBSCAN algorithm based on density clustering, so that the potential pixel points are classified into 17 classes. And counting the number of 17 kinds of pixel points obtained by clustering. In this embodiment, classes with the number of pixels greater than 20 remain, and the result is shown in the asterisk marked pixels in fig. 11, so as to finally realize detection of corn leaf veins.
As another specific embodiment, the present invention also provides a corn vein detection system, including:
the color image acquisition module is used for acquiring a color image of corn to be detected;
the image processing module is used for carrying out gray scale and binarization processing on the color image;
and the leaf vein detection module is used for determining the leaf vein of the corn to be detected according to the gray level and the binarized image.
In order to execute the method corresponding to the embodiment to achieve the corresponding functions and technical effects, the invention also provides a corn vein detection device, which comprises: at least one processor, at least one memory, and computer program instructions stored in the memory, which when executed by the processor, implement the method.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.
Claims (8)
1. A method for detecting corn veins, comprising:
acquiring a color image of corn to be detected;
gray scale and binarization processing are carried out on the color image;
and determining the veins of the corn to be detected according to the gray level and the binarized image.
2. The method for detecting corn veins according to claim 1, wherein said performing gray scale and binarization processing on said color image specifically comprises:
determining a first gray image according to the S component of the color image in the HSV color space;
determining a second gray level image and a third gray level image according to the components of the color image in the RGB color space;
performing segmentation processing of a segmentation threshold on the first gray level image to determine a first binary image;
and dividing the second gray level image by adopting a maximum inter-class variance method, and determining a second binary image.
3. The method for detecting corn veins according to claim 2, wherein determining the second gray level image and the third gray level image according to the components of the color image in the RGB color space specifically comprises:
using formula I gray2 (i, j) =g (i, j) 1.262-R (i, j) 0.884-B (i, j) 0.311, determining a second gray scale image;
using formula I gray3 (i, j) =g (i, j) 0.587+r (i, j) 0.299+b (i, j) 0.114, a third gray scale image is determined;
where I, j are the row and column coordinates of the pixel, G (I, j), R (I, j) and B (I, j) are the gray values of the color component of pixel G, R, B at color image (I, j), respectively, I gray2 (I, j) is the gray value of the pixel at (I, j) of the converted second gray image, I gray3 (i, j) is the gray value of the pixel at (i, j) of the converted third gray image.
4. The method of claim 2, wherein the dividing the second gray level image by using a maximum inter-class variance method to determine a second binary image, and further comprising:
and denoising the second binary image.
5. The method for detecting corn veins according to claim 2, wherein determining the veins of the corn to be detected based on the gray scale and binarized image specifically comprises:
acquiring centroids of all pixel points with gray values of 1 in the first binary image, and taking the centroids as center points of corns to be detected;
determining the minimum convex polygon surrounding the corn to be detected by adopting a convex hull algorithm according to the second binary image, and obtaining each vertex of the convex polygon;
the maximum value of the distances between the center point and each vertex is the maximum distance from the center point of the corn to be detected to the blade;
performing logical AND operation according to the second binary image and the third gray level image to determine a fourth gray level image;
and carrying out circular scanning by taking the central point as the center of a circle according to the fourth gray level image of the corn to be detected, searching pixel points of the leaf veins of the corn to be detected, and determining the leaf veins of the corn to be detected.
6. The method for detecting corn veins according to claim 5, wherein the circular scanning is performed with a center point as a center point according to the fourth gray level image of the corn to be detected, the pixel points of the corn veins to be detected are searched, and the corn veins to be detected are determined, specifically including:
scanning the fourth gray level image clockwise by taking the center point as the center of a circle; setting an initial radius of scanning and the number of pixel points which are increased in each scanning, wherein the maximum radius of scanning is the maximum distance from a central point to a blade;
dividing the circular pixel point into a plurality of areas by using a pixel point with a gray value of 0 in the circular pixel point;
reserving the pixel point with the maximum gray value in each region; and is used as potential pixel points of the leaf veins of the corn to be detected;
and clustering potential pixel points of the leaf veins of the corn to be detected by adopting a DBSCAN algorithm based on density clustering, so as to realize the detection of the corn leaf veins.
7. A corn leaf vein detection system, comprising:
the color image acquisition module is used for acquiring a color image of corn to be detected;
the image processing module is used for carrying out gray scale and binarization processing on the color image;
and the leaf vein detection module is used for determining the leaf vein of the corn to be detected according to the gray level and the binarized image.
8. A corn leaf vein detection apparatus, comprising: at least one processor, at least one memory, and computer program instructions stored in the memory, which when executed by the processor, implement the method of any one of claims 1-6.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310206849.3A CN116739968A (en) | 2023-03-07 | 2023-03-07 | Corn leaf vein detection method, system and equipment |
| NL2036042A NL2036042A (en) | 2023-03-07 | 2023-10-14 | Method, system and apparatus for detecting leaf vein of corn |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310206849.3A CN116739968A (en) | 2023-03-07 | 2023-03-07 | Corn leaf vein detection method, system and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116739968A true CN116739968A (en) | 2023-09-12 |
Family
ID=87915776
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310206849.3A Pending CN116739968A (en) | 2023-03-07 | 2023-03-07 | Corn leaf vein detection method, system and equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN116739968A (en) |
| NL (1) | NL2036042A (en) |
-
2023
- 2023-03-07 CN CN202310206849.3A patent/CN116739968A/en active Pending
- 2023-10-14 NL NL2036042A patent/NL2036042A/en unknown
Also Published As
| Publication number | Publication date |
|---|---|
| NL2036042A (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108121991B (en) | Deep learning ship target detection method based on edge candidate region extraction | |
| US8340420B2 (en) | Method for recognizing objects in images | |
| CN109165538B (en) | Bar code detection method and device based on deep neural network | |
| CN107784669A (en) | A kind of method that hot spot extraction and its barycenter determine | |
| CN111046880A (en) | Infrared target image segmentation method and system, electronic device and storage medium | |
| CN108960011B (en) | Partially-shielded citrus fruit image identification method | |
| CN111915704A (en) | Apple hierarchical identification method based on deep learning | |
| CN109800619B (en) | Image recognition method for citrus fruits in mature period | |
| CN107220647B (en) | Crop center point positioning method and system under blade crossing condition | |
| CN111695373B (en) | Zebra stripes positioning method, system, medium and equipment | |
| CN111382658B (en) | Road traffic sign detection method in natural environment based on image gray gradient consistency | |
| CN111161281A (en) | Face region identification method and device and storage medium | |
| CN113780110A (en) | Method and device for detecting weak and small targets in image sequence in real time | |
| CN111353992B (en) | Agricultural product defect detection method and system based on textural features | |
| CN110363103B (en) | Insect pest identification method and device, computer equipment and storage medium | |
| CN109190452B (en) | Crop row identification method and device | |
| CN116596921B (en) | Method and system for sorting incinerator slag | |
| WO2024016632A1 (en) | Bright spot location method, bright spot location apparatus, electronic device and storage medium | |
| CN114445814B (en) | Character region extraction method and computer-readable storage medium | |
| CN116739968A (en) | Corn leaf vein detection method, system and equipment | |
| CN111027560B (en) | Text detection method and related device | |
| Khan et al. | Segmentation of single and overlapping leaves by extracting appropriate contours | |
| CN115187744A (en) | Cabinet identification method based on laser point cloud | |
| CN110570437B (en) | Electric power channel automatic inspection data processing method based on boundary identification | |
| CN113537253A (en) | Infrared image target detection method and device, computing equipment 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 |