CN114581660A - Plant leaf segmentation identification method and system - Google Patents
Plant leaf segmentation identification method and system Download PDFInfo
- Publication number
- CN114581660A CN114581660A CN202210072808.5A CN202210072808A CN114581660A CN 114581660 A CN114581660 A CN 114581660A CN 202210072808 A CN202210072808 A CN 202210072808A CN 114581660 A CN114581660 A CN 114581660A
- Authority
- CN
- China
- Prior art keywords
- image
- plant
- leaf
- area
- plant leaf
- 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
- 230000011218 segmentation Effects 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 44
- 239000002689 soil Substances 0.000 claims abstract description 18
- 230000000877 morphologic effect Effects 0.000 claims abstract description 16
- 238000009499 grossing Methods 0.000 claims abstract description 11
- 238000000605 extraction Methods 0.000 claims abstract description 9
- 238000004590 computer program Methods 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 5
- 238000000926 separation method Methods 0.000 claims description 4
- 239000003086 colorant Substances 0.000 claims description 3
- 230000007797 corrosion Effects 0.000 claims description 2
- 238000005260 corrosion Methods 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 abstract description 3
- 241000196324 Embryophyta Species 0.000 description 73
- 229920000742 Cotton Polymers 0.000 description 9
- 241000219146 Gossypium Species 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 241000238631 Hexapoda Species 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 241000607479 Yersinia pestis Species 0.000 description 4
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 230000003628 erosive effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 240000002024 Gossypium herbaceum Species 0.000 description 1
- 235000004341 Gossypium herbaceum Nutrition 0.000 description 1
- 206010042496 Sunburn Diseases 0.000 description 1
- 241001464837 Viridiplantae Species 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 239000004463 hay Substances 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002362 mulch Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000004383 yellowing Methods 0.000 description 1
Images
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-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
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- 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
- G06T2207/20036—Morphological image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geometry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a plant leaf segmentation identification method and a plant leaf segmentation identification system, which belong to the technical field of computer vision, and are used for separating a soil background from a plant leaf image to be segmented based on a color index and extracting a green part in the image; separating a non-blade part based on morphological opening operation, and smoothing the edge of a blade area; according to the area of the communicated region, setting a threshold value to remove interference factors of non-plant parts in the smoothed image; and filling the image holes to obtain a complete plant leaf area after segmentation. The invention effectively removes the noise caused in the image acquisition process; the color characteristics of the foreground and the background are effectively distinguished; the vegetation extraction color index divides the image into two types of green vegetation and background, and the morphological opening operation separates the leaf and stem, the trunk and the smooth leaf edge; interference factors in backgrounds such as hay and covering can be removed through the area of the communication area; the problem of incomplete blade segmentation is considered, the segmented blades are filled, and the complete blades are accurately and effectively extracted.
Description
Technical Field
The invention relates to the technical field of computer vision, in particular to a plant leaf segmentation and identification method and system.
Background
Cotton is one of the most important crops in the world, and has the characteristics of large yield, wide distribution, wide application and the like. The cotton planting has important functions in adjusting agricultural production structure and guaranteeing the income of farmers. However, the cotton is easily affected by various plant diseases and insect pests in the growth process, and prevention in advance and timely treatment are the basis for ensuring cotton production.
The leaf information is the direct reflection of the growth condition of crops, and the cotton diseases and insect pests, the growth condition and the like can be effectively identified and judged by using an image processing method and a computer vision technology. The image segmentation is the first step of image processing and analysis and is also the most critical step, and the quality of the segmentation result directly influences the accuracy of subsequent feature extraction and target identification.
In natural scenes, the segmentation of cotton leaves can encounter many challenges. For example, the illumination intensity varies rapidly during the day, and different weather conditions can have some effect on the imaging. While the background of the image also includes soil, hay, mulch, shadows, etc. The existence of complex background increases the difficulty of blade image segmentation.
Disclosure of Invention
The invention aims to provide a method and a system for efficiently and accurately identifying plant leaf segmentation, so as to solve at least one technical problem in the background technology.
In order to achieve the purpose, the invention adopts the following technical scheme:
in one aspect, the present invention provides a plant leaf segmentation and identification method, including:
acquiring an image of a plant leaf to be segmented;
separating a soil background from the plant leaf image to be segmented based on the color index, and extracting a green part in the image;
separating the non-leaf part of the plant in the image with the green part extracted based on morphological opening operation, and smoothing the edge of the leaf area; according to the area of the communicated region, setting a threshold value to remove interference factors of non-plant parts in the smoothed image;
and filling image holes in the image without the interference factors of the non-plant part to obtain a complete plant leaf area after segmentation.
Optionally, before separating the soil background based on the color index, the plant leaf image to be segmented is preprocessed, including: removing noise of R, G, B color channels of the image through Gaussian filtering, and simultaneously performing histogram equalization processing on a G channel to enhance the contrast of a green part; and combining the processed gray level images of the three channels to obtain a preprocessed image.
Optionally, filling an image hole in the image without the interference factors of the non-plant part, including:
checking all background regions of the whole binary image, if the periphery of the background region is classified into leaves, namely a central hole region, considering that the background region is influenced by colors and cannot be correctly segmented, and resetting the background region as a leaf region;
and traversing all pixels for the incomplete part of the blade edge, checking a grid area with a preset size taking each pixel as a center, and if the area of the classified blade part is larger than half of the area of the grid area, determining that the pixel belongs to the blade.
Optionally, the green vegetation is extracted based on the color index CIVE, which is specifically defined as follows:
CIVE＝0.441R-0.811G+0.385B+18.74745；
wherein R, G, B are the channel component values of the preprocessed color image, respectively.
Optionally, the morphological opening operation includes performing erosion operation on the image, and then performing expansion operation on the eroded image, so as to smooth the contour of the object and eliminate the slender protrusion.
Optionally, according to the area of the connected region, setting a threshold to remove non-plant part interference factors in the smoothed image, and obtaining a segmented plant leaf region, including: and removing the object with the area of the connected region smaller than the preset pixel threshold value by means of the smoothed binary image of the image.
In a second aspect, the present invention provides a plant leaf segmentation identification system, comprising:
the acquisition module is used for acquiring an image of a plant leaf to be segmented;
the extraction module is used for separating a soil background from the plant leaf image to be segmented based on the color index and extracting a green part in the image;
the separation module is used for separating the non-leaf part of the plant in the image with the green part extracted and smoothing the edge of the leaf area based on morphological opening operation; according to the area of the communicated region, setting a threshold value to remove interference factors of non-plant parts in the smoothed image;
and the filling module is used for filling image holes in the image without the interference factors of the non-plant parts to obtain a complete plant leaf area after segmentation.
In a third aspect, the invention provides a non-transitory computer readable storage medium for storing computer instructions which, when executed by a processor, implement a plant leaf segmentation identification method as described above.
In a fourth aspect, the present invention provides a computer program product comprising a computer program for implementing a plant leaf segmentation identification method as described above when run on one or more processors.
In a fifth aspect, the present invention provides an electronic device, comprising: a processor, a memory, and a computer program; wherein a processor is connected with the memory, the computer program is stored in the memory, and when the electronic device runs, the processor executes the computer program stored in the memory, so that the electronic device executes the instructions for implementing the plant leaf segmentation identification method.
The invention has the beneficial effects that: noise caused in the image acquisition process is effectively removed; the color characteristics of the foreground and the background are effectively distinguished; the vegetation extraction color index divides the image into two types of green vegetation and background, and the morphological opening operation separates the leaf and stem, the trunk and the smooth leaf edge; interference factors in backgrounds such as hay and covering can be removed through the area of the communication area; in addition, the problem of incomplete blade segmentation caused by leaf blight, insect damage and the like is fully considered, the segmented blades are filled, and the complete blades can be effectively extracted.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a plant leaf segmentation and identification method according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below by way of the drawings are illustrative only and are not to be construed as limiting the invention.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
For the purpose of facilitating an understanding of the present invention, the present invention will be further explained by way of specific embodiments with reference to the accompanying drawings, which are not intended to limit the present invention.
It should be understood by those skilled in the art that the drawings are merely schematic representations of embodiments and that the elements shown in the drawings are not necessarily required to practice the invention.
Example 1
This embodiment 1 provides a plant leaf segmentation identification system, and this system includes:
the acquisition module is used for acquiring an image of a plant leaf to be segmented;
the extraction module is used for separating a soil background from the plant leaf image to be segmented based on the color index and extracting a green part in the image;
the separation module is used for separating and extracting non-leaf parts of plants in the images of the green parts based on morphological opening operation and smoothing the edges of leaf areas; according to the area of the communicated region, setting a threshold value to remove interference factors of non-plant parts in the smoothed image;
and the filling module is used for filling image holes in the image without the interference factors of the non-plant parts to obtain a complete plant leaf area after segmentation.
In this embodiment 1, the plant leaf segmentation recognition method is realized by using the above plant leaf segmentation recognition system, and includes:
acquiring an image of a plant leaf to be segmented;
separating a soil background from the plant leaf image to be segmented based on the color index, and extracting a green part in the image;
separating the non-leaf part of the plant in the image with the green part extracted based on morphological opening operation, and smoothing the edge of the leaf area; according to the area of the communicated region, setting a threshold value to remove interference factors of non-plant parts in the smoothed image;
and filling image holes in the image without the interference factors of the non-plant part to obtain a complete plant leaf area after segmentation.
Preprocessing the plant leaf image to be segmented before separating the soil background based on the color index, comprising: removing noise of R, G, B color channels of the image through Gaussian filtering, and simultaneously performing histogram equalization processing on a G channel to enhance the contrast of a green part; and combining the processed gray level images of the three channels to obtain a preprocessed image.
Specifically, in the image acquisition process, the image noise is caused by factors such as insufficient illumination and uneven exposure, and the image needs to be preprocessed. Since the acquired cotton image is color, each pixel contains an R component, a G component, and a B component. Thus, noise is removed by gaussian filtering for the R, G, and B grayscale images, respectively. Compared with the method for directly denoising the RGB image, the method can better inhibit noise, the part with the same color in the image is smoother, and the details of the image are reserved. In order to emphasize the cotton leaf part, in this embodiment 1, an additional histogram equalization process is performed on the G grayscale image to reduce the influence of light and shadow, and distinguish the plant from the background. And then combining the processed 3 gray level images to obtain a preprocessed image.
Filling image holes in the image without the interference factors of the non-plant parts, wherein the filling comprises the following steps: checking all background regions of the whole binary image, if the periphery of the background region is classified into leaves, namely a central hole region, considering that the background region is influenced by colors and cannot be correctly segmented, and resetting the background region as a leaf region; and traversing all pixels for the incomplete part of the blade edge, checking a grid area with a preset size taking each pixel as a center, and if the area of the classified blade part is larger than half of the area of the grid area, determining that the pixel belongs to the blade.
Specifically, plant leaves, such as cotton leaves, usually do not exhibit a completely healthy green color, and are affected by sunburn, leaf blight, natural withering and yellowing, and the color of a part of the plant leaves is close to that of soil, which easily causes misclassification. Secondly, various insect pests can cause the edges or the centers of the leaves to be incomplete, so that the finally divided leaves are incomplete. For this purpose, a padding process is required for the previously divided leaves. In this embodiment 1, all background regions of the entire binary image are checked, and if the surrounding regions are classified as leaves (i.e., central hollow regions), the regions are considered to be affected by color and not correctly divided, and the regions are reset as leaf regions. And obtaining the blade without the cavity after the treatment. The blade edge defect part is often surrounded by three parts of the blade. For this reason, in the present embodiment 1, all pixels are traversed, a 5 × 5 grid region centered on each pixel is checked, and if the area classified as the leaf part is larger than 1/2 grid areas, the pixel is considered to belong to a leaf. And then horizontally turning the picture, and performing more than one operation on the picture again to solve the problem of left and right defects of the blade and finish the extraction of the whole blade. Extracting the positions of the corresponding classified leaf pixels from the original picture to obtain the divided complete leaf
In this embodiment 1, the initial goal of the image analysis process is to classify different pixels in a scene into two categories: soil (background and residue) and plants (crops and weeds). The spectral reflectance difference between vegetation and soil is utilized, and vegetation indexes are used for highlighting certain wavelengths of the image so as to conveniently separate green plants from the soil background and evaluate the growth condition of crops. In this embodiment 1, a vegetation extraction Color Index (CIVE) is used to extract green vegetation, and because the index emphasizes a green region, the index has a better segmentation effect, and the green vegetation is extracted based on the CIVE, which is specifically defined as follows:
CIVE＝0.441R-0.811G+0.385B+18.74745；
wherein R, G, B are the channel component values of the pre-processed color image, respectively.
The morphological opening operation comprises the steps of firstly carrying out corrosion operation on the image, and then carrying out expansion operation on the corroded image, so as to realize the purpose of smoothing the outline of the object and eliminating the slender protrusions. Specifically, the analysis of the growth condition of the crops, whether the crops are affected by diseases and insect pests and the like is based on the whole leaf, and the trunks and stems of the cotton plants are not regions needing attention, so that the trunks and stems are removed in advance to be beneficial to subsequent evaluation. The operation is to perform erosion operation on the image and then perform expansion operation on the eroded image, so as to smooth the contour of the object and eliminate the slender protrusions. The method can effectively remove tiny flaws of the image and break narrow stems and trunks of the image through opening operation, does not influence the position and the shape of the leaf, and is favorable for further segmentation.
According to the area of the connected region, setting a threshold value to remove interference factors of non-plant parts in the smoothed image, and obtaining a segmented plant leaf region, wherein the method comprises the following steps: and removing the object with the area of the connected region smaller than the preset pixel threshold value by means of the smoothed binary image of the image. Specifically, the background of the image in the natural environment may also include various interference factors such as irregularly-shaped weeds, covering, shadows and the like, and the conventional segmentation method cannot completely and accurately identify such objects, so that the initial segmented image appears to occupy an independent closed connected region. It cannot be handled by multiple iterations of the open operation or a simple erosion operation, as this would severely damage the normal blade profile, resulting in a final segmentation that is not ideal. In this embodiment 1, with the help of the binary image, small objects with the area of the connected region smaller than 500 pixels are removed, and simultaneously, the leaf stem and the stem part left by one-step operation are also removed, so that the background interference factor is solved.
In summary, the plant leaf segmentation recognition method described in this embodiment 1 performs gaussian filtering on each channel of the acquired RGB color image, thereby effectively solving the noise caused in the image acquisition process; the G channel histogram equalization can enable the color characteristics of the foreground and the background to have better distinguishability; the vegetation extraction color index divides the image into two types of green vegetation and background, and the morphological opening operation separates the leaf and stem, the trunk and the smooth leaf edge; interference factors in backgrounds such as hay and covering can be removed through the area of the communication area; in addition, the problem of incomplete blade segmentation caused by leaf blight, insect damage and the like is fully considered, the segmented blades are filled, and the complete blades can be effectively extracted.
Example 2
An embodiment 2 of the present invention provides a non-transitory computer-readable storage medium, which is used for storing computer instructions, and when the computer instructions are executed by a processor, the non-transitory computer-readable storage medium implements a plant leaf segmentation identification method, where the method includes:
acquiring an image of a plant leaf to be segmented;
separating a soil background from the plant leaf image to be segmented based on the color index, and extracting a green part in the image;
separating the non-leaf part of the plant in the image with the green part extracted based on morphological opening operation, and smoothing the edge of the leaf area; according to the area of the communicated region, setting a threshold value to remove interference factors of non-plant parts in the smoothed image;
and filling image holes in the image without the interference factors of the non-plant part to obtain a complete plant leaf area after segmentation.
Example 3
An embodiment 3 of the present invention provides a computer program (product) comprising a computer program for implementing a plant leaf segmentation identification method when run on one or more processors, the method comprising:
acquiring an image of a plant leaf to be segmented;
separating a soil background from the plant leaf image to be segmented based on the color index, and extracting a green part in the image;
separating the non-leaf part of the plant in the image with the green part extracted based on morphological opening operation, and smoothing the edge of the leaf area; according to the area of the communicated region, setting a threshold value to remove interference factors of non-plant parts in the smoothed image;
and filling image holes in the image without the interference factors of the non-plant part to obtain a complete plant leaf area after segmentation.
Example 4
An embodiment 4 of the present invention provides an electronic device, including: a processor, a memory, and a computer program; wherein a processor is connected with the memory, the computer program is stored in the memory, when the electronic device runs, the processor executes the computer program stored in the memory, so as to make the electronic device execute the instructions for realizing the plant leaf segmentation identification method, and the method comprises the following steps:
acquiring an image of a plant leaf to be segmented;
separating a soil background from the plant leaf image to be segmented based on the color index, and extracting a green part in the image;
separating the non-leaf part of the plant in the image with the green part extracted based on morphological opening operation, and smoothing the edge of the leaf area; according to the area of the communicated region, setting a threshold value to remove interference factors of non-plant parts in the smoothed image;
and filling image holes in the image without the interference factors of the non-plant part to obtain a complete plant leaf area after segmentation.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts based on the technical solutions disclosed in the present invention.
Claims (10)
1. A plant leaf segmentation and identification method is characterized by comprising the following steps:
acquiring an image of a plant leaf to be segmented;
separating a soil background from the plant leaf image to be segmented based on the color index, and extracting a green part in the image;
separating the non-leaf part of the plant in the image with the green part extracted based on morphological opening operation, and smoothing the edge of the leaf area; according to the area of the communicated region, setting a threshold value to remove interference factors of non-plant parts in the smoothed image;
and filling image holes in the image without the interference factors of the non-plant part to obtain a complete plant leaf area after segmentation.
2. The plant leaf segmentation recognition method according to claim 1, wherein the preprocessing of the plant leaf image to be segmented before the separation of the soil background based on the color index comprises: removing noise of R, G, B color channels of the image through Gaussian filtering, and simultaneously performing histogram equalization processing on a G channel to enhance the contrast of a green part; and combining the processed gray level images of the three channels to obtain a preprocessed image.
3. The plant leaf segmentation and identification method according to claim 1, wherein the image hole filling is performed on the image from which the non-plant part interference factors are removed, and the method comprises the following steps:
checking all background regions of the whole binary image, if the periphery of the background region is classified into leaves, namely a central hole region, considering that the background region is influenced by colors and cannot be correctly segmented, and resetting the background region as a leaf region;
and traversing all pixels for the incomplete part of the blade edge, checking a grid area with a preset size taking each pixel as a center, and if the area of the classified blade part is larger than half of the area of the grid area, determining that the pixel belongs to the blade.
4. The plant leaf segmentation and identification method according to claim 2, wherein the green vegetation is extracted based on a color index CIVE, which is specifically defined as follows:
CIVE＝0.441R-0.811G+0.385B+18.74745；
wherein R, G, B are the channel component values of the pre-processed color image, respectively.
5. The plant leaf segmentation and identification method according to claim 1, wherein the morphological opening operation comprises a corrosion operation on the image, and then an expansion operation on the corroded image, so as to smooth the contour of the object and eliminate the slender protrusions.
6. The method for identifying plant leaf segmentation according to claim 1, wherein the step of setting a threshold value according to the area of the connected region to remove non-plant interference factors in the smoothed image to obtain the segmented plant leaf region comprises: and removing the object with the area of the connected region smaller than the preset pixel threshold value by means of the smoothed binary image of the image.
7. A plant leaf segmentation identification system, comprising:
the acquisition module is used for acquiring an image of a plant leaf to be segmented;
the extraction module is used for separating a soil background from the plant leaf image to be segmented based on the color index and extracting a green part in the image;
the separation module is used for separating the non-leaf part of the plant in the image with the green part extracted and smoothing the edge of the leaf area based on morphological opening operation; according to the area of the communicated region, setting a threshold value to remove interference factors of non-plant parts in the smoothed image;
and the filling module is used for filling image holes in the image without the interference factors of the non-plant parts to obtain a complete plant leaf area after segmentation.
8. A non-transitory computer-readable storage medium storing computer instructions which, when executed by a processor, implement the plant leaf segmentation identification method according to any one of claims 1 to 6.
9. A computer program product, comprising a computer program for implementing a plant leaf segmentation identification method according to any one of claims 1 to 6 when the computer program is run on one or more processors.
10. An electronic device, comprising: a processor, a memory, and a computer program; wherein a processor is connected with the memory, the computer program is stored in the memory, and when the electronic device runs, the processor executes the computer program stored in the memory to make the electronic device execute the instructions for implementing the plant leaf segmentation identification method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210072808.5A CN114581660A (en) | 2022-01-21 | 2022-01-21 | Plant leaf segmentation identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210072808.5A CN114581660A (en) | 2022-01-21 | 2022-01-21 | Plant leaf segmentation identification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114581660A true CN114581660A (en) | 2022-06-03 |
Family
ID=81772365
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210072808.5A Pending CN114581660A (en) | 2022-01-21 | 2022-01-21 | Plant leaf segmentation identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114581660A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115330786A (en) * | 2022-10-13 | 2022-11-11 | 南京邮电大学 | Method for creating rice plant deep learning counting data set based on CECI algorithm |
-
2022
- 2022-01-21 CN CN202210072808.5A patent/CN114581660A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115330786A (en) * | 2022-10-13 | 2022-11-11 | 南京邮电大学 | Method for creating rice plant deep learning counting data set based on CECI algorithm |
| CN115330786B (en) * | 2022-10-13 | 2023-04-25 | 南京邮电大学 | Method for creating rice plant deep learning counting data set based on CECI algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105701829B (en) | A kind of bagging green fruit image partition method | |
| CN109978848B (en) | Method for detecting hard exudation in fundus image based on multi-light-source color constancy model | |
| CN111681253B (en) | Leaf image segmentation method and system based on color and morphological characteristics | |
| CN113298777A (en) | Cotton leaf blight detection method and system based on color features and super-pixel clustering | |
| US11880981B2 (en) | Method and system for leaf age estimation based on morphological features extracted from segmented leaves | |
| Wang et al. | Combining SUN-based visual attention model and saliency contour detection algorithm for apple image segmentation | |
| CN111784764A (en) | Tea tender shoot identification and positioning algorithm | |
| CN109754423B (en) | Method and equipment for extracting coverage area of leaf scab | |
| CN109871900A (en) | The recognition positioning method of apple under a kind of complex background based on image procossing | |
| Anantrasirichai et al. | Automatic leaf extraction from outdoor images | |
| Raut et al. | Review on leaf disease detection using image processing techniques | |
| Tripathy | Detection of cotton leaf disease using image processing techniques | |
| CN114581660A (en) | Plant leaf segmentation identification method and system | |
| CN113269690A (en) | Method and system for detecting diseased region of blade | |
| CN115994921A (en) | Mature cherry fruit image segmentation method integrating HSV model and improving Otsu algorithm | |
| Yao et al. | Study on detection method of external defects of potato image in visible light environment | |
| CN112016418B (en) | Secant recognition method and device, electronic equipment and storage medium | |
| CN110633720A (en) | Corn disease identification method | |
| CN113989522A (en) | Farming robot-oriented field corn plant contour extraction method and system | |
| Di et al. | The research on the feature extraction of sunflower leaf rust characteristics based on color and texture feature | |
| KR102392252B1 (en) | Mushroom Object Growth Monitoring Method Using Image Processing Technology | |
| Neethi et al. | Yield estimation in mango orchards using machine vision | |
| CN111967357A (en) | Intelligent sorghum disease identification system and identification method based on machine vision | |
| CN117237384B (en) | Visual detection method and system for intelligent agricultural planted crops | |
| CN113256671B (en) | Tree fruit counting method based on YCbCr color space |
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 |