CN111144186B - Method and system for automatically identifying microscopic components - Google Patents
Method and system for automatically identifying microscopic components Download PDFInfo
- Publication number
- CN111144186B CN111144186B CN201811317028.2A CN201811317028A CN111144186B CN 111144186 B CN111144186 B CN 111144186B CN 201811317028 A CN201811317028 A CN 201811317028A CN 111144186 B CN111144186 B CN 111144186B
- Authority
- CN
- China
- Prior art keywords
- image data
- identified
- contents
- gray
- minimum value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 239000004079 vitrinite Substances 0.000 claims abstract description 89
- 229920002101 Chitin Polymers 0.000 claims abstract description 19
- 230000001174 ascending effect Effects 0.000 claims abstract description 13
- 238000002310 reflectometry Methods 0.000 claims description 70
- 238000009499 grossing Methods 0.000 claims description 66
- 238000012545 processing Methods 0.000 claims description 52
- 238000001914 filtration Methods 0.000 claims description 40
- 238000009825 accumulation Methods 0.000 claims description 34
- 238000004364 calculation method Methods 0.000 claims description 32
- 239000002734 clay mineral Substances 0.000 claims description 28
- 229910052500 inorganic mineral Inorganic materials 0.000 claims description 27
- 239000011707 mineral Substances 0.000 claims description 27
- 238000009795 derivation Methods 0.000 claims 1
- 239000003245 coal Substances 0.000 description 22
- 238000012935 Averaging Methods 0.000 description 6
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical compound [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 description 6
- 230000002146 bilateral effect Effects 0.000 description 6
- 239000000203 mixture Substances 0.000 description 6
- 239000011593 sulfur Substances 0.000 description 6
- 229910052717 sulfur Inorganic materials 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000005416 organic matter Substances 0.000 description 3
- 239000000843 powder Substances 0.000 description 3
- 241001465754 Metazoa Species 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000011946 reduction process Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
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
- G06V20/698—Matching; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration by the use of histogram techniques
-
- G06T5/70—
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
Abstract
The invention discloses a method and a system for automatically identifying microscopic components, wherein the method comprises the following steps: acquiring initialized image data associated with a target object to be identified, and determining the number of pixel points included in the image data; generating a gray histogram of the image data and determining a plurality of minimum value points of the gray histogram of the image data; sorting the plurality of minimum value points according to the ascending order of the data values to generate a minimum value point sequence; determining a region between any two adjacent minimum value points in the plurality of minimum value points as a region to be identified of the image data, thereby obtaining a plurality of regions to be identified; the content of the vitrinite, the content of the chitin group, and the content of the inertinite of each of a plurality of regions to be identified of the image data are determined.
Description
Technical Field
The invention relates to the technical field of micro-component identification, and in particular relates to a method and a system for automatically identifying micro-components.
Background
The microcomponents originate mainly from residues of various tissues and organs of plants and animals. The microcomponents are not of a specific crystalline form, physical properties and chemical composition nor are they fixed and vary with maturity. The microscopic component contains both visible insoluble organic matter and partially visible soluble organic matter. In addition, the microscopic components also have a substantial portion of kerogen and are in a sub-microscopic finely dispersed distribution and are not directly visible under the mirror. Thus, the microcomponents are not exactly identical to kerogen.
Generally, organic petrology classifies microscopic components into the classes of sapropel, chitin, vitrinite, inertinite, animal organic debris, and secondary organic matter. Each group also contains a plurality of specific microscopic components, and each component has its morphological and optical characteristics.
The basic units that make up the coal can be identified under an optical microscope, where the change from plant remains is known as an organic microscopic component, and mineral impurities in the coal are known as inorganic microscopic components. The microscopic composition of the coal was examined, and the coal was ground into a sheet (thickness: about 0.02 mm) and observed under an optical microscope with transmitted light. The different micro components have different colors, red, yellow, brown, black and the like, and the structures and the forms are also different. However, the research of coal flakes is limited to low and medium coalification degree coals, and medium and high coalification degree coals are unfavorable for the research because the coal flakes are gradually opaque. The coal is ground into light sheets or the coal particles are bonded to form the light powder sheets, and the light powder sheets are observed by reflected light under an optical microscope, and the reflected light color, the morphology, the structure and the protrusions of the light powder sheets are different from each other. Coal with different coalification degrees can be observed under reflected light, so that the light sheet and the pulverized coal light sheet are widely applied. The microscopic components of coal seen in transmitted and reflected light can be divided into organic and inorganic microscopic components
The organic micro-components of coal can be divided into three groups, namely a vitrinite group, a chitin group and an inertinite group, and a plurality of micro-components and micro-sub-components can be separated from each group according to different forms and structures. The identification of microcomponents in the prior art is generally carried out using a manually assisted manner, but such a manually assisted manner of microcomponent identification is inefficient and prone to erroneous identification.
Disclosure of Invention
According to one aspect of the present invention there is provided a method for automatically identifying microscopic components, the method comprising:
acquiring initialized image data associated with a target object to be identified, and determining the number of pixel points included in the image data;
acquiring all gray values of the image data based on the number of pixel points included in the image data, and generating a gray histogram of the image data based on all gray values of the image data;
performing data processing on the image data based on the gray level histogram to determine a plurality of minimum value points of the gray level histogram of the image data;
sorting the plurality of minimum value points according to the ascending order of the data values to generate a minimum value point sequence;
Determining a region between a minimum value point with the minimum data value among the plurality of minimum value points and a data value zero point as a region to be identified of the image data, and determining a region between any two adjacent minimum value points among the plurality of minimum value points as a region to be identified of the image data, thereby obtaining a plurality of regions to be identified;
determining the gray level uniformity of each to-be-identified area in a plurality of to-be-identified areas of the image data, and determining the content of the vitrinite of the image data according to the gray level uniformity of each to-be-identified area;
determining a first accumulated sum of contents of components having lower reflectivity than the vitrinite, accumulated in a full gloss sheet of the image data, subtracting the contents of clay minerals from the first accumulated sum and subtracting the contents of high reflectivity minerals from the first accumulated sum to determine the contents of the shell group of the image data; and
determining a second accumulated sum of contents of components having higher reflectivity than the vitrinite, accumulated in the full gloss sheet of the image data, subtracting the contents of clay minerals from the second accumulated sum and subtracting the contents of high-reflectivity minerals from the second accumulated sum to determine the contents of the inertinite of the image data.
Before acquiring the initialized image data associated with the target object to be identified, the method further comprises the step of shooting a plurality of microscopic images uniformly distributed in positions on the target object to be identified through a high-precision camera installed on a microscope.
And splicing a plurality of microscopic images uniformly distributed at positions on the target object to be identified to generate image data.
Reflectivity and gray scale uniformity of the generated image data are determined.
The generated image data is subjected to an initialization process based on the reflectivity and the gradation uniformity to generate the initialized image data associated with the target object to be recognized.
The initialization process includes: smoothing filtering and gray level equalization.
The data processing of the image data based on the gray histogram includes:
and smoothing the gray level histogram according to a preset mode.
The predetermined manner includes: five-point three smoothing, five-point two smoothing and seven-point two smoothing.
The data processing of the image data based on the gray histogram includes:
the gray histograms are fitted using a taylor series in a piecewise and derivative polynomial manner to generate a fitting function.
And deriving the fitting function, and determining the minimum value point with the first derivative being zero and the second derivative being greater than zero.
The determining the gray uniformity of each of a plurality of regions to be identified of the image data includes:
The gray level uniformity of each of a plurality of regions to be identified of the image data is determined according to a mean value calculation, a variance calculation, a range calculation or a median calculation.
Determining the content of the vitrinite of image data according to the gray level uniformity of each region to be identified comprises:
the number of vitrinite is determined according to the gray uniformity of each region to be identified, and the content of vitrinite of the image data is determined according to the ratio of the number of vitrinite to the total number.
According to another aspect of the present invention there is provided a method for automatically identifying microscopic components, the method comprising:
acquiring a plurality of image data which are associated with a target object to be identified and are subjected to initialization processing, and determining the number of pixel points included in each image data in the plurality of image data;
acquiring all gray values of each image data based on the number of pixel points included in each image data, and generating a gray histogram of each image data based on all gray values of each image data;
performing data processing on each image data based on the gray histogram to determine a plurality of minimum points of the gray histogram of each image data;
Sorting the plurality of minimum value points according to the ascending order of the data values to generate a minimum value point sequence;
determining a region between a minimum value point with the minimum data value among the plurality of minimum value points and a data value zero point as a region to be identified of each image data, and determining a region between any two adjacent minimum value points among the plurality of minimum value points as a region to be identified of each image data, thereby obtaining a plurality of regions to be identified;
determining the gray uniformity of each to-be-identified area in a plurality of to-be-identified areas of each image data, and determining the content of the vitrinite of each image data according to the gray uniformity of each to-be-identified area;
determining a first accumulated sum of contents of components having lower reflectivity than the vitrinite, accumulated in the full gloss sheet of each image data, subtracting the contents of clay minerals from the first accumulated sum and subtracting the contents of high-reflectivity minerals from the first accumulated sum to determine the contents of the shell groups of each image data;
determining a second accumulated sum of contents of components having higher reflectivity than the vitrinite, accumulated in the full gloss sheet of each image data, subtracting the contents of clay minerals from the second accumulated sum and subtracting the contents of high-reflectivity minerals from the second accumulated sum to determine the contents of the inertinite of each image data; and
The average value of the contents of the vitrinite, the chitin group and the inertinite of the plurality of image data is taken as the contents of the vitrinite, the chitin group and the inertinite of the target object to be identified.
According to yet another aspect of the present invention, there is provided a system for automatic identification of microscopic components, the system comprising:
an acquisition unit that acquires initialized image data associated with a target object to be identified, and determines the number of pixels included in the image data;
a generation unit that acquires all gray values of the image data based on the number of pixel points included in the image data, and generates a gray histogram of the image data based on all gray values of the image data;
a processing unit that performs data processing on the image data based on the gradation histogram to determine a plurality of minimum value points of the gradation histogram of the image data;
the sorting unit sorts the plurality of minimum value points according to the ascending order of the data values so as to generate a minimum value point sequence;
an identification unit that determines a region between a minimum value point at which a data value is minimum among the plurality of minimum value points and a data value zero point as a region to be identified of the image data, and determines a region between any two adjacent minimum value points among the plurality of minimum value points as a region to be identified of the image data, thereby obtaining a plurality of regions to be identified;
A first determining unit that determines a gray uniformity of each of a plurality of regions to be identified of the image data, and determines a content of a vitrinite of the image data according to the gray uniformity of each region to be identified;
a second determining unit that determines a first accumulation sum in which contents of components having lower reflectivity than a vitrinite are accumulated in a full gloss sheet of the image data, subtracts the contents of clay minerals from the first accumulation sum, and subtracts the contents of high-reflectivity minerals from the first accumulation sum to determine contents of a vitrinite of the image data; and
and a third determining unit determining a second accumulation sum in which contents of components having higher reflectivity than the vitrinite are accumulated in the full gloss sheet of the image data, subtracting the contents of clay minerals from the second accumulation sum and subtracting the contents of high-reflectivity minerals from the second accumulation sum to determine the contents of the inertinite of the image data.
The system also comprises an initialization unit, wherein a plurality of microscopic images with evenly distributed positions on the target object to be identified are shot by a high-precision camera arranged on the microscope.
The initialization unit splices a plurality of microscopic images uniformly distributed in positions on the target object to be identified to generate image data.
An initialization unit is further included to determine reflectivity and gray uniformity of the generated image data.
The initialization unit performs an initialization process on the generated image data based on the reflectivity and the gradation uniformity to generate the initialized image data associated with the target object to be recognized.
The initialization process includes: smoothing filtering and gray level equalization.
The processing unit performs smoothing processing on the gradation histogram in a predetermined manner.
The predetermined manner includes: five-point three smoothing, five-point two smoothing and seven-point two smoothing.
The processing unit fits the gray level histogram using a taylor series in a piecewise and polynomial-conductive manner to generate a fitting function.
And deriving the fitting function, and determining the minimum value point with the first derivative being zero and the second derivative being greater than zero.
The first determination unit determines the gradation uniformity of each of a plurality of regions to be identified of the image data in accordance with a mean value calculation, variance calculation, range calculation, or median calculation.
The first determining unit determines the number of vitrinite according to the gradation uniformity of each region to be identified, and determines the content of vitrinite of the image data according to the ratio of the number of vitrinite to the total number.
According to yet another aspect of the present invention there is provided a system for automatic identification of microscopic components, the system comprising:
an acquisition unit that acquires a plurality of image data subjected to initialization processing associated with a target object to be identified, and determines the number of pixels included in each of the plurality of image data;
a generation unit that acquires all gray values of each image data based on the number of pixel points included in each image data, and generates a gray histogram of each image data based on all gray values of each image data;
a processing unit that performs data processing on each image data based on the gradation histogram to determine a plurality of minimum value points of the gradation histogram of each image data;
the sorting unit sorts the plurality of minimum value points according to the ascending order of the data values so as to generate a minimum value point sequence;
an identification unit that determines a region between a minimum value point at which a data value is minimum among the plurality of minimum value points and a data value zero point as a region to be identified for each image data, and determines a region between any two adjacent minimum value points among the plurality of minimum value points as a region to be identified for each image data, thereby obtaining a plurality of regions to be identified;
A first determining unit that determines a gradation uniformity of each of a plurality of regions to be identified of each image data, and determines a content of a vitrinite of each image data according to the gradation uniformity of each region to be identified;
a second determining unit determining a first accumulation sum in which contents of components having lower reflectivity than the vitrinite are accumulated in the full gloss sheet of each image data, subtracting the contents of clay minerals from the first accumulation sum and subtracting the contents of high-reflectivity minerals from the first accumulation sum to determine contents of the shell group of each image data;
a third determining unit determining a second accumulation sum in which contents of components having higher reflectivity than the vitrinite are accumulated in the full gloss sheet of each image data, subtracting the contents of clay minerals from the second accumulation sum and subtracting the contents of high-reflectivity minerals from the second accumulation sum to determine contents of the inertinite of each image data; and
and a result determination unit that takes the average value of the contents of the vitrinite, the chitin group and the inertinite of the plurality of image data as the contents of the vitrinite, the chitin group and the inertinite of the target object to be identified.
Drawings
Exemplary embodiments of the present invention may be more completely understood in consideration of the following drawings:
FIG. 1 is a flow chart of a method for automatically identifying microscopic components according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for automatically identifying microscopic components according to another embodiment of the present invention;
FIG. 3 is a flow chart of a method for gray histogram based threshold segmentation in accordance with an embodiment of the present invention;
FIG. 4 is a schematic diagram of a system for automatic identification of microscopic components according to an embodiment of the present invention; and
fig. 5 is a schematic structural view of a system for automatically identifying microscopic components according to another embodiment of the present invention.
Detailed Description
Fig. 1 is a flow chart of a method 100 for automatically identifying microscopic components according to an embodiment of the present invention. As shown in fig. 1, method 100 begins at step 101. In step 101, image data associated with a target object to be identified, which has undergone an initialization process, is acquired, and the number of pixels included in the image data is determined. Wherein the target object to be identified is for example coal. For example, the image data includes 2048×1536 pixel points. Before acquiring the initialized image data associated with the target object to be identified, the method further comprises the step of shooting a plurality of microscopic images uniformly distributed in positions on the target object to be identified through a high-precision camera installed on a microscope. For example 20, 30, 50 or 100 microscopic images with evenly distributed positions on the target object to be identified are captured by means of a high-precision camera mounted on the microscope. And splicing 20, 30, 50 or 100 microscopic images with uniformly distributed positions on the target object to be identified to generate image data. In general, the reflectivity and gray level uniformity of the generated image data may be determined by any existing image stitching means. The generated image data is subjected to an initialization process based on the reflectivity and the gradation uniformity to generate the initialized image data associated with the target object to be recognized. The initialization process includes: smoothing filtering and gray level equalization.
In step 102, all gray values of the image data are acquired based on the number of pixel points included in the image data, and a gray histogram of the image data is generated based on all gray values of the image data. The method determines the gray value of each pixel included in the image data so as to determine all gray values of all pixels of the image data. A gray histogram of the image data indicating a distribution of the restoration values is generated based on all gray values of the image data. In the gray level histogram, the abscissa is a gray level value and the ordinate is the number.
In step 103, the image data is data processed based on the gray level histogram to determine a plurality of minimum value points of the gray level histogram of the image data. Performing data processing on the image data based on the gray histogram includes: and smoothing the gray level histogram according to a preset mode. The predetermined mode comprises the following steps: five-point three smoothing, five-point two smoothing, seven-point two smoothing, etc.
Smoothing purposes are of two types: one is blurring; the other is to eliminate noise. The smoothing filtering in the spatial domain is generally performed by a simple averaging method, i.e. the average brightness value of adjacent pixel points is obtained. The size of the neighborhood is directly related to the smoothing effect, the larger the neighborhood is, the better the smoothing effect is, but the larger the neighborhood is, the larger the smoothing loss of edge information is, so that the output image becomes fuzzy, and the size of the neighborhood needs to be reasonably selected. Therefore, "smoothing processing" is also called "blurring processing", and is a simple image processing method with a high frequency of use. Smoothing is used for many purposes, but is most commonly used to reduce noise or distortion on images. Smoothing is important when reducing the resolution of an image.
The smoothing process includes mean filtering, median filtering, gaussian filtering, and bilateral filtering. The average filtering is a typical linear filtering algorithm, which refers to giving a template to the target pixel on the image, wherein the template includes neighboring pixels around the template (8 pixels around the target pixel as the center, forming a filtering template, i.e. removing the target pixel itself), and replacing the original pixel value with the average value of all the pixels in the template. The median filtering is a nonlinear smoothing technique that sets the gray value of each pixel to the median of the gray values of all pixels within a certain neighborhood window of the point, i.e., the value of the center pixel is replaced with the median (not the average) of all pixel values. Gaussian filtering is a linear smoothing filtering, is suitable for eliminating Gaussian noise, and is widely applied to a noise reduction process of image processing. In popular terms, gaussian filtering is a process of weighted averaging over the entire image, where the value of each pixel is obtained by weighted averaging itself and other pixel values in the neighborhood. The specific operations of gaussian filtering are: each pixel in the image is scanned with a template (or convolution, mask), and the value of the center pixel point of the template is replaced with the weighted average gray value of the pixels in the neighborhood determined by the template. The bilateral filtering is a nonlinear filtering method, is a compromise process combining the spatial proximity of the image and the similarity of pixel values, and simultaneously considers the spatial domain information and the gray level similarity to achieve the purposes of edge protection and denoising. Has the characteristics of simplicity, non-iteration and local. Bilateral filtering can provide a way to not smooth out edges, but at the cost of more processing time.
Performing data processing on the image data based on the gray histogram includes: the gray histograms are fitted using a taylor series in a piecewise and derivative polynomial manner to generate a fitting function. And deriving the fitting function, and determining the minimum value point with the first derivative being zero and the second derivative being greater than zero.
At step 104, the plurality of minimum points are ordered in an ascending order of data values to generate a sequence of minimum points. In the minimum value point sequence, the earlier the ranking, the smaller the data value, and the later the ranking, the larger the data value.
In step 105, a region between a minimum value point at which the data value is minimum among the plurality of minimum value points and a data value zero point is determined as a region to be identified of the image data, and a region between any two adjacent minimum value points among the plurality of minimum value points is determined as a region to be identified of the image data, thereby obtaining a plurality of regions to be identified.
In step 106, the gray uniformity of each of the plurality of regions to be identified of the image data is determined, and the content of the vitrinite of the image data is determined according to the gray uniformity of each region to be identified. Determining the gray uniformity of each of a plurality of regions to be identified of the image data comprises: the gray level uniformity of each of a plurality of regions to be identified of the image data is determined according to a mean value calculation, a variance calculation, a range calculation or a median calculation.
Determining the content of the vitrinite of image data according to the gray level uniformity of each region to be identified comprises: the number of vitrinite is determined according to the gray uniformity of each region to be identified, and the content of vitrinite of the image data is determined according to the ratio of the number of vitrinite to the total number.
In step 107, a first accumulated sum of the contents of components having lower reflectivity than the vitrinite is determined to be accumulated in the full gloss sheet of the image data, and the contents of clay minerals are subtracted from the first accumulated sum and the contents of high reflectivity minerals are subtracted to determine the contents of the chitin group of the image data.
In step 108, a second accumulated sum of the contents of the components having higher reflectivity than the vitrinite is determined to be accumulated in the full gloss sheet of the image data, and the contents of the clay minerals are subtracted from the second accumulated sum to determine the contents of the inertinite of the image data.
After the vitrinite is determined, the clay mineral and other high-reflectivity mineral contents in the coal can be obtained by utilizing the data of dry base ash Ad, total sulfur St (the sum of sulfur in various forms in the coal), component sulfur, ash components and the like in the coal, and the shell group and inert group contents are obtained by respectively subtracting the clay mineral and the high-reflectivity mineral contents after accumulating the components with lower reflectivity than the vitrinite and higher reflectivity than the vitrinite in a total light sheet.
Fig. 2 is a flow chart of a method 200 for automatically identifying microscopic components according to another embodiment of the present invention. As shown in fig. 2, method 200 begins at step 201. In step 201, a plurality of image data subjected to an initialization process associated with a target object to be identified is acquired, and the number of pixels included in each of the plurality of image data is determined. Wherein the target object to be identified is for example coal. The method and the device can acquire 10, 15, 20 and 50 image data which are associated with the target object to be identified and subjected to initialization processing, and determine the microscopic component presented by each image data. The composition of the target object to be identified is determined by calculating the average value of the microscopic composition of each image data.
For example, the image data includes 2048×1536 pixel points. Before acquiring the initialized image data associated with the target object to be identified, the method further comprises the step of shooting a plurality of microscopic images uniformly distributed in positions on the target object to be identified through a high-precision camera installed on a microscope. For example 20, 30, 50 or 100 microscopic images with evenly distributed positions on the target object to be identified are captured by means of a high-precision camera mounted on the microscope. And splicing 20, 30, 50 or 100 microscopic images with uniformly distributed positions on the target object to be identified to generate image data. In general, the reflectivity and gray level uniformity of the generated image data may be determined by any existing image stitching means. The generated image data is subjected to an initialization process based on the reflectivity and the gradation uniformity to generate the initialized image data associated with the target object to be recognized. The initialization process includes: smoothing filtering and gray level equalization.
In step 202, all gray values of each image data are acquired based on the number of pixel points included in each image data, and a gray histogram of each image data is generated based on all gray values of each image data. The present application determines a gray value of each pixel included in each image data to determine all gray values of all pixels of each image data. A gray histogram of the image data indicating the distribution of the restoration values is generated based on all gray values of each image data. In the gray level histogram, the abscissa is a gray level value and the ordinate is the number.
In step 203, data processing is performed on each image data based on the gray level histogram to determine a plurality of minimum value points of the gray level histogram of each image data. Performing data processing on each image data based on the gray histogram includes: and smoothing the gray level histogram according to a preset mode. The predetermined mode comprises the following steps: five-point three smoothing, five-point two smoothing, seven-point two smoothing, etc.
At step 204, the plurality of minimum points are ordered in an ascending order of data values to generate a sequence of minimum points. In the minimum value point sequence, the earlier the ranking, the smaller the data value, and the later the ranking, the larger the data value.
In step 205, a region between a minimum value point at which the data value is minimum among the plurality of minimum value points and the data value zero point is determined as a region to be identified for each image data, and a region between any two adjacent minimum value points among the plurality of minimum value points is determined as a region to be identified for each image data, thereby obtaining a plurality of regions to be identified.
In step 206, the gray uniformity of each of the plurality of regions to be identified of each image data is determined, and the content of the vitrinite of each image data is determined according to the gray uniformity of each region to be identified. Determining the gray uniformity of each of the plurality of regions to be identified for each image data includes: the gray uniformity of each of the plurality of regions to be identified of each image data is determined in accordance with the mean value calculation, variance calculation, range calculation, or median calculation.
Determining the content of the vitrinite of each image data according to the gray uniformity of each region to be identified includes: the number of vitrinite is determined according to the gradation uniformity of each region to be identified, and the content of vitrinite of each image data is determined according to the ratio of the number of vitrinite to the total number.
In step 207, a first accumulated sum of the contents of the components having lower reflectivity than the vitrinite is determined to be accumulated in the full gloss sheet of each image data, and the contents of the clay minerals are subtracted from the first accumulated sum and the contents of the high reflectivity minerals are subtracted to determine the contents of the chitin group of each image data.
At step 208, a second accumulated sum of the contents of the components having higher reflectivity than the vitrinite is determined to be accumulated in the full gloss sheet of each image data, and the contents of the clay minerals are subtracted from the second accumulated sum to determine the contents of the inertinite of each image data.
In step 209, the average of the contents of the vitrinite, chitin and inertinite of the plurality of image data is taken as the contents of the vitrinite, chitin and inertinite of the target object to be identified.
Fig. 3 is a flow chart of a method 300 for gray histogram based threshold segmentation in accordance with an embodiment of the present invention. As shown in fig. 3, method 300 begins at step 301. In step 301, an image gray level histogram is acquired. In effect, a histogram is made of 2048×1536 point gray values for each image. In step 302, smoothing processing is performed: in the conventional method for processing the histogram, there are five-point three-time smoothing, five-point two-time smoothing, seven-point two-time smoothing and the like. In step 303, a taylor series fit is performed, typically using taylor series expansion on complex functions, to fit the histogram with a piecewise, steerable polynomial. At step 304, a derivative is derived, wherein the first derivative f' (x) =0 and the second derivative f "(x) > 0 yields the minimum point of the fitting function. In step 305, a region is defined, wherein the first minimum point is region 1; the first minimum value point-the second minimum value point is a region 2; the N minimum point-255 is the region n+1.
Fig. 4 is a schematic diagram of a system 400 for automatically identifying microscopic components according to an embodiment of the present invention. The system 400 includes: an acquisition unit 401, a generation unit 402, a processing unit 403, a sorting unit 404, an identification unit 405, a first determination unit 406, a second determination unit 407, and a third determination unit 408.
The acquisition unit 401 acquires the initialized image data associated with the target object to be recognized, and determines the number of pixels included in the image data. Wherein the target object to be identified is for example coal. For example, the image data includes 2048×1536 pixel points. Before acquiring the initialized image data associated with the target object to be identified, the method further comprises the step of shooting a plurality of microscopic images uniformly distributed in positions on the target object to be identified through a high-precision camera installed on a microscope. For example 20, 30, 50 or 100 microscopic images with evenly distributed positions on the target object to be identified are captured by means of a high-precision camera mounted on the microscope. And splicing 20, 30, 50 or 100 microscopic images with uniformly distributed positions on the target object to be identified to generate image data. In general, the reflectivity and gray level uniformity of the generated image data may be determined by any existing image stitching means. The generated image data is subjected to an initialization process based on the reflectivity and the gradation uniformity to generate the initialized image data associated with the target object to be recognized. The initialization process includes: smoothing filtering and gray level equalization.
The generation unit 402 acquires all gray values of the image data based on the number of pixel points included in the image data, and generates a gray histogram of the image data based on all gray values of the image data. The method determines the gray value of each pixel included in the image data so as to determine all gray values of all pixels of the image data. A gray histogram of the image data indicating a distribution of the restoration values is generated based on all gray values of the image data. In the gray level histogram, the abscissa is a gray level value and the ordinate is the number.
The processing unit 403 performs data processing on the image data based on the gradation histogram to determine a plurality of minimum value points of the gradation histogram of the image data. Performing data processing on the image data based on the gray histogram includes: and smoothing the gray level histogram according to a preset mode. The predetermined mode comprises the following steps: five-point three smoothing, five-point two smoothing, seven-point two smoothing, etc.
Smoothing purposes are of two types: one is blurring; the other is to eliminate noise. The smoothing filtering in the spatial domain is generally performed by a simple averaging method, i.e. the average brightness value of adjacent pixel points is obtained. The size of the neighborhood is directly related to the smoothing effect, the larger the neighborhood is, the better the smoothing effect is, but the larger the neighborhood is, the larger the smoothing loss of edge information is, so that the output image becomes fuzzy, and the size of the neighborhood needs to be reasonably selected. Therefore, "smoothing processing" is also called "blurring processing", and is a simple image processing method with a high frequency of use. Smoothing is used for many purposes, but is most commonly used to reduce noise or distortion on images. Smoothing is important when reducing the resolution of an image.
The smoothing process includes mean filtering, median filtering, gaussian filtering, and bilateral filtering. The average filtering is a typical linear filtering algorithm, which refers to giving a template to the target pixel on the image, wherein the template includes neighboring pixels around the template (8 pixels around the target pixel as the center, forming a filtering template, i.e. removing the target pixel itself), and replacing the original pixel value with the average value of all the pixels in the template. The median filtering is a nonlinear smoothing technique that sets the gray value of each pixel to the median of the gray values of all pixels within a certain neighborhood window of the point, i.e., the value of the center pixel is replaced with the median (not the average) of all pixel values. Gaussian filtering is a linear smoothing filtering, is suitable for eliminating Gaussian noise, and is widely applied to a noise reduction process of image processing. In popular terms, gaussian filtering is a process of weighted averaging over the entire image, where the value of each pixel is obtained by weighted averaging itself and other pixel values in the neighborhood. The specific operations of gaussian filtering are: each pixel in the image is scanned with a template (or convolution, mask), and the value of the center pixel point of the template is replaced with the weighted average gray value of the pixels in the neighborhood determined by the template. The bilateral filtering is a nonlinear filtering method, is a compromise process combining the spatial proximity of the image and the similarity of pixel values, and simultaneously considers the spatial domain information and the gray level similarity to achieve the purposes of edge protection and denoising. Has the characteristics of simplicity, non-iteration and local. Bilateral filtering can provide a way to not smooth out edges, but at the cost of more processing time.
Performing data processing on the image data based on the gray histogram includes: the gray histograms are fitted using a taylor series in a piecewise and derivative polynomial manner to generate a fitting function. And deriving the fitting function, and determining the minimum value point with the first derivative being zero and the second derivative being greater than zero.
The sorting unit 404 sorts the plurality of minimum value points in an ascending order of the data values to generate a minimum value point sequence. In the minimum value point sequence, the earlier the ranking, the smaller the data value, and the later the ranking, the larger the data value.
The recognition unit 405 determines a region between a minimum value point at which the data value is smallest among the plurality of minimum value points and a data value zero point as a region to be recognized of the image data, and a region between any two adjacent minimum value points among the plurality of minimum value points as a region to be recognized of the image data, thereby obtaining a plurality of regions to be recognized.
The first determining unit 406 determines the gradation uniformity of each of the plurality of regions to be identified of the image data, and determines the content of the vitrinite of the image data according to the gradation uniformity of each region to be identified. Determining the gray uniformity of each of a plurality of regions to be identified of the image data comprises: the gray level uniformity of each of a plurality of regions to be identified of the image data is determined according to a mean value calculation, a variance calculation, a range calculation or a median calculation.
Determining the content of the vitrinite of image data according to the gray level uniformity of each region to be identified comprises: the number of vitrinite is determined according to the gray uniformity of each region to be identified, and the content of vitrinite of the image data is determined according to the ratio of the number of vitrinite to the total number.
The second determining unit 407 determines a first accumulation sum in which contents of components having lower reflectivity than the vitrinite are accumulated in the full gloss sheet of the image data, subtracts the contents of clay minerals and subtracts the contents of high-reflectivity minerals from the first accumulation sum to determine the contents of the chitin groups of the image data.
The third determination unit 408 determines a second accumulation sum in which contents of components having higher reflectivity than the vitrinite are accumulated in the full gloss sheet of the image data, subtracts the contents of clay minerals from the second accumulation sum, and subtracts the contents of high-reflectivity minerals from the second accumulation sum to determine the contents of the inertinite of the image data.
After the vitrinite is determined, the clay mineral and other high-reflectivity mineral contents in the coal can be obtained by utilizing the data of dry base ash Ad, total sulfur St (the sum of sulfur in various forms in the coal), component sulfur, ash components and the like in the coal, and the shell group and inert group contents are obtained by respectively subtracting the clay mineral and the high-reflectivity mineral contents after accumulating the components with lower reflectivity than the vitrinite and higher reflectivity than the vitrinite in a total light sheet.
Fig. 5 is a schematic diagram of a system 500 for automatic identification of microscopic components according to another embodiment of the present invention. The system 500 includes: an acquisition unit 501, a generation unit 502, a processing unit 503, a sorting unit 504, an identification unit 505, a first determination unit 506, a second determination unit 507, a third determination unit 508, and a result determination unit 509.
The acquisition unit 501 acquires a plurality of image data subjected to initialization processing associated with a target object to be identified, and determines the number of pixels included in each of the plurality of image data. Wherein the target object to be identified is for example coal. The method and the device can acquire 10, 15, 20 and 50 image data which are associated with the target object to be identified and subjected to initialization processing, and determine the microscopic component presented by each image data. The composition of the target object to be identified is determined by calculating the average value of the microscopic composition of each image data.
For example, the image data includes 2048×1536 pixel points. Before acquiring the initialized image data associated with the target object to be identified, the method further comprises the step of shooting a plurality of microscopic images uniformly distributed in positions on the target object to be identified through a high-precision camera installed on a microscope. For example 20, 30, 50 or 100 microscopic images with evenly distributed positions on the target object to be identified are captured by means of a high-precision camera mounted on the microscope. And splicing 20, 30, 50 or 100 microscopic images with uniformly distributed positions on the target object to be identified to generate image data. In general, the reflectivity and gray level uniformity of the generated image data may be determined by any existing image stitching means. The generated image data is subjected to an initialization process based on the reflectivity and the gradation uniformity to generate the initialized image data associated with the target object to be recognized. The initialization process includes: smoothing filtering and gray level equalization.
The generating unit 502 acquires all gray values of each image data based on the number of pixel points included in each image data, and generates a gray histogram of each image data based on all gray values of each image data. The present application determines a gray value of each pixel included in each image data to determine all gray values of all pixels of each image data. A gray histogram of the image data indicating the distribution of the restoration values is generated based on all gray values of each image data. In the gray level histogram, the abscissa is a gray level value and the ordinate is the number.
The processing unit 503 performs data processing on each image data based on the gradation histogram to determine a plurality of minimum value points of the gradation histogram of each image data. Performing data processing on each image data based on the gray histogram includes: and smoothing the gray level histogram according to a preset mode. The predetermined mode comprises the following steps: five-point three smoothing, five-point two smoothing, seven-point two smoothing, etc.
The sorting unit 504 sorts the plurality of minimum value points in ascending order of the data values to generate a minimum value point sequence. In the minimum value point sequence, the earlier the ranking, the smaller the data value, and the later the ranking, the larger the data value.
The identifying unit 505 determines a region between a minimum value point at which the data value is smallest among the plurality of minimum value points and the data value zero point as a region to be identified for each image data, and a region between any two adjacent minimum value points among the plurality of minimum value points as a region to be identified for each image data, thereby obtaining a plurality of regions to be identified.
The first determining unit 506 determines the gradation uniformity of each of the plurality of regions to be recognized of each image data, and determines the content of the vitrinite of each image data according to the gradation uniformity of each region to be recognized. Determining the gray uniformity of each of the plurality of regions to be identified for each image data includes: the gray uniformity of each of the plurality of regions to be identified of each image data is determined in accordance with the mean value calculation, variance calculation, range calculation, or median calculation.
Determining the content of the vitrinite of each image data according to the gray uniformity of each region to be identified includes: the number of vitrinite is determined according to the gradation uniformity of each region to be identified, and the content of vitrinite of each image data is determined according to the ratio of the number of vitrinite to the total number.
The second determination unit 507 determines a first accumulation sum in which contents of components having lower reflectivity than the vitrinite are accumulated in the full gloss sheet of each image data, subtracts the contents of clay minerals and subtracts the contents of high-reflectivity minerals from the first accumulation sum to determine the contents of the chitin groups of each image data.
The third determination unit 508 determines a second accumulation sum in which contents of components having higher reflectivity than the vitrinite are accumulated in the full gloss sheet of each image data, subtracts the contents of the clay mineral from the second accumulation sum, and subtracts the contents of the high-reflectivity mineral from the second accumulation sum to determine the contents of the inertinite of each image data.
The result determination unit 509 regards the average of the contents of the vitrinite, chitin and inertinite of the plurality of image data as the contents of the vitrinite, chitin and inertinite of the target object to be identified.
The invention has been described with reference to a few embodiments. However, as is well known to those skilled in the art, other embodiments than the above disclosed invention are equally possible within the scope of the invention, as defined by the appended patent claims.
Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise therein. All references to "a/an/the [ means, component, etc. ]" are to be interpreted openly as referring to at least one instance of said means, component, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless explicitly stated.
Claims (10)
1. A method for automatically identifying microscopic components, the method comprising:
acquiring initialized image data associated with a target object to be identified, and determining the number of pixel points included in the image data;
acquiring all gray values of the image data based on the number of pixel points included in the image data, and generating a gray histogram of the image data based on all gray values of the image data;
performing data processing on the image data based on the gray level histogram to determine a plurality of minimum value points of the gray level histogram of the image data;
sorting the plurality of minimum value points according to the ascending order of the data values to generate a minimum value point sequence;
determining a region between a minimum value point with the minimum data value among the plurality of minimum value points and a data value zero point as a region to be identified of the image data, and determining a region between any two adjacent minimum value points among the plurality of minimum value points as a region to be identified of the image data, thereby obtaining a plurality of regions to be identified;
determining the gray level uniformity of each to-be-identified area in a plurality of to-be-identified areas of the image data, and determining the content of the vitrinite of the image data according to the gray level uniformity of each to-be-identified area;
Determining a first accumulated sum of contents of components having lower reflectivity than the vitrinite, accumulated in a full gloss sheet of the image data, subtracting the contents of clay minerals from the first accumulated sum and subtracting the contents of high reflectivity minerals from the first accumulated sum to determine the contents of the shell group of the image data; and
determining a second accumulated sum of contents of components having higher reflectivity than the vitrinite, accumulated in the full gloss sheet of the image data, subtracting the contents of clay minerals from the second accumulated sum and subtracting the contents of high-reflectivity minerals from the second accumulated sum to determine the contents of the inertinite of the image data.
2. The method according to claim 1, further comprising, before acquiring the initialized image data associated with the target object to be identified, capturing a plurality of microscopic images uniformly distributed in position on the target object to be identified by a high-precision camera mounted on a microscope;
splicing a plurality of microscopic images uniformly distributed in positions on a target object to be identified to generate image data;
determining reflectivity and gray uniformity of the generated image data;
initializing the generated image data based on the reflectivity and the gray uniformity to generate initialized image data associated with the target object to be identified;
The initialization process includes: smoothing filtering and gray level balancing;
the data processing of the image data based on the gray histogram includes:
smoothing the gray level histogram in a preset mode;
the predetermined manner includes: five-point three smoothing, five-point two smoothing and seven-point two smoothing.
3. The method of claim 1 or 2, the data processing of the image data based on the grayscale histogram comprising:
fitting the gray histogram using a taylor series in a segmented and derivative polynomial manner to generate a fitting function;
and deriving the fitting function, and determining the minimum value point with the first derivative being zero and the second derivative being greater than zero.
4. The method of claim 1 or 2, the determining gray level uniformity for each of a plurality of regions of the image data comprising:
determining the gray level uniformity of each of a plurality of regions to be identified of the image data according to means calculation, variance calculation, range calculation or median calculation;
determining the content of the vitrinite of image data according to the gray level uniformity of each region to be identified comprises:
The number of vitrinite is determined according to the gray uniformity of each region to be identified, and the content of vitrinite of the image data is determined according to the ratio of the number of vitrinite to the total number.
5. A method for automatically identifying microscopic components, the method comprising:
acquiring a plurality of image data which are associated with a target object to be identified and are subjected to initialization processing, and determining the number of pixel points included in each image data in the plurality of image data;
acquiring all gray values of each image data based on the number of pixel points included in each image data, and generating a gray histogram of each image data based on all gray values of each image data;
performing data processing on each image data based on the gray histogram to determine a plurality of minimum points of the gray histogram of each image data;
sorting the plurality of minimum value points according to the ascending order of the data values to generate a minimum value point sequence;
determining a region between a minimum value point with the minimum data value among the plurality of minimum value points and a data value zero point as a region to be identified of each image data, and determining a region between any two adjacent minimum value points among the plurality of minimum value points as a region to be identified of each image data, thereby obtaining a plurality of regions to be identified;
Determining the gray uniformity of each to-be-identified area in a plurality of to-be-identified areas of each image data, and determining the content of the vitrinite of each image data according to the gray uniformity of each to-be-identified area;
determining a first accumulated sum of contents of components having lower reflectivity than the vitrinite, accumulated in the full gloss sheet of each image data, subtracting the contents of clay minerals from the first accumulated sum and subtracting the contents of high-reflectivity minerals from the first accumulated sum to determine the contents of the shell groups of each image data;
determining a second accumulated sum of contents of components having higher reflectivity than the vitrinite, accumulated in the full gloss sheet of each image data, subtracting the contents of clay minerals from the second accumulated sum and subtracting the contents of high-reflectivity minerals from the second accumulated sum to determine the contents of the inertinite of each image data; and
the average value of the contents of the vitrinite, the chitin group and the inertinite of the plurality of image data is taken as the contents of the vitrinite, the chitin group and the inertinite of the target object to be identified.
6. A system for automatically identifying microscopic components, the system comprising:
an acquisition unit that acquires initialized image data associated with a target object to be identified, and determines the number of pixels included in the image data;
A generation unit that acquires all gray values of the image data based on the number of pixel points included in the image data, and generates a gray histogram of the image data based on all gray values of the image data;
a processing unit that performs data processing on the image data based on the gradation histogram to determine a plurality of minimum value points of the gradation histogram of the image data;
the sorting unit sorts the plurality of minimum value points according to the ascending order of the data values so as to generate a minimum value point sequence;
an identification unit that determines a region between a minimum value point at which a data value is minimum among the plurality of minimum value points and a data value zero point as a region to be identified of the image data, and determines a region between any two adjacent minimum value points among the plurality of minimum value points as a region to be identified of the image data, thereby obtaining a plurality of regions to be identified;
a first determining unit that determines a gray uniformity of each of a plurality of regions to be identified of the image data, and determines a content of a vitrinite of the image data according to the gray uniformity of each region to be identified;
a second determining unit that determines a first accumulation sum in which contents of components having lower reflectivity than a vitrinite are accumulated in a full gloss sheet of the image data, subtracts the contents of clay minerals from the first accumulation sum, and subtracts the contents of high-reflectivity minerals from the first accumulation sum to determine contents of a vitrinite of the image data; and
And a third determining unit determining a second accumulation sum in which contents of components having higher reflectivity than the vitrinite are accumulated in the full gloss sheet of the image data, subtracting the contents of clay minerals from the second accumulation sum and subtracting the contents of high-reflectivity minerals from the second accumulation sum to determine the contents of the inertinite of the image data.
7. The system according to claim 6, further comprising an initializing unit that photographs a plurality of microscopic images uniformly distributed in position on the target object to be identified by a high-precision camera mounted on the microscope;
the initialization unit is used for splicing a plurality of microscopic images uniformly distributed at the positions on the target object to be identified so as to generate image data;
the device also comprises an initialization unit, a display unit and a display unit, wherein the initialization unit is used for determining the reflectivity and gray uniformity of the generated image data;
an initializing unit performs initializing processing on the generated image data based on the reflectivity and the gradation uniformity to generate initializing-processed image data associated with the target object to be recognized;
the initialization process includes: smoothing filtering and gray level equalization.
8. The system according to claim 6 or 7, the processing unit smoothing the gradation histogram in a predetermined manner;
The predetermined manner includes: five-point three smoothing, five-point two smoothing and seven-point two smoothing.
9. The system of claim 6 or 7, the processing unit fitting the gray level histogram using taylor series in a piecewise and derivative polynomial manner to generate a fitting function;
conducting derivation on the fitting function, and determining a minimum value point with a first derivative being zero and a second derivative being greater than zero;
the first determining unit determines gray uniformity of each of a plurality of regions to be identified of the image data according to a mean value calculation, a variance calculation, a range calculation or a median calculation;
the first determining unit determines the number of vitrinite according to the gradation uniformity of each region to be identified, and determines the content of vitrinite of the image data according to the ratio of the number of vitrinite to the total number.
10. A system for automatically identifying microscopic components, the system comprising:
an acquisition unit that acquires a plurality of image data subjected to initialization processing associated with a target object to be identified, and determines the number of pixels included in each of the plurality of image data;
A generation unit that acquires all gray values of each image data based on the number of pixel points included in each image data, and generates a gray histogram of each image data based on all gray values of each image data;
a processing unit that performs data processing on each image data based on the gradation histogram to determine a plurality of minimum value points of the gradation histogram of each image data;
the sorting unit sorts the plurality of minimum value points according to the ascending order of the data values so as to generate a minimum value point sequence;
an identification unit that determines a region between a minimum value point at which a data value is minimum among the plurality of minimum value points and a data value zero point as a region to be identified for each image data, and determines a region between any two adjacent minimum value points among the plurality of minimum value points as a region to be identified for each image data, thereby obtaining a plurality of regions to be identified;
a first determining unit that determines a gradation uniformity of each of a plurality of regions to be identified of each image data, and determines a content of a vitrinite of each image data according to the gradation uniformity of each region to be identified;
a second determining unit determining a first accumulation sum in which contents of components having lower reflectivity than the vitrinite are accumulated in the full gloss sheet of each image data, subtracting the contents of clay minerals from the first accumulation sum and subtracting the contents of high-reflectivity minerals from the first accumulation sum to determine contents of the shell group of each image data;
A third determining unit determining a second accumulation sum in which contents of components having higher reflectivity than the vitrinite are accumulated in the full gloss sheet of each image data, subtracting the contents of clay minerals from the second accumulation sum and subtracting the contents of high-reflectivity minerals from the second accumulation sum to determine contents of the inertinite of each image data; and
and a result determination unit that takes the average value of the contents of the vitrinite, the chitin group and the inertinite of the plurality of image data as the contents of the vitrinite, the chitin group and the inertinite of the target object to be identified.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811317028.2A CN111144186B (en) | 2018-11-06 | 2018-11-06 | Method and system for automatically identifying microscopic components |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811317028.2A CN111144186B (en) | 2018-11-06 | 2018-11-06 | Method and system for automatically identifying microscopic components |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111144186A CN111144186A (en) | 2020-05-12 |
| CN111144186B true CN111144186B (en) | 2023-05-05 |
Family
ID=70515280
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811317028.2A Active CN111144186B (en) | 2018-11-06 | 2018-11-06 | Method and system for automatically identifying microscopic components |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111144186B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112986244A (en) * | 2020-11-06 | 2021-06-18 | 长江大学 | Large-visual-field rock sample organic component microscopic image acquisition method |
| CN112233111A (en) * | 2020-11-18 | 2021-01-15 | 安徽国钜工程机械科技有限公司 | Tunnel gap detection method based on digital image processing |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5841882A (en) * | 1993-12-10 | 1998-11-24 | Sollac | Automatic process for the maceral analysis and the determination of the reflectance of vitrinite in coals |
| CN102507493A (en) * | 2011-10-24 | 2012-06-20 | 上海理工大学 | Method for measuring interaction between vitrinite and inertinite in coal during pyrolysis process |
| CN108346147A (en) * | 2018-02-08 | 2018-07-31 | 辽宁翔舜科技有限公司 | A kind of macerals is fast automatic to accurately identify technical method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060258018A1 (en) * | 2003-09-23 | 2006-11-16 | Curl Claire L | Method and apparatus for determining the area or confluency of a sample |
-
2018
- 2018-11-06 CN CN201811317028.2A patent/CN111144186B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5841882A (en) * | 1993-12-10 | 1998-11-24 | Sollac | Automatic process for the maceral analysis and the determination of the reflectance of vitrinite in coals |
| CN102507493A (en) * | 2011-10-24 | 2012-06-20 | 上海理工大学 | Method for measuring interaction between vitrinite and inertinite in coal during pyrolysis process |
| CN108346147A (en) * | 2018-02-08 | 2018-07-31 | 辽宁翔舜科技有限公司 | A kind of macerals is fast automatic to accurately identify technical method |
Non-Patent Citations (2)
| Title |
|---|
| 基于灰度直方图拟合曲线的数字图像多阈值分割技术研究;梁忠伟 等;现代制造工程(09);103-106 * |
| 煤中有机显微组分自动识别初步研究;丁华 等;煤质技术(01);1-5 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111144186A (en) | 2020-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Senthilkumaran et al. | Image segmentation by using thresholding techniques for medical images | |
| CN109242791B (en) | Batch repair method for damaged plant leaves | |
| CN106780486B (en) | Steel plate surface defect image extraction method | |
| CN108447068B (en) | Ternary diagram automatic generation method and foreground extraction method using ternary diagram | |
| CN111144186B (en) | Method and system for automatically identifying microscopic components | |
| CN105447489B (en) | A kind of character of picture OCR identifying system and background adhesion noise cancellation method | |
| CN102609704A (en) | Detecting device and method of video monitoring image movement targets under foggy weather conditions | |
| CN107610144B (en) | Improved infrared image segmentation method based on maximum inter-class variance method | |
| CN110060221B (en) | Bridge vehicle detection method based on unmanned aerial vehicle aerial image | |
| CN107038690B (en) | Moving shadow removing method based on multi-feature fusion | |
| CN112750089B (en) | Optical remote sensing image defogging method based on local block maximum and minimum pixel prior | |
| Gupta et al. | Fast single image haze removal method for inhomogeneous environment using variable scattering coefficient | |
| Zhou et al. | A novel adaptive local thresholding approach for segmentation of HEp-2 cell images | |
| Yu et al. | MSER based shadow detection in high resolution remote sensing image | |
| CN109635679B (en) | Real-time target paper positioning and loop line identification method | |
| CN202495068U (en) | Video surveillance image moving target detection device under foggy weather condition | |
| CN113298730B (en) | Defogging restoration method based on image decomposition | |
| Lin et al. | Locating license plate based on edge features of intensity and saturation subimages | |
| Sanap et al. | License plate recognition system for Indian vehicles | |
| Khan et al. | Shadow removal from digital images using multi-channel binarization and shadow matting | |
| CN113205469A (en) | Single image defogging method based on improved dark channel | |
| CN113538297A (en) | Image rain removing method based on gradient priori knowledge and N-S equation | |
| Yadav et al. | Single image dehazing using adaptive gamma correction method | |
| Kamanga | An Adaptive Approach to Improve Canny Method for Edge Detection | |
| Yan et al. | A boosted decision tree approach to shadow detection in scanning electron microscope (SEM) images for machine vision applications |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |