CN115346213A - Method and system for detecting lignin and cellulose based on plant staining image - Google Patents

Method and system for detecting lignin and cellulose based on plant staining image Download PDF

Info

Publication number
CN115346213A
CN115346213A CN202210886368.7A CN202210886368A CN115346213A CN 115346213 A CN115346213 A CN 115346213A CN 202210886368 A CN202210886368 A CN 202210886368A CN 115346213 A CN115346213 A CN 115346213A
Authority
CN
China
Prior art keywords
image
lignin
plant
cellulose
signal intensity
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210886368.7A
Other languages
Chinese (zh)
Inventor
杨增玲
廖科科
黄圆萍
韩鲁佳
袁天怡
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Agricultural University
Original Assignee
China Agricultural University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Agricultural University filed Critical China Agricultural University
Priority to CN202210886368.7A priority Critical patent/CN115346213A/en
Publication of CN115346213A publication Critical patent/CN115346213A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
    • G06V20/695—Preprocessing, e.g. image segmentation
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • 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
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/761—Proximity, similarity or dissimilarity measures
    • 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
    • G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
    • G06V20/698—Matching; Classification
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N2021/8466—Investigation of vegetal material, e.g. leaves, plants, fruits

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Molecular Biology (AREA)
  • Medical Informatics (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Chemical & Material Sciences (AREA)
  • Probability & Statistics with Applications (AREA)
  • Pathology (AREA)
  • Analytical Chemistry (AREA)
  • Immunology (AREA)
  • Biochemistry (AREA)
  • Investigating Or Analysing Biological Materials (AREA)

Abstract

The invention provides a method and a system for detecting lignin and cellulose based on a plant staining image, wherein the method comprises the following steps: acquiring a tissue distribution image based on a stained section image of a plant sample to be detected; after RGB channel decomposition is carried out on the tissue distribution image, a first image and a second image are obtained; and respectively carrying out statistical analysis on the signal intensity of the first image and the second image to obtain a first quantitative result and a second quantitative result. According to the method and the system for detecting the lignin and the cellulose based on the plant staining image, provided by the invention, the R/B value and the G/B value can be respectively used as the quantitative indexes of the distribution of the lignin and the cellulose, analyzable quantitative data can be synchronously provided for the lignin and the cellulose, and in-situ synchronous quantitative analysis can be realized. Subjective errors of directly analyzing and judging the distribution of the lignin and the cellulose through human eyes are avoided, and the accuracy, objectivity and repeatability of plant detection are improved.

Description

Method and system for detecting lignin and cellulose based on plant staining image
Technical Field
The invention relates to the technical field of plant cell detection, in particular to a method and a system for detecting lignin and cellulose based on a plant staining image.
Background
Higher plant cell walls are composed primarily of cellulose, lignin and non-cellulosic polysaccharides, the proportions of which depend on the specific function of the cell. Cellulose aggregates into microfibrils with regular structure, defining the skeleton of the cell wall, and the spaces between the dense cell wall fibers are filled by lignin molecules through chemical and/or hydrogen bonds, giving the plant material hydrophobicity, mechanical strength, extensibility, and rigidity.
With the development of microscopy and image digital processing techniques, qualitative histological staining techniques were developed and more objective and reproducible methods were developed. Conventional histochemical staining based on specific binding of cell wall components to staining agents is an alternative, for example, safranin-fast green staining allows simultaneous observation of lignin and cellulose distribution, staining lignin red and cellulose green. The degree of lignification of the plant tissue is then quantified by collected color image analysis. However, methods for quantitative analysis based on staining images generally focus only on the distribution of lignin. The changes of lignin and cellulose in plant tissues are often synergistic and mutually influenced, so how to synchronously analyze the spatial distribution of lignin and cellulose in the plant tissues has important significance for accurately analyzing a gene regulation network and the utilization mechanism of lignocellulose resources.
Disclosure of Invention
The invention provides a method and a system for detecting lignin and cellulose based on a plant staining image, which are used for solving the defect that the spatial distribution of the lignin and the cellulose in plant tissues cannot be synchronously analyzed in the prior art.
The invention provides a method for detecting lignin and cellulose based on a plant staining image, which comprises the following steps:
acquiring a tissue distribution image based on a stained section image of a plant sample to be detected;
after RGB channel decomposition is carried out on the tissue distribution image, a first image and a second image are obtained;
respectively carrying out statistical analysis on the signal intensity of the first image and the second image to obtain a first quantitative result and a second quantitative result;
wherein the stained section image is obtained after performing safranin-fast green staining on the plant sample to be detected; the pixel value of the first image is a ratio of an R-channel signal intensity and a B-channel signal intensity; the pixel value of the second image is a ratio of a G-channel signal intensity and a B-channel signal intensity; the first quantitative result is used for indicating the content of lignin of the plant sample to be detected in the corresponding tissue part; the second quantitative result is used for indicating the content of the cellulose of the plant sample to be detected in the corresponding tissue part.
According to the detection method of lignin and cellulose based on plant staining images provided by the invention, after RGB channel decomposition is carried out on the tissue distribution images, a first image and a second image are obtained, and the method comprises the following steps:
determining a signal intensity threshold based on channel signal intensity of the tissue distribution image;
screening an R channel image of the cell wall, a G channel image of the cell wall and a B channel image of the cell wall from the channel signal intensity of the tissue distribution image based on the signal intensity threshold;
comparing the R channel image of the cell wall and the G channel image of the cell wall with the B channel image of the cell wall respectively to obtain the first image and the second image;
wherein the channel signal intensities of the tissue distribution image include R-channel signal intensity, G-channel signal intensity, and B-channel signal intensity.
According to the detection method of lignin and cellulose based on the plant staining image provided by the invention,
after the acquiring the first image and the second image, further comprising:
respectively carrying out clustering analysis on the first image and the second image to obtain a first clustering result and a second clustering result;
the first clustering result is used for indicating the difference distribution of the lignin content of the plant sample to be detected; the second clustering result is used for indicating the difference distribution of the cellulose content of the plant sample to be tested.
According to the method for detecting lignin and cellulose based on the plant staining image, the step of performing cluster analysis on the first image and the second image respectively to obtain a first clustering result and a second clustering result comprises the following steps:
performing R-type clustering analysis on the first image and the second image to respectively obtain a first pixel point proportion and a second pixel point proportion of the first image and the second image in each classification;
and respectively determining the first clustering result and the second clustering result based on the first pixel point ratio and the second pixel point ratio.
According to the detection method of lignin and cellulose based on the plant staining image provided by the invention, the tissue distribution image is obtained based on the staining slice image of the plant sample to be detected, and the method comprises the following steps:
converting the stained section image into a Hue preservation Value color space for foreground extraction to obtain a target image;
and extracting the tissue distribution image based on the target image.
According to the detection method of the lignin and the cellulose based on the plant staining image, the staining slice image of the plant sample to be detected is collected after white balance correction is carried out on the staining slice image through a white board in a visual field.
The invention also provides a lignin and cellulose detection system based on the plant staining image, which comprises the following components:
the sample image processing module is used for acquiring a tissue distribution image based on a dyed slice image of a plant sample to be detected;
the composition extraction module is used for obtaining a first image and a second image after RGB channel decomposition is carried out on the tissue distribution image;
the quantification module is used for respectively carrying out signal intensity statistical analysis on the first image and the second image to obtain a first quantification result and a second quantification result;
wherein, the stained section image is obtained after the plant sample to be detected is stained with safranin-fast green; the pixel value of the first image is a ratio of an R-channel signal intensity and a B-channel signal intensity; the pixel value of the second image is a ratio of a G-channel signal intensity and a B-channel signal intensity; the first quantitative result is used for indicating the content of lignin of the plant sample to be detected in the corresponding tissue part; the second quantitative result is used for indicating the content of the cellulose of the plant sample to be detected in the corresponding tissue part.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the method for detecting lignin and cellulose based on plant staining images as described in any of the above.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a plant stain image based lignin and cellulose detection method as described in any of the above.
The present invention also provides a computer program product comprising a computer program which, when executed by a processor, implements a method for plant stain image based detection of lignin and cellulose as described in any of the above.
According to the method and the system for detecting the lignin and the cellulose based on the plant staining image, the tissue distribution image is extracted based on the staining slice image of the plant sample to be detected, and a first quantitative result and a second quantitative result are obtained by counting a first image and a second image obtained by processing the tissue distribution image. The R/B value and the G/B value can be respectively used as quantitative indexes of the distribution of lignin and cellulose, analyzable quantitative data can be synchronously provided for the lignin and the cellulose, and in-situ synchronous quantitative analysis is realized. Subjective errors in judging the distribution of the lignin and the cellulose by human eye analysis are avoided, and the accuracy, objectivity and repeatability of plant detection are improved.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for detecting lignin and cellulose based on a plant staining image provided by the present invention;
FIG. 2 is a schematic diagram of a simulation of the method for detecting lignin and cellulose based on a plant stain image provided by the present invention;
FIG. 3 is a second simulation schematic diagram of the detection method of lignin and cellulose based on plant staining images provided by the present invention;
FIG. 4 is a third simulation schematic diagram of the detection method of lignin and cellulose based on plant staining images provided by the present invention;
FIG. 5 is a fourth schematic diagram of a simulation of the method for detecting lignin and cellulose based on a plant staining image provided by the present invention;
FIG. 6 is a schematic structural diagram of a detection system for lignin and cellulose based on a plant stain image provided by the present invention;
fig. 7 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
The terms "first," "second," and the like in this application are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that embodiments of the application may be practiced in sequences other than those illustrated or described herein, and that the terms "first," "second," and the like are generally used herein in a generic sense and do not limit the number of terms, e.g., the first term can be one or more than one.
It is to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this application, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The terms "comprises" and "comprising" indicate the presence of the described 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.
FIG. 1 is a schematic flow chart of a method for detecting lignin and cellulose based on a plant staining image provided by the invention. As shown in fig. 1, a method for detecting lignin and cellulose based on a plant staining image according to an embodiment of the present invention includes: step 101, acquiring a tissue distribution image based on a stained section image of a plant sample to be detected.
Wherein, the stained section image is obtained after the plant sample to be detected is stained by safranin-fast green.
It should be noted that the implementation subject of the method for detecting lignin and cellulose based on a plant staining image provided by the embodiment of the present invention is an electronic device operated by the system for detecting lignin and cellulose based on a plant staining image.
The electronic device described above may be implemented in various forms. The electronic devices described in the embodiments of the present application may include mobile terminals such as a mobile phone, a smart phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a navigation device, a smart band, a smart watch, a digital camera, and the like, and fixed terminals such as a digital TV, a desktop computer, and the like. In the following, it is assumed that the electronic device is a mobile terminal. However, it will be understood by those skilled in the art that the configuration according to the embodiment of the present application can be applied to a fixed type terminal in addition to elements particularly used for moving purposes.
The application scenario of the lignin and cellulose detection system based on the plant staining image is that a plant sample slice is prepared, safranin-fast green is adopted for staining and a visible light microscope image is obtained, RGB decomposition is carried out on the processed microscopic image, the lignin content is reflected by the R/B value, the cellulose content is reflected by the G/B value, and in-situ visualization and quantitative characterization of spatial distribution are carried out.
It should be noted that, before step 101, a safranin-fast green staining reagent is used to perform sample counterstaining preparation and stain image acquisition on a plant sample to be detected.
The specific implementation process comprises the following steps: cutting a plant sample to be detected, fixing the cut plant sample in a formalin-acetic acid-ethanol fixing agent for more than 24 hours, embedding the cut plant sample in paraffin, carrying out safranin-fast green counter staining on the cut plant sample, observing the stained cut plant sample by using an objective lens (for example, 5 times, 10 times or 20 times) under a common biological microscope, and sending an obtained microscopic image serving as a stained cut plant image to a detection system of lignin and cellulose based on the plant stained image.
The preparation of the plant sample to be detected in the embodiment of the present invention is not particularly limited.
The implementation process is as follows:
(1) A plant sample to be tested is cut in a fresh state to a thickness of not more than 5 millimeters (mm), and then fixed in Formalin-Acetic-Alcohol (FAA) fixative for more than 24 hours.
(2) The fixed sample is paraffin embedded section, and the section thickness can be between 12 micrometers (mum) and 16μm.
(3) The safranin-fast green counter-dyeing method comprises the following specific operations:
(a) Dewaxing (xylene/ethanol solution: 100% xylene, xylene/ethanol (3/1, v/v), xylene/ethanol (1/1, v/v), absolute ethanol, each solution being soaked for 10 minutes in sequence).
(b) Safranin-fast green is counter-dyed (anhydrous ethanol, soaking 3 times, 3 minutes/time; 95%, 85% and 70% ethanol, soaking 3 minutes in sequence; 1% safranin in 50% ethanol, soaking 30 minutes at 37 deg.C; soaking 2 times, 1 minute/time in 70% ethanol; soaking 1 minute in 80% ethanol; soaking 2 times, 1 minute/time in 95% ethanol; soaking 0.5% fast green (95% ethanol as solvent) for 6 seconds; soaking 2 times, 1 minute/time in anhydrous ethanol; soaking 1 minute/time in xylene/ethanol solution (1/1, v/v); soaking 2 times, 1 minute/time in 100% xylene solution).
Specifically, in step 101, the detection system for lignin and cellulose based on plant staining images performs single tissue structure extraction on the received stained section images by using a series of image processing methods, and obtains corresponding tissue distribution images.
102, performing RGB channel decomposition on the tissue distribution image, and acquiring a first image and a second image.
Wherein the pixel value of the first image is a ratio of the R-channel signal intensity and the B-channel signal intensity. The pixel value of the second image is a ratio of the G-channel signal strength and the B-channel signal strength.
Specifically, in step 102, the detection system based on lignin and cellulose of the plant stain image performs channel decomposition on the processed tissue distribution map image to the tissue distribution image, and performs normalization in the range of 0 to 1, after acquiring corresponding red R channel image, green G channel image and blue B channel image respectively. And performing locus division on the R channel image and the B channel image to generate a first image with R/B pixel values, and performing locus division on the G channel image and the B channel image to generate a second image with G/B pixel values in the same way.
The pixel value of each pixel point in the first image is a ratio of the R channel signal intensity and the B channel signal intensity of the pixel point in the tissue distribution image, and the R/B ratio can be used as a quantization index of lignin.
The pixel value of each pixel point in the second image is the ratio of the pixel point between the signal intensity of the G channel and the signal intensity of the B channel of the tissue distribution image, and the G/B ratio can be used as the quantization index of the cellulose.
And 103, performing signal intensity statistical analysis on the first image and the second image respectively to obtain a first quantitative result and a second quantitative result.
Wherein the first quantitative result is used for indicating the content of lignin of the plant sample to be tested in the corresponding tissue part. The second quantitative result is used for indicating the content of the cellulose of the plant sample to be tested in the corresponding tissue part.
Specifically, in step 103, the plant stain image-based lignin and cellulose detection system performs a statistical analysis on the R/B ratio in the first image and the G/B ratio in the second image, respectively, to obtain a first quantitative result and a second quantitative result.
The first quantitative result is a statistical result of the R/B ratio in the first image, and can be used to characterize the distribution of the lignin content of the plant sample to be tested in space.
The second quantitative result is a statistical result of the G/B ratio in the second image, and can be used to characterize the distribution of the lignin content of the plant sample to be detected in space.
The statistical method used for the pixel values in the first image and the second image includes, but is not limited to, a method of counting an average value of the pixel values, a method of counting a variance of the pixel values, and the like, which is not specifically limited in this embodiment of the present invention.
The lignin and cellulose distribution quantitative data indicated by the first quantitative result and the second quantitative result can support the statistically significant difference analysis of different tissues of the same sample and the same tissue of different samples, and is beneficial to analyzing a regulation network formed by different genes and characters and a degradation mechanism in a resource utilization process in crop breeding research.
According to the embodiment of the invention, the tissue distribution image is extracted based on the stained section image of the plant sample to be detected, and the first quantitative result and the second quantitative result are obtained by counting the first image and the second image which are obtained by processing the tissue distribution image. The R/B value and the G/B value can be respectively used as quantitative indexes of the distribution of lignin and cellulose, analyzable quantitative data can be synchronously provided for the lignin and the cellulose, and in-situ synchronous quantitative analysis is realized. Subjective errors of directly analyzing and judging the distribution of the lignin and the cellulose through human eyes are avoided, and the accuracy, objectivity and repeatability of plant detection are improved.
On the basis of any of the above embodiments, after performing RGB channel decomposition on the tissue distribution image, acquiring a first image and a second image, including: a signal intensity threshold is determined based on the channel signal intensity of the tissue distribution image.
Specifically, in step 102, the detection system based on lignin and cellulose of the plant stain image respectively counts corresponding channel thresholds from frequency distribution histograms of different channel images for the normalized R channel image, G channel image and B channel image, and then averages the channel thresholds to determine the signal intensity threshold of the cell wall and stain residual information.
It can be understood that, since the difference between the channel thresholds of the channel images is relatively small, the frequency distribution histogram of the B channel image alone may be counted to obtain the signal strength threshold.
And screening an R channel image of the cell wall, a G channel image of the cell wall and a B channel image of the cell wall from the channel signal intensity of the tissue distribution image based on the signal intensity threshold. Specifically, the detection system for lignin and cellulose based on plant stain images uses the B-channel signal intensity in the RGB channel as a reference, and converts pixels in the B-channel image that are greater than a signal intensity threshold into NaN (i.e., pixels without a numerical value), so that only pixels that are less than or equal to the signal intensity threshold remain, resulting in a B-channel image of the cell wall. And similarly, recording the pixel point coordinates converted into NaN, converting the pixel values in the pixel point coordinates corresponding to the R channel image and the G channel image into NaN, respectively obtaining the R channel image of the cell wall and the G channel image of the cell wall so as to remove the residual coloring agent and keep the signal intensity of the RGB channel of the information cell wall.
And comparing the R channel image of the cell wall and the G channel image of the cell wall with the B channel image of the cell wall respectively to obtain a first image and a second image.
Specifically, the lignin and cellulose detection system based on the plant stain image compares the R-channel image of the cell wall with the B-channel image of the cell wall to obtain a first image. Similarly, the second image is obtained by comparing the G channel image of the cell wall with the B channel image of the cell wall.
The method comprises the steps of determining a signal intensity threshold value based on a frequency distribution histogram of RGB three channels, screening RGB three-channel images through the signal intensity threshold value, removing residual information of coloring agents, only keeping RGB three-channel signal intensity of cell walls, and respectively taking the R/B ratio of a first image and the G/B ratio of a second image as quantitative indexes of lignin and cellulose distribution. The quantitative comparative analysis of the lignin and cellulose content between tissues is carried out by the quantitative index mean value of all cell wall pixels in the plant tissue structure, and the distribution difference of the lignin and the cellulose can be described qualitatively and quantitatively.
On the basis of any of the above embodiments, after acquiring the first image and the second image, the method further includes: and respectively carrying out clustering analysis on the first image and the second image to obtain a first clustering result and a second clustering result.
And the first clustering result is used for indicating the difference distribution of the lignin content of the plant sample to be detected. The second clustering result is used to indicate the differential distribution of the cellulose content of the plant sample to be tested.
Specifically, the detection system for lignin and cellulose based on the plant staining image clusters the R/B ratio in the first image and the G/B ratio in the second image respectively, and the ratios with high similarity are regarded as one type to obtain a first clustering result and a second clustering result.
The first clustering result is a classification with the maximum R/B ratio, has obvious data characteristics, and can be used for representing the distribution of the lignin content difference of the plant sample to be detected in the space.
The second clustering result refers to the classification with the maximum G/B ratio, which has obvious data characteristics and can be used for representing the distribution of the cellulose content difference of the plant sample to be tested in space.
It is understood that the cluster analysis method includes, but is not limited to, a direct clustering method, a shortest distance clustering method, or a farthest distance clustering method, and the like, which is not particularly limited in this embodiment of the present invention.
The similarity measure can be implemented by calculating a distance, which includes, but is not limited to, an euclidean distance, a manhattan distance, a chebyshev distance, a minh distance, a normalized euclidean distance, a cosine similarity, a mahalanobis distance, a hamming distance, or a babbitt distance.
According to the embodiment of the invention, clustering analysis is carried out based on the R/B value in the first image and the G/B value in the second image, so that the spatial difference distribution of the obtained lignin and cellulose is represented according to the obtained first clustering result and the second clustering result. The method can qualitatively and quantitatively describe the distribution difference of lignin and cellulose of different tissues of the same sample and the same tissue of different samples, and is beneficial to analyzing a regulation network formed by different genes and characters and a degradation mechanism in a resource utilization process in crop breeding research.
On the basis of any of the above embodiments, performing cluster analysis on the first image and the second image, respectively, to obtain a first clustering result and a second clustering result, includes: and performing R-type clustering analysis on the first image and the second image to respectively obtain a first pixel point proportion and a second pixel point proportion of the first image and the second image in each classification.
Specifically, a lignin and cellulose detection system based on a plant dye image sets a classification number n for a clustering analysis process, then R-type clustering in unsupervised K-means clustering is adopted to respectively cluster R/B in a first image and G/B in a second image, a clustering center point is not set, n times of distance repeated calculation are carried out, ratios with similar distances are regarded as one type, the ratio of each classified R/B pixel point in all pixel points of the first image is calculated to be used as a first pixel point ratio, and the ratio of each classified G/B pixel point in all pixel points of the second image is used as a second pixel point ratio.
And determining a first clustering result and a second clustering result based on the first pixel point ratio and the second pixel point ratio.
Specifically, the plant dye image-based lignin and cellulose detection system compares the first pixel point proportion and the second pixel point proportion under each classification to determine a first clustering result and a second clustering result.
The embodiment of the invention carries out R-type clustering analysis based on the first image and the second image, and obtains and determines a first clustering result and a second clustering result through the first pixel point proportion and the second pixel point proportion in each classification. The distribution difference of the lignin and the cellulose can be qualitatively and quantitatively described.
On the basis of any one of the above embodiments, acquiring a tissue distribution image based on a stained section image of a plant sample to be tested includes: and converting the stained section image into a Hue preservation Value color space for foreground extraction, and acquiring a target image.
Specifically, in step 101, after the detection system of lignin and cellulose based on plant staining image converts the staining slice image into the Hue failure Value (HSV) color space, the binarization is performed in the V space by using the adaptive threshold method, and then the foreground extraction is performed by selecting the foreground polarity parameter, so as to obtain the target image.
Based on the target image, a tissue distribution image is extracted.
Specifically, the detection system for lignin and cellulose based on the plant staining image extracts a single tissue in the plant section staining image from the target image by using multipoint fitting to obtain a corresponding tissue distribution image.
Tissue distribution images, including distribution images of lignin (i.e., red components) and cellulose (i.e., green components) in individual plant tissues.
The embodiment of the invention performs foreground extraction and different tissue structures extraction on the dye slice image conversion to obtain the tissue distribution image. The characteristic extraction of the sample image is realized, only the plant tissue part is reserved, and the accuracy, objectivity and repeatability of plant detection are improved.
On the basis of any of the above embodiments, the stained section image of the plant sample to be tested is collected after white balance correction is performed on the white board in the field of view.
Specifically, the stained section image received by the lignin and cellulose detection system based on the plant stained image is a microscopic image obtained by observing the stained section by a 5X/10X/20X objective lens under a common biological microscope, simultaneously acquiring various tissue microscopic images with the highest resolution in a field of view, and performing white balance correction by using a white board in the microscopic measurement process.
FIG. 2 is a schematic diagram of a simulation of the method for detecting lignin and cellulose based on a plant staining image provided by the present invention. FIG. 3 is a second simulation schematic diagram of the detection method of lignin and cellulose based on plant staining images provided by the present invention. Fig. 4 is a third simulation schematic diagram of the detection method of lignin and cellulose based on the plant staining image provided by the invention. FIG. 5 is a fourth simulation schematic diagram of the detection method of lignin and cellulose based on plant staining images provided by the invention. As shown in fig. 2 to fig. 5, in the embodiment of the present invention, rice with an introduction line IL349 (IL 349) and rice with a Brittle Culm1 gene mutant (KO-BC 1) isolated from IL349 are used to grow in an outdoor paddy field environment, and the middle parts of penultimate internodes of two rice stalks are used as plant samples to be tested:
example 1 is an in-situ synchronous quantitative study on the content difference of cellulose and lignin in cross sections of rice stalks:
(1-1) sample preparation: cutting the collected penultimate node of the rice stem from the middle part, then placing the cut rice stem in FAA fixative, fixing for more than 24h, embedding the cut rice stem in paraffin, cutting a cross section with the thickness of about 15 mu m by using a slide-away slicer, and then carrying out safranin-fast green counter-staining, wherein the specific operations comprise: (a) Dewaxing (xylene/ethanol solution: 100% xylene, xylene/ethanol (3/1, v/v), xylene/ethanol (1/1, v/v), absolute ethanol, each solution being soaked for 10 minutes in turn); (b) Safranin-fast green is counter-dyed (anhydrous ethanol, soaking 3 times, 3 minutes/time; 95%, 85% and 70% ethanol, soaking 3 minutes in sequence; 1% safranin in 50% ethanol, soaking 30 minutes at 37 deg.C; soaking 2 times, 1 minute/time in 70% ethanol; soaking 1 minute in 80% ethanol; soaking 2 times, 1 minute/time in 95% ethanol; 0.5% fast green in 95% ethanol for 6 seconds; soaking 2 times, 1 minute/time in anhydrous ethanol; soaking 1 minute/time in xylene/ethanol solution (1/1, v/v); soaking 2 times, 1 minute/time in 100% xylene solution).
(1-2) microscopic image acquisition: under a normal biological microscope, the stained section is observed with a 10X objective lens, and various tissue microscopic images are simultaneously acquired at the highest resolution within one field of view, and white balance correction is performed with a white board before the images are acquired. As shown in FIG. 2, the scale is set to 100 μm, and the left subgraph is the stained section image corresponding to IL349, and the right subgraph is the stained section image corresponding to KO-BC 1.
(1-3) treatment of stained image: the images are converted into HSV color spaces, respectively, and then converted into a binary image of V space using an adaptive threshold method. And finally, selecting the foreground polarity parameters to perform foreground to obtain a tissue distribution image.
(1-4) quantification of spatial distribution of lignin and cellulose in plant tissues: the tissue distribution images of the two rice samples were subjected to RGB decomposition and normalized in the range of 0-1. And obtaining an RGB signal intensity threshold value of cell wall and stain residual information according to a frequency distribution histogram of the RGB channel signal intensity of the stain image, and converting pixels larger than the threshold value into NaN (namely pixels without numerical values) by using the B channel signal intensity in the RGB channel as a reference so as to only reserve the cell wall RGB channel signal intensity. And calculating R/B and G/B ratios as quantitative indexes of lignin and cellulose, generating an R/B ratio image (namely a first image) and a G/B ratio image (namely a second image) for the in-situ analysis of the spatial distribution of the lignin and the cellulose, and performing quantitative comparative analysis on the content of the lignin and the cellulose between tissues by using the mean value of R/B and G/B values of all cell wall pixels.
As shown in fig. 3, the subgraphs (a) and (b) correspond to the first image and the second image of two kinds of rice, respectively, and the enlarged image in the white frame is displayed on the right side of the graph. Subgraphs (c) and (d) are the statistics of the R/B ratio in the first image and the G/B ratio in the second image, respectively.
Where the abbreviation E, is epidermal-mechanical tissue. Abbreviation P, parenchyma. The abbreviation V, is the vascular bundle.
The statistical results show that: the R/B ratio of KO-BC1 rice straw was clearly compared in epidermal-mechanical tissue with less difference in parenchyma and vascular bundles compared to IL349 rice straw (FIG. 3 a). From the R/B ratio violin plot (fig. 3 c) it can be derived that the mean value of KO-BC1 is higher than IL349, indicating that the difference in lignin content is mainly reflected in the epidermo-mechanical tissue. The results of the G/B and R/B ratio images are in contrast (FIG. 3B), with the epidermal-mechanical tissue of KO-BC1 rice stalks having a G/B ratio significantly lower than IL349 and parenchyma and vascular bundles slightly lower than IL 349. It can be obtained from the G/B ratio violin chart (FIG. 3 d) that the average value of the G/B ratio of KO-BC1 rice stalks is lower than that of IL349, which indicates that the difference of cellulose content is also mainly reflected in the epidermis-mechanical tissue.
Example 2 is an in-situ synchronous quantitative study on the content difference of cellulose and lignin in the epidermal-mechanical tissue of rice straw, and the sample preparation (2-1) and the microscopic image acquisition (2-2) are the same as those in example 1.
(2-3) treatment of stained image: the image is converted into HSV color space, respectively, and then converted into a binary image of V space using an adaptive thresholding method. Finally, selecting foreground polarity parameters to perform foreground, and extracting a tissue distribution image of the epidermis-mechanical tissue from the stained section image through multi-point fitting
(2-4) quantification of the spatial distribution of lignin and cellulose in epidermal-mechanical tissue: the tissue distribution images of the two rice samples were subjected to RGB decomposition and normalized in the range of 0 to 1. And obtaining an RGB signal intensity threshold value of cell wall and stain residual information according to a frequency distribution histogram of the RGB channel signal intensity of the stain image, and converting pixels larger than the threshold value into NaN (namely pixels without numerical values) by using the B channel signal intensity in the RGB channel as a reference so as to only reserve the cell wall RGB channel signal intensity. An R/B ratio image (i.e., a first image) and a G/B ratio image (i.e., a second image) are generated, and the R/B and G/B ratios are calculated as quantitative indicators of lignin and cellulose.
(2-5) K-means clustering analysis: and respectively carrying out K-means clustering on the R/B and G/B ratios in the first image and the second image of the two kinds of rice, not setting a clustering center point, repeatedly calculating for 5 times by using City Distance (City Distance), and regarding the ratios with similar City distances as one class.
As shown in FIG. 4, the five upper subgraphs are IL349 rice straw epidermis-mechanical tissue R/B ratio K-means cluster images, and the five lower subgraphs are KO-BC1 rice straw epidermis-mechanical tissue R/B ratio K-means cluster images.
As shown in fig. 5, the five upper sub-images are IL349 rice straw epidermis-mechanical tissue G/B ratio K-means cluster images, and the five lower sub-images are KO-BC1 rice straw epidermis-mechanical tissue G/B ratio K-means cluster images.
Wherein the abbreviation Epi is epidermis. The abbreviation Sa means a thick wall structure. The abbreviation Svb, bundle of small dimensions.
According to the clustering result shown in FIG. 4, the sclerenchyma tissue in the epidermis-mechanical tissue of IL349 rice stem is intensively distributed in the 3 rd and 4 th classes, while KO-BC1 is mainly distributed in the 1 st class, which shows that the lignin content in the sclerenchyma tissue of KO-BC1 rice stem is higher than that of IL349, and the difference is the largest. The small vascular bundle in the IL349 rice straw is mainly represented in the 2 nd class and has relatively complete outline, while the small vascular bundle of the KO-BC1 is basically represented in the 1 st class, which indicates that the small vascular bundle of the KO-BC1 rice straw has higher lignin content. The K-means cluster images also showed that the epidermis of IL349 rice straw is mainly shown in the 1 st and 2 nd classes, while the epidermis of KO-BC1 is basically distributed in the 1 st class with minimal difference.
Two rice epidermis-mechanical tissue G/B ratio K-means cluster images (as shown in FIG. 5) show that the morphological structure information of the epidermis and the sclerenchyma of the KO-BC1 rice stem is mostly presented in the 4 th class and partially included in the 3 rd class. In contrast, the epidermis and the sclerenchyma of IL349 are distributed in the 1 st and 2 nd classes, the sclerenchyma in the 3 rd class is relatively broken, and the epidermis is relatively complete, which indicates that the cellulose content of the epidermis-mechanical tissue of KO-BC1 rice stem is lower than that of IL349, and the tissue part with the largest difference is the sclerenchyma of two rice stems and the epidermis. There is a difference between the centralized distribution of the vascular bundles of KO-BC1 in class 3 and the centralized distribution of the vascular bundles of IL349 in classes 2 and 3.
In the embodiment of the invention, before the stained section image is obtained, the white balance processing is carried out by arranging the white board in the microscopic imaging process, so that the stained section image is obtained. Stray factors in the environment of the sample image are filtered, and the accuracy, objectivity and repeatability of plant detection are improved.
FIG. 6 is a schematic structural diagram of a lignin and cellulose detection system based on a plant staining image provided by the invention. On the basis of any one of the above embodiments, as shown in fig. 6, the detection system for lignin and cellulose based on plant staining images provided by the embodiments of the present invention includes: a sample image processing module 610, a composition extraction module 620, and a quantization module 630, wherein:
and the sample image processing module 610 is configured to obtain a tissue distribution image based on the stained section image of the plant sample to be detected.
And a composition extraction module 620, configured to perform RGB channel decomposition on the tissue distribution image, and then obtain a first image and a second image.
The quantification module 630 is configured to perform statistical analysis on the signal intensity of the first image and the signal intensity of the second image, and obtain a first quantification result and a second quantification result.
Wherein, the stained section image is obtained after the plant sample to be detected is stained with safranin-fast green. The pixel value of the first image is a ratio of the R-channel signal intensity and the B-channel signal intensity. The pixel value of the second image is a ratio of the G-channel signal intensity and the B-channel signal intensity. The first quantitative result is used for indicating the content of lignin of the plant sample to be detected in the corresponding tissue part. The second quantitative result is used for indicating the content of the cellulose of the plant sample to be detected in the corresponding tissue part.
Specifically, the sample image processing module 610, the constituent extraction module 620, and the quantization module 630 are electrically connected in sequence.
The sample image processing module 610 performs single tissue structure extraction on the received stained section image by using a series of image processing modes to obtain a corresponding tissue distribution image.
The tissue distribution image processed by the composition extraction module 620 is processed to obtain a first image and a second image.
The pixel value of each pixel point in the first image is a ratio of the pixel point between a red component and a blue component of the tissue distribution image, and the R/B ratio can be used as a quantification index of lignin.
The pixel value of each pixel point in the second image is the ratio of the pixel point between the green component and the blue component of the tissue distribution image, and the G/B ratio can be used as the quantization index of cellulose.
The quantization module 630 clusters the R/B ratio in the first image and the G/B ratio in the second image, respectively, and regards the ratios with higher similarity as one class to obtain a first clustering result and a second clustering result.
Optionally, the composition component extracting module 620 includes a threshold determining unit, a pixel screening unit, and a tissue extracting unit, wherein:
a threshold determination unit for determining a signal intensity threshold based on the channel signal intensity of the tissue distribution image.
And the pixel screening unit is used for screening the R channel image of the cell wall, the G channel image of the cell wall and the B channel image of the cell wall from the channel signal intensity of the tissue distribution image based on the signal intensity threshold value.
And the tissue extraction unit is used for comparing the R channel image of the cell wall and the G channel image of the cell wall with the B channel image of the cell wall respectively to obtain a first image and a second image.
Optionally, the plant stain image-based lignin and cellulose detection system further comprises an analysis module, wherein:
and the analysis module is used for respectively carrying out clustering analysis on the first image and the second image to obtain a first clustering result and a second clustering result.
And the first clustering result is used for indicating the difference distribution of the lignin content of the plant sample to be detected. The second clustering result is used to indicate the differential distribution of cellulose content of the plant sample to be tested.
Optionally, the analysis module comprises a clustering unit and an analysis unit, wherein:
and the clustering unit is used for performing R-type clustering analysis on the first image and the second image to respectively obtain the first pixel point proportion and the second pixel point proportion of the first image and the second image in each classification.
And the analysis unit is used for determining a first clustering result and a second clustering result based on the first pixel point proportion and the second pixel point proportion.
Optionally, the sample image processing module 610 includes a spatial conversion unit and a feature extraction unit, wherein:
and the space conversion unit is used for converting the stained section image into a Hue preservation Value color space for foreground extraction and acquiring a target image.
And the characteristic extraction unit is used for extracting the tissue distribution image based on the target image.
Optionally, the stained section image of the plant sample to be tested is acquired after white balance correction via a white board within the field of view.
The detection system of lignin and cellulose based on a plant staining image provided by the embodiment of the invention is used for executing the detection method of lignin and cellulose based on a plant staining image provided by the invention, and the implementation manner of the detection system of lignin and cellulose based on a plant staining image provided by the invention is consistent with that of the detection method of lignin and cellulose based on a plant staining image provided by the invention, and the same beneficial effects can be achieved, and are not repeated herein.
According to the embodiment of the invention, the tissue distribution image is extracted based on the stained section image of the plant sample to be detected, and the first quantitative result and the second quantitative result are obtained by counting the first image and the second image which are obtained by processing the tissue distribution image. The R/B value and the G/B value can be respectively used as quantitative indexes of the distribution of lignin and cellulose, analyzable quantitative data can be synchronously provided for the lignin and the cellulose, and in-situ synchronous quantitative analysis is realized. Subjective errors in judging the distribution of the lignin and the cellulose by human eye analysis are avoided, and the accuracy, objectivity and repeatability of plant detection are improved.
Fig. 7 illustrates a physical structure diagram of an electronic device, and as shown in fig. 7, the electronic device may include: a processor (processor) 710, a communication Interface (Communications Interface) 720, a memory (memory) 730, and a communication bus 740, wherein the processor 710, the communication Interface 720, and the memory 730 communicate with each other via the communication bus 740. Processor 710 may invoke logic instructions in memory 730 to perform a method of detecting lignin and cellulose based on a plant stain image, the method comprising: acquiring a tissue distribution image based on a stained section image of a plant sample to be detected; after RGB channel decomposition is carried out on the tissue distribution image, a first image and a second image are obtained; respectively carrying out statistical analysis on the signal intensity of the first image and the second image to obtain a first quantitative result and a second quantitative result; wherein, the stained section image is obtained after the plant sample to be detected is stained with safranin-fast green; the pixel value of the first image is a ratio of the R-channel signal intensity and the B-channel signal intensity; the pixel value of the second image is a ratio of the G-channel signal intensity and the B-channel signal intensity; the first quantitative result is used for indicating the content of lignin of the plant sample to be detected in the corresponding tissue part; the second quantitative result is used for indicating the content of the cellulose of the plant sample to be tested in the corresponding tissue part.
In addition, the logic instructions in the memory 730 can be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program, the computer program being stored on a non-transitory computer readable storage medium, the computer program, when executed by a processor, being capable of executing the method for detecting lignin and cellulose based on a plant stain image provided by the above method, the method comprising: acquiring a tissue distribution image based on a stained section image of a plant sample to be detected; after RGB channel decomposition is carried out on the tissue distribution image, a first image and a second image are obtained; respectively carrying out statistical analysis on the signal intensity of the first image and the second image to obtain a first quantitative result and a second quantitative result; wherein, the stained section image is obtained after the plant sample to be detected is stained with safranin-fast green; the pixel value of the first image is a ratio of the R-channel signal intensity and the B-channel signal intensity; the pixel value of the second image is a ratio of the G-channel signal intensity and the B-channel signal intensity; the first quantitative result is used for indicating the content of lignin of the plant sample to be detected in the corresponding tissue part; the second quantitative result is used for indicating the content of the cellulose of the plant sample to be tested in the corresponding tissue part.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method for detecting lignin and cellulose based on a plant stain image provided by the above methods, the method comprising: acquiring a tissue distribution image based on a stained section image of a plant sample to be detected; after RGB channel decomposition is carried out on the tissue distribution image, a first image and a second image are obtained; respectively carrying out statistical analysis on the signal intensity of the first image and the second image to obtain a first quantitative result and a second quantitative result; wherein, the stained section image is obtained after the plant sample to be detected is stained with safranin-fast green; the pixel value of the first image is a ratio of the R-channel signal intensity and the B-channel signal intensity; the pixel value of the second image is a ratio of the G-channel signal intensity and the B-channel signal intensity; the first quantitative result is used for indicating the content of lignin of the plant sample to be detected in the corresponding tissue part; the second quantitative result is used for indicating the content of the cellulose of the plant sample to be tested in the corresponding tissue part.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. Based on the understanding, the above technical solutions substantially or otherwise contributing to the prior art may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the various embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (10)

1. A method for detecting lignin and cellulose based on plant staining images is characterized by comprising the following steps:
acquiring a tissue distribution image based on a stained section image of a plant sample to be detected;
after RGB channel decomposition is carried out on the tissue distribution image, a first image and a second image are obtained;
respectively carrying out statistical analysis on the signal intensity of the first image and the second image to obtain a first quantitative result and a second quantitative result;
wherein, the stained section image is obtained after the plant sample to be detected is stained with safranin-fast green; the pixel value of the first image is a ratio of an R-channel signal intensity and a B-channel signal intensity; the pixel value of the second image is a ratio of a G-channel signal intensity and a B-channel signal intensity; the first quantitative result is used for indicating the content of lignin of the plant sample to be detected in the corresponding tissue part; the second quantitative result is used for indicating the content of the cellulose of the plant sample to be detected in the corresponding tissue part.
2. The method for detecting lignin and cellulose based on plant stain images according to claim 1, wherein after the RGB channel decomposition of the tissue distribution image, acquiring a first image and a second image comprises:
determining a signal intensity threshold based on channel signal intensity of the tissue distribution image;
screening an R channel image of the cell wall, a G channel image of the cell wall and a B channel image of the cell wall from the channel signal intensity of the tissue distribution image based on the signal intensity threshold;
comparing the R channel image of the cell wall and the G channel image of the cell wall with the B channel image of the cell wall respectively to obtain the first image and the second image;
wherein the channel signal intensities of the tissue distribution image include R-channel signal intensity, G-channel signal intensity, and B-channel signal intensity.
3. The method for detecting lignin and cellulose based on plant stain images according to claim 1, further comprising, after said acquiring the first image and the second image:
respectively carrying out clustering analysis on the first image and the second image to obtain a first clustering result and a second clustering result;
the first clustering result is used for indicating the difference distribution of the lignin content of the plant sample to be detected; the second clustering result is used for indicating the difference distribution of the cellulose content of the plant sample to be tested.
4. The method for detecting lignin and cellulose based on plant staining images according to claim 1, wherein the performing cluster analysis on the first image and the second image to obtain a first clustering result and a second clustering result comprises:
performing R-type clustering analysis on the first image and the second image to respectively obtain a first pixel point proportion and a second pixel point proportion of the first image and the second image in each classification;
and respectively determining the first clustering result and the second clustering result based on the first pixel point proportion and the second pixel point proportion.
5. The method for detecting lignin and cellulose based on plant staining images according to claim 1, wherein the obtaining of the tissue distribution image based on the stained section image of the plant sample to be tested comprises:
converting the stained section image into a Hue Saturration Value color space for foreground extraction to obtain a target image;
and extracting the tissue distribution image based on the target image.
6. The plant stain image-based lignin and cellulose detection method according to claim 1, wherein the stained section image of the plant sample to be tested is collected after white balance correction via a white board within a field of view.
7. A plant stain image-based lignin and cellulose detection system, comprising:
the sample image processing module is used for acquiring a tissue distribution image based on a dyed slice image of a plant sample to be detected;
the composition extraction module is used for obtaining a first image and a second image after RGB channel decomposition is carried out on the tissue distribution image;
the quantification module is used for respectively carrying out signal intensity statistical analysis on the first image and the second image to obtain a first quantification result and a second quantification result;
wherein the stained section image is obtained after performing safranin-fast green staining on the plant sample to be detected; the pixel value of the first image is a ratio of an R-channel signal intensity and a B-channel signal intensity; the pixel value of the second image is a ratio of a G-channel signal intensity and a B-channel signal intensity; the first quantitative result is used for indicating the content of lignin of the plant sample to be detected in the corresponding tissue part; the second quantitative result is used for indicating the content of the cellulose of the plant sample to be tested in the corresponding tissue part.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the method for detecting lignin and cellulose based on plant stain images as claimed in any one of claims 1 to 6.
9. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the plant stain image based lignin and cellulose detection method of any one of claims 1 to 6.
10. A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the plant stain image based lignin and cellulose detection method of any one of claims 1 to 6.
CN202210886368.7A 2022-07-26 2022-07-26 Method and system for detecting lignin and cellulose based on plant staining image Pending CN115346213A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210886368.7A CN115346213A (en) 2022-07-26 2022-07-26 Method and system for detecting lignin and cellulose based on plant staining image

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210886368.7A CN115346213A (en) 2022-07-26 2022-07-26 Method and system for detecting lignin and cellulose based on plant staining image

Publications (1)

Publication Number Publication Date
CN115346213A true CN115346213A (en) 2022-11-15

Family

ID=83949519

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210886368.7A Pending CN115346213A (en) 2022-07-26 2022-07-26 Method and system for detecting lignin and cellulose based on plant staining image

Country Status (1)

Country Link
CN (1) CN115346213A (en)

Similar Documents

Publication Publication Date Title
US11880974B2 (en) Method and device for detecting circulating abnormal cells
Kothari et al. Automatic batch-invariant color segmentation of histological cancer images
JP5996494B2 (en) How to display a digital slide image
US8320655B2 (en) Process and system for analyzing the expression of biomarkers in cells
Rishal et al. WIS‐neuromath enables versatile high throughput analyses of neuronal processes
CN110458835B (en) Image processing method, device, equipment, system and medium
US9607374B2 (en) Color decomposition in histology
Hortinela et al. Identification of abnormal red blood cells and diagnosing specific types of anemia using image processing and support vector machine
JP2009115599A (en) Evaluation system, evaluation method and evaluation program
CN111242961A (en) Automatic film reading method and system for PD-L1 antibody stained section
CN110838094B (en) Pathological section dyeing style conversion method and electronic equipment
WO2012109571A1 (en) Systems and methods for object identification
CN111863118A (en) Method for carrying out TCT and DNA ploidy analysis based on TCT film-making
CN107563427A (en) The method and corresponding use that copyright for oil painting is identified
JP6246978B2 (en) Method for detecting and quantifying fibrosis
EP3567546A1 (en) Image analysis program and image analysis method
CN115564776B (en) Abnormal cell sample detection method and device based on machine learning
CN115346213A (en) Method and system for detecting lignin and cellulose based on plant staining image
JP4897488B2 (en) A system for classifying slides using a scatter plot distribution
Palokangas et al. Segmentation of folds in tissue section images
CN115602311A (en) Pancreatic cancer auxiliary inspection tool based on collagen fiber multivariate parameter analysis
CN114627308A (en) Extraction method and system of bone marrow cell morphological characteristics
CN109919924B (en) Method suitable for cell digital processing of large-batch HE staining pictures
JPWO2018131091A1 (en) Image processing apparatus, image processing method, and image processing program
RU2691768C2 (en) Method of determining colour group of flax fibre

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