CN113936021A - Soft aggregation molecule identification method and system based on SEM image - Google Patents
Soft aggregation molecule identification method and system based on SEM image Download PDFInfo
- Publication number
- CN113936021A CN113936021A CN202111101266.1A CN202111101266A CN113936021A CN 113936021 A CN113936021 A CN 113936021A CN 202111101266 A CN202111101266 A CN 202111101266A CN 113936021 A CN113936021 A CN 113936021A
- Authority
- CN
- China
- Prior art keywords
- gray scale
- array
- aset
- sub
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a soft agglomerated molecule identification method and system based on an SEM image, which are characterized in that a gray scale image of the SEM image is obtained, an edge line of the gray scale image is obtained through an edge detection algorithm, a sub-image set is obtained from the gray scale image by using the edge line, a molecule agglomeration value is calculated for a plurality of sub-images, the probability of the existence of soft agglomerated molecules is calculated according to the molecule agglomeration value of each sub-image and output is carried out, and therefore the effect of judging whether the soft agglomerated molecules exist or not is achieved only by calculating and comparing the SEM images before and after processing.
Description
Technical Field
The disclosure belongs to the field of image processing and molecular recognition, and particularly relates to a soft agglomerated molecule recognition method and system based on an SEM image.
Background
Soft agglomeration is a nanoparticle phenomenon caused by electrostatic and van der waals forces, and is ubiquitous in chemical engineering and process production. The SEM image is an important means for observing the soft agglomeration phenomenon, and is very effective for observing and identifying soft agglomerated molecules. The image recognition algorithm based on computer vision is beneficial to distinguishing the soft molecular agglomeration phenomenon through the SEM image, and can be widely applied to characteristic comparison between the SEM image before processing and the SEM image after processing, so that the optimization and improvement of the recognition of the soft agglomeration phenomenon are realized.
Disclosure of Invention
The present invention is directed to a method and system for identifying soft agglomerated molecules based on SEM images, so as to solve one or more technical problems in the prior art and provide at least one useful choice or creation condition.
By comparing the characteristics of the SEM image before processing with those of the SEM image after processing, it is possible to discriminate whether or not soft agglomerated molecules are present.
The invention provides a soft agglomerated molecule identification method and system based on an SEM image, which are used for obtaining a gray scale image of the SEM image and obtaining an edge line of the gray scale image through an edge detection algorithm, further calculating a molecular agglomeration value of a sub-image set obtained from the gray scale image by using the edge line for a plurality of sub-images, and calculating and outputting the probability of the existence of soft agglomerated molecules according to the molecular agglomeration value of each sub-image, thereby realizing the effect of judging whether the soft agglomerated molecules exist through comparing the SEM images before and after processing.
In order to achieve the above objects, according to an aspect of the present disclosure, there is provided a soft agglomerated molecule identification method based on SEM images, the method including the steps of:
s100, acquiring a gray scale image of the SEM image;
s200, obtaining an edge line of the gray-scale image through an edge detection algorithm;
s300, dividing the gray graph into a plurality of sub-graphs through edge lines, and forming a sub-graph set by all the sub-graphs;
s400, calculating a molecular clustering value of each subgraph in the subgraph set;
and S500, calculating the probability of the soft agglomerated molecules according to the molecular agglomeration values of the sub-images and outputting the probability.
In S100, the SEM image is: taking 1g of nano SiO2, CaCO3 and surface modified nano SiO2 or CaCO; placed on a slide and scraped flat against another slide to compact it to obtain a flat surface, and imaged under a scanning electron microscope to acquire the resulting SEM image.
Further, in S100, the method of acquiring the grayscale map of the SEM image includes: inputting a first SEM image, and obtaining a gray scale image of the first SEM image through a gray scale image algorithm and marking the gray scale image as a first gray scale image; and inputting a second SEM image, and obtaining a gray scale image of the second SEM image through a gray scale image algorithm to be recorded as a second gray scale image.
The first SEM image is an SEM image obtained before physical or chemical treatment, and the second SEM image is an SEM image obtained after physical or chemical treatment.
Preferably, the physical or chemical treatment is a surfactant modification of the SiO2 nanoparticles.
Preferably, the first SEM image is an SEM image of SiO2, and the second SEM image is an SEM image obtained by: preparing a hydrophobic surface SiO2 obtained by treating SiO2 by a method recorded in a university of Zhejiang, academic edition, 2011(2), 189 and 193 (namely modifying an SiO2 nanoparticle surfactant) on the basis of a super-hydrophobic surface of CaCO3/SiO2 composite particles, wherein the academic edition is scientific and academic edition; and acquiring an SEM image of the SiO2 on the hydrophobic surface by using a scanning electron microscope to obtain a second SEM image.
Further, in S200, the method for obtaining the edge line of the gray scale map by the edge detection algorithm includes: obtaining a plurality of edge lines on the first gray scale image by using an edge detection algorithm for the first gray scale image, and taking a set of the plurality of edge lines on the first gray scale image as a first edge line set; and obtaining a plurality of edge lines on the second gray scale image by using an edge detection algorithm for the second gray scale image, and taking a set of the plurality of edge lines on the second gray scale image as a second edge line set.
Further, in S300, the gray-scale map is divided into a plurality of sub-maps by edge lines, and a method for forming a sub-map set by all the sub-maps includes:
on the first gray scale map, defining a geometric figure formed by taking one or more edge lines belonging to a first edge line set as edges on the first gray scale map as a first sub-figure, wherein the first sub-figure is a sub-figure of the first gray scale map, and defining a set formed by one or more first sub-figures on the first gray scale map as a first sub-figure set;
and on the second gray scale map, defining a geometric figure formed by taking one or more edge lines belonging to the second edge line set as edges on the second gray scale map as a back sub-graph, wherein the back sub-graph is a sub-graph of the second gray scale map, and a set formed by one or more back sub-graphs on the second gray scale map is marked as a second sub-graph set.
Further, in S400, the method for calculating the molecular clustering value for the plurality of subgraphs is:
marking a first subgraph set as a set Aset, the number of elements in the set Aset is n, a variable i represents the serial number of the elements in the set Aset, i belongs to [1, n ], the element with the serial number of i in the set Aset is marked as Aset (i), a second subgraph set is marked as a set Bset, the number of the elements in the set Bset is m, a variable j represents the serial number of the elements in the set Bset, j belongs to [1, m ], and the element with the serial number of j in the set Bset is marked as Bset (j);
setting an initialization vector Mr, wherein the numerical value of each element in the initialization vector Mr represents an initial probability value, and the size of the initialization vector Mr is k-dimension;
wherein, the value of k in the Mr is obtained by defining a Min () function as a function of finding the smallest element in one or more input arrays, vectors, sequences or sets or the smallest element in a plurality of input values, a len () function is a function of calculating the number of elements in one or more input arrays, vectors, matrices, sequences or sets, as Aset (i) and Bset (j) are both obtained from the image of the gray-scale map and are composed of pixels, len (Aset (i)) represents the number of pixels in Aset (i), len (Aset (i)) } represents a set composed of the number of pixels in each element in the set Aset, len (Bset (j)) represents the number of pixels in Bset (j), len (Bset () } represents a set composed of the number of pixels in each element in the set Aset, the avg () function is a function for obtaining a rounded down arithmetic mean, avg ({ len (Aset (i)) }) represents a rounded down arithmetic mean for obtaining the number of pixel points in each element in Aset, avg ({ len (Bset (j)) }) represents a rounded down arithmetic mean for obtaining the number of pixel points in each element in Bset, and Min (avg ({ len (Aset (i)) }), avg ({ len (Bset (j)) })) represents the smallest of two values for obtaining avg ({ len (Aset (i)) }) and avg ({ len (Bset (j)) }), and the value of k is Min (avg ({ len (Aset (i)) }), avg ({ len (bs (j)) });
defining the molecular clustering value as a numerical value for measuring soft agglomerated molecules in subgraphs, and calculating the molecular clustering value of a plurality of subgraphs of the first gray level graph by the following specific steps:
s401-1, starting a program; acquiring an initialization vector Mr; acquiring a set Aset; setting the initial value of i as 1; setting an empty array Tset; go to S401-2;
s401-2, acquiring an element with sequence number i in the set Aset as Aset (i), further acquiring the number of pixel points in Aset (i) as an, setting ai to represent the sequence number of the pixel points in Aset (i), wherein ai belongs to [1, an ], and marking the pixel value of the pixel point with sequence number ai in Aset (i) as A (ai); setting ai as 1; setting an empty array tseq; go to S401-31;
s401-31, judging whether constraint conditions (an-ai) ≧ k-1 are met, if yes, turning to S401-32, and if not, turning to S401-33;
s401-32, acquiring a k-dimensional array composed of pixel values of all pixel points with sequence numbers ai to ai + k-1 in Aset (i) as an array V (ai); go to S401-4;
s401-33, acquiring pixel values of a total of an-ai +1 pixel points from the serial number ai to the serial number an in the aset (i), and connecting k- (an-ai +1) numerical values which are zero behind the pixel values to form a k-dimensional array V (ai); go to S401-4;
s401-4, setting a variable q to represent the sequence number of an array or an element in a vector with a dimension of k, wherein q belongs to [1, k ], V (ai) q represents an element with the sequence number of q in an array V (ai), and Mr (q) represents an element with the sequence number of q in an initialization vector Mr; setting a variable t (ai) to be a variable used in the process of calculating the array V (ai), wherein the formula for calculating t (ai) according to the initialization vector Mr and the array V (ai) is as follows:
adding the t (ai) obtained by the calculation into an array tseq; go to S401-5;
s401-5, judging whether the number of elements in the array tseq is larger than or equal to an, if so, turning to the step S401-6, otherwise, turning to the step S401-7;
s401-6, calculating and obtaining the arithmetic mean of each element in the array tseq as t _ i, adding t _ i into the array Tset, and taking t _ i as an element with the sequence number of i in the array Tset; go to step S401-8;
s401-7, increasing the value of ai by 1; go to step S401-31;
s401-8, judging whether i < n is satisfied, if so, increasing the value of i by 1 and then turning to S401-2, otherwise, turning to the step S401-9;
s401-9, outputting the Tset; ending the program;
wherein, Tset is a molecular clustering value obtained by calculating each subgraph of the first gray scale map;
the specific steps of calculating the molecular clustering value of the multiple subgraphs of the second gray scale map are as follows:
s402-1, starting a program; acquiring an initialization vector Mr; acquiring a set Bset; setting the initial value of j to 1; setting an empty array Lset; go to S402-2;
s402-2, acquiring an element with a sequence number j in a set Bset as Bset (j), further acquiring the number of pixel points in the Bset (j) as bm, setting bj to represent the sequence number of the pixel points in the Bset (j), setting bj to be [1, bm ], and recording the pixel value of the pixel point with the sequence number bj in the Bset (j) as B (bj); setting the initial value of bj as 1; setting an empty array lseq; go to S402-31;
s402-31, judging whether constraint conditions (bm-bj) ≧ k-1 are met, if yes, turning to S402-32, and if not, turning to S402-33;
s402-32, acquiring a k-dimensional array composed of pixel values with sequence numbers bj to bj + k-1 in Bset (j) as an array W (bj); go to S402-4;
s402-33, obtaining pixel values of bm-bj +1 pixel points with sequence number bj to sequence number bm in Bset (j), and connecting k- (bm-bj +1) numerical values with zero at the back to form a k-dimensional array W (bj); go to S402-4;
s402-4, setting a variable q to represent the sequence number of an array or an element in a vector with a dimension of k, wherein q belongs to [1, k ], W (bj) q represents an element with the sequence number of q in an array W (bj), and Mr (q) represents an element with the sequence number of q in an initialization vector Mr; setting variables l (bj) as variables used in the process of calculating the arrays W (bj), wherein the formula for calculating l (bj) according to the initialization vector Mr and the arrays W (bj) is as follows:
adding l (bj) obtained by the calculation into an array lseq; go to S402-5;
s402-5, judging whether the number of elements in the array lseq is larger than or equal to bm, if so, turning to S402-6, otherwise, turning to S402-7;
s402-6, calculating and solving the arithmetic mean of each element in the array lseq as l _ j, and adding l _ j into the array Lset as an element with the sequence number of j in the array Lset; go to S402-8;
s402-7, increasing the value of bj by 1; go to S402-31;
s402-8, judging whether j < m is met, if so, increasing the value of j by 1, and then turning to S402-2, otherwise, turning to S402-9;
s402-9, outputting Lset; ending the program;
and the Lset obtained in the steps S402-1 to S402-9 is a molecular clustering value obtained by calculating each subgraph of the second gray scale map.
Further, in S500, the method of calculating and outputting the probability of the existence of soft agglomerated molecules according to the molecular agglomeration value of each sub-graph is as follows: calculating the probability of existence of soft agglomerated molecules according to the molecular agglomeration values of the sub-images of the first gray-scale image and the second gray-scale image, defining the actual change degree from the molecular agglomeration values of the sub-images of the first gray-scale image to the molecular agglomeration values of the sub-images of the second gray-scale image as rho, wherein the function exp () is an exponential function with the natural number e as the base, the function log () is a logarithmic function with the natural number 2 as the base, and the calculation formula of rho is as follows:
defining the change degree of each dimension value in the initialization vector Mr as beta, and calculating the beta according to the formula:
the probability of the existence of the soft aggregation molecules is recorded as lambda, and the formula for calculating the probability lambda of the existence of the soft aggregation molecules on the basis of the obtained rho and beta is as follows:
and the obtained lambda is the probability of the existence of soft aggregation molecules calculated according to the molecular aggregation values of the sub-images, whether the lambda is greater than eta is judged, if so, the judgment result is that the soft aggregation molecules exist in the second SEM image, if so, the judgment result is that the soft aggregation molecules do not exist in the second SEM image, and the lambda value and the corresponding judgment result are output through an output device of a computer or stored through a memory, wherein the eta is the probability threshold of the soft aggregation molecules, and the value range of the probability threshold of the soft aggregation molecules is [0.5,1 ].
The present disclosure also provides a soft agglomerated molecule recognition system based on SEM images, the soft agglomerated molecule recognition system based on SEM images comprising: the processor executes the computer program to realize the steps in the soft aggregation molecule identification method based on the SEM image, the soft aggregation molecule identification system based on the SEM image can be operated in computing equipment such as a desktop computer, a notebook computer, a palm computer and a cloud data center, and the operable system can include, but is not limited to, the processor, the memory and a server cluster, and the processor executes the computer program to operate in the following units of the system:
a grayscale image acquisition unit for acquiring a grayscale image of the SEM image;
the edge line detection unit is used for obtaining the edge line of the gray level image through an edge detection algorithm;
the sub-image set acquisition unit is used for obtaining a sub-image set from the gray-scale image through the edge line;
a molecular aggregation value calculation unit for calculating a molecular aggregation value for the plurality of subgraphs;
and the probability calculation unit is used for calculating the probability of the soft agglomerated molecules according to the molecular agglomeration value of each subgraph and outputting the probability.
The beneficial effect of this disclosure does: the invention provides a soft agglomerated molecule identification method and system based on an SEM image, which are characterized in that a gray scale image of the SEM image is obtained, an edge line of the gray scale image is obtained through an edge detection algorithm, a sub-image set is obtained from the gray scale image by using the edge line, a molecule agglomeration value is calculated for a plurality of sub-images, the probability of the existence of soft agglomerated molecules is calculated according to the molecule agglomeration value of each sub-image and output, and therefore the beneficial effect of judging whether the soft agglomerated molecules exist or not is achieved only by calculating and comparing the SEM images before and after processing.
Drawings
The foregoing and other features of the present disclosure will become more apparent from the detailed description of the embodiments shown in conjunction with the drawings in which like reference characters designate the same or similar elements throughout the several views, and it is apparent that the drawings in the following description are merely some examples of the present disclosure and that other drawings may be derived therefrom by those skilled in the art without the benefit of any inventive faculty, and in which:
FIG. 1 is a flow chart of a method for identifying soft agglomerated molecules based on SEM images;
FIG. 2 is a system diagram of a soft agglomerated molecule recognition system based on SEM images.
Detailed Description
The conception, specific structure and technical effects of the present disclosure will be clearly and completely described below in conjunction with the embodiments and the accompanying drawings to fully understand the objects, aspects and effects of the present disclosure. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
Referring to fig. 1, a flow chart of a soft agglomerated molecule recognition method based on SEM image according to the present invention is shown, and a soft agglomerated molecule recognition method and system based on SEM image according to an embodiment of the present invention is described below with reference to fig. 1.
The disclosure provides a soft agglomerated molecule identification method based on SEM images, which specifically comprises the following steps:
s100, acquiring a gray scale image of the SEM image;
s200, obtaining an edge line of the gray-scale image through an edge detection algorithm;
s300, obtaining a sub-image set from the gray-scale image through edge lines;
s400, calculating a molecular clustering value for the multiple subgraphs;
and S500, calculating the probability of the soft agglomerated molecules according to the molecular agglomeration values of the sub-images and outputting the probability.
In S100, the SEM image is: taking 1g of nano SiO2, CaCO3 and surface modified nano SiO2 or CaCO; placed on a slide and scraped flat against another slide to compact it to give a flat surface, which is imaged under a scanning electron microscope to obtain an SEM image.
Further, in S100, the method of acquiring the grayscale map of the SEM image includes: inputting a first SEM image, and obtaining a gray scale image of the first SEM image through a gray scale image algorithm and marking the gray scale image as a first gray scale image; inputting a second SEM image, and obtaining a gray scale image of the second SEM image through a gray scale image algorithm and marking the gray scale image as a second gray scale image; the first SEM image is an SEM image obtained before physical or chemical treatment, and the second SEM image is an SEM image obtained after physical or chemical treatment.
Further, in S200, the method for obtaining the edge line of the gray scale map by the edge detection algorithm includes: obtaining a plurality of edge lines on the first gray scale image by using an edge detection algorithm for the first gray scale image, and taking a set of the plurality of edge lines on the first gray scale image as a first edge line set; and obtaining a plurality of edge lines on the second gray scale image by using an edge detection algorithm for the second gray scale image, and taking a set of the plurality of edge lines on the second gray scale image as a second edge line set.
Further, in S300, the method for obtaining the sub-image set from the gray-scale map through the edge line includes: on the first gray scale map, defining a geometric figure formed by taking one or more edge lines belonging to a first edge line set as edges on the first gray scale map as a first sub-figure, wherein the first sub-figure is a sub-figure of the first gray scale map, and defining a set formed by one or more first sub-figures on the first gray scale map as a first sub-figure set; and on the second gray scale map, defining a geometric figure formed by taking one or more edge lines belonging to the second edge line set as edges on the second gray scale map as a back sub-graph, wherein the back sub-graph is a sub-graph of the second gray scale map, and a set formed by one or more back sub-graphs on the second gray scale map is marked as a second sub-graph set.
Further, in S400, the method for calculating the molecular clustering value for the plurality of subgraphs is:
marking a first subgraph set as a set Aset, the number of elements in the set Aset is n, a variable i represents the serial number of the elements in the set Aset, i belongs to [1, n ], the element with the serial number of i in the set Aset is marked as Aset (i), a second subgraph set is a set Bset, the number of the elements in the set Bset is m, a variable j represents the serial number of the elements in the set Bset, j belongs to [1, m ], and the element with the serial number of j in the set Bset is marked as Bset (j);
setting an initialization vector Mr, wherein the value of each element in the initialization vector Mr represents an initial probability value, the size of the initialization vector Mr is k-dimensional, the value of each element in the initialization vector Mr belongs to a (0,1) interval, the average number of each element is 0, and the variance of each element is 1;
wherein, the value of k in the Mr is obtained by defining a Min () function as a function of finding the smallest element in one or more input arrays, vectors, sequences, sets or the smallest element in a plurality of input values, a len () function is a function of calculating the number of the elements in one or more input arrays, vectors, matrices, sequences, sets, as Aset (i) and Bset (j) are both obtained from the image of the gray-scale map and are composed of pixels, len (Aset (i)) represents the number of pixels in Aset (i), len (Aset (i)) } represents a set composed of the number of pixels in each element in the set Aset, len (Bset (j)) represents the number of pixels in Bset (j), len (Bset () } represents a set composed of the number of pixels in each element in the set Aset, the avg () function is a function for obtaining a rounded down arithmetic mean, avg ({ len (Aset (i)) }) represents a rounded down arithmetic mean for obtaining the number of pixel points in each element in Aset, avg ({ len (Bset (j)) }) represents a rounded down arithmetic mean for obtaining the number of pixel points in each element in Bset, and Min (avg ({ len (Aset (i)) }), avg ({ len (Bset (j)) })) represents the smallest of two values for obtaining avg ({ len (Aset (i)) }) and avg ({ len (Bset (j)) }), and the value of k is Min (avg ({ len (Aset (i)) }), avg ({ len (bs (j)) });
defining the molecular clustering value as a numerical value for measuring soft agglomerated molecules in subgraphs, and calculating the molecular clustering value of a plurality of subgraphs of the first gray level graph by the following specific steps:
s401-1, starting a program; acquiring an initialization vector Mr, wherein Mr is preferably a vector of all 1 or a vector of all 0 or each value of the vector in Mr is a random number between 0 and 1 generated by a random function; acquiring a set Aset; setting a variable i, and setting an initial value of i to be 1; setting an empty array Tset; go to S401-2;
s401-2, acquiring an element with sequence number i in the set Aset as Aset (i), further acquiring the number of pixel points in Aset (i) as an, setting ai to represent the sequence number of the pixel points in Aset (i), wherein ai belongs to [1, an ], and marking the pixel value of the pixel point with sequence number ai in Aset (i) as A (ai); setting ai as 1; setting an empty array tseq; go to S401-31;
s401-31, judging whether constraint conditions (an-ai) ≧ k-1 are met, if yes, turning to S401-32, and if not, turning to S401-33; s401-32, acquiring a k-dimensional array composed of pixel values of k pixels with sequence numbers ai to ai + k-1 in Aset (i) as an array V (ai); go to S401-4;
s401-33, acquiring pixel values of a total of an-ai +1 pixel points from the serial number ai to the serial number an in the Aset (i), and connecting k- (an-ai +1) numerical values which are zero to form a k-dimensional array which is an array V (ai); go to S401-4;
s401-4, setting a variable q1 to represent the sequence number of an array or an element in a vector with a dimension k, wherein q1 belongs to [1, k ], V (ai) q1 represents an element with a sequence number of q1 in a V (ai) array, and Mr (q1) represents an element with a sequence number of q1 in an initialization vector Mr; setting a variable t (ai) to be a variable used in the process of calculating the array V (ai), wherein the formula for calculating t (ai) according to the initialization vector Mr and the array V (ai) is as follows:
adding the t (ai) obtained by the calculation into an array tseq; go to S401-5;
s401-5, judging whether the number of elements in the array tseq is larger than or equal to an, if so, turning to S401-6, otherwise, turning to S401-7;
s401-6, calculating and obtaining the arithmetic mean of each element in the array tseq as t _ i, adding t _ i into the array Tset, and taking t _ i as an element with the sequence number of i in the array Tset; go to S401-8;
s401-7, increasing the value of ai by 1; go to S401-31;
s401-8, judging whether i < n is met, if so, increasing the value of i by 1 and then turning to S401-2, otherwise, turning to S401-9;
s401-9, outputting the Tset; ending the program;
the Tset obtained in the steps S401-1 to S401-9 is a molecular clustering value obtained by calculating a plurality of subgraphs of the first gray scale map;
the specific steps of calculating the molecular clustering value of the multiple subgraphs of the second gray scale map are as follows:
s402-1, starting a program; acquiring an initialization vector Mr; acquiring a set Bset; setting a variable j, and enabling an initial value of the j to be 1; setting an empty array Lset; go to S402-2;
s402-2, acquiring an element with a sequence number j in a set Bset as Bset (j), further acquiring the number of pixel points in the Bset (j) as bm, setting bj to represent the sequence number of the pixel points in the Bset (j), setting bj to be [1, bm ], and recording the pixel value of the pixel point with the sequence number bj in the Bset (j) as B (bj); setting the initial value of bj as 1; setting an empty array lseq; go to S402-31;
s402-31, judging whether constraint conditions (bm-bj) ≧ k-1 are met, if yes, turning to S402-32, and if not, turning to S402-33; s402-32, acquiring a k-dimensional array composed of pixel values of k pixel points with sequence numbers bj to bj + k-1 in Bset (j) as an array W (bj); go to S402-4;
s402-33, obtaining pixel values of bm-bj +1 pixel points with sequence number bj to sequence number bm in Bset (j), and connecting k- (bm-bj +1) numerical values with zero in the following to form a k-dimensional array W (bj); go to S402-4;
s402-4, setting a variable q2 to represent the sequence number of an array or an element in a vector with a dimension of k, wherein q2 belongs to [1, k ], W (bj) q2 represents an element with a sequence number of q2 in an array W (bj), and Mr (q2) represents an element with a sequence number of q2 in an initialization vector Mr; setting variables l (bj) as variables used in the process of calculating the arrays W (bj), wherein the formula for calculating l (bj) according to the initialization vector Mr and the arrays W (bj) is as follows:
adding l (bj) obtained by the calculation into an array lseq; go to S402-5;
s402-5, judging whether the number of elements in the array lseq is larger than or equal to bm, if so, turning to S402-6, otherwise, turning to S402-7;
s402-6, calculating and solving the arithmetic mean of each element in the array lseq as l _ j, and adding l _ j into the array Lset as an element with the sequence number of j in the array Lset; go to S402-8;
s402-7, increasing the value of bj by 1; go to S402-31;
s402-8, judging whether j < m is met, if so, increasing the value of j by 1, and then turning to S402-2, otherwise, turning to S402-9;
s402-9, outputting Lset; ending the program;
；
wherein, preferably, part of the code in steps S402-1 to S402-9 includes:
and Lset obtained in the steps S402-1 to S402-9 is a molecular clustering value obtained by calculating a plurality of subgraphs of the second gray scale map.
Further, in S500, the method of calculating and outputting the probability of the existence of soft agglomerated molecules according to the molecular agglomeration value of each sub-graph is as follows: calculating the probability of existence of soft agglomerated molecules according to the molecular agglomeration values of the sub-images of the first gray-scale image and the second gray-scale image, defining the actual change degree from the molecular agglomeration values of the sub-images of the first gray-scale image to the molecular agglomeration values of the sub-images of the second gray-scale image as rho, wherein the function exp () is an exponential function with the natural number e as the base, the function log () is a logarithmic function with the natural number 2 as the base, and the calculation formula of rho is as follows:
defining the change degree of each dimension value in the initialization vector Mr as beta, and calculating the beta according to the formula:
wherein q is a value of q1 or q2, the probability of the presence of soft agglomerated molecules is denoted as λ, and the formula for calculating the probability of the presence of soft agglomerated molecules λ on the basis of the obtained ρ and β is:
and the obtained lambda is the probability of the existence of soft aggregation molecules calculated according to the molecular aggregation values of the sub-images, whether the lambda is greater than eta is judged, if so, the judgment result is that the soft aggregation molecules exist in the second SEM image, if so, the judgment result is that the soft aggregation molecules do not exist in the second SEM image, and the lambda value and the corresponding judgment result are output through an output device of a computer or stored through a memory, wherein the eta is the probability threshold of the soft aggregation molecules, and the value range of the probability threshold of the soft aggregation molecules is [0.5,1 ].
The soft agglomerated molecule recognition system based on the SEM image comprises: the processor executes the computer program to implement the steps in the above-mentioned soft aggregation molecule identification method based on SEM image, and the soft aggregation molecule identification system based on SEM image may be operated in a desktop computer, a notebook, a palm computer, a cloud data center, and other computing devices, and the operable system may include, but is not limited to, a processor, a memory, and a server cluster.
As shown in fig. 2, the soft agglomerated molecule recognition system based on SEM image according to the embodiment of the present disclosure includes: a processor, a memory and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in the above-mentioned embodiment of the SEM image-based soft agglomerated molecule identification method, and the processor executes the computer program to run in the following system units:
a grayscale image acquisition unit for acquiring a grayscale image of the SEM image;
the edge line detection unit is used for obtaining the edge line of the gray level image through an edge detection algorithm;
the sub-image set acquisition unit is used for obtaining a sub-image set from the gray-scale image through the edge line;
a molecular aggregation value calculation unit for calculating a molecular aggregation value for the plurality of subgraphs;
and the probability calculation unit is used for calculating the probability of the soft agglomerated molecules according to the molecular agglomeration value of each subgraph and outputting the probability.
The soft aggregation molecule recognition system based on the SEM image can be operated in computing equipment such as desktop computers, notebooks, palm computers and cloud data centers. The soft agglomerated molecule recognition system based on the SEM image comprises, but is not limited to, a processor and a memory. It will be understood by those skilled in the art that the example is merely an example of a soft agglomerated molecule recognition method and system based on SEM images, and does not constitute a limitation of a soft agglomerated molecule recognition method and system based on SEM images, and may include more or less components than the SEM images, or some components in combination, or different components, for example, the soft agglomerated molecule recognition system based on SEM images may further include an input and output device, a network access device, a bus, etc.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete component Gate or transistor logic, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor, etc., and the processor is a control center of the SEM image-based soft agglomerated molecule recognition system, and various interfaces and lines are used to connect various subareas of the whole SEM image-based soft agglomerated molecule recognition system.
The memory may be used for storing the computer program and/or the module, and the processor may implement various functions of the method and the system for identifying soft agglomerated molecules based on SEM images by operating or executing the computer program and/or the module stored in the memory and calling data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The invention provides a soft agglomerated molecule identification method and system based on an SEM image, which are characterized in that a gray scale image of the SEM image is obtained, an edge line of the gray scale image is obtained through an edge detection algorithm, a sub-image set is obtained from the gray scale image by using the edge line, a molecule agglomeration value is calculated for a plurality of sub-images, the probability of the existence of soft agglomerated molecules is calculated according to the molecule agglomeration value of each sub-image and output, and therefore the beneficial effect of judging whether the soft agglomerated molecules exist or not is achieved only by calculating and comparing the SEM images before and after processing.
Although the description of the present disclosure has been rather exhaustive and particularly described with respect to several illustrated embodiments, it is not intended to be limited to any such details or embodiments or any particular embodiments, so as to effectively encompass the intended scope of the present disclosure. Furthermore, the foregoing describes the disclosure in terms of embodiments foreseen by the inventor for which an enabling description was available, notwithstanding that insubstantial modifications of the disclosure, not presently foreseen, may nonetheless represent equivalent modifications thereto.
Claims (7)
1. A soft agglomerated molecule identification method based on SEM images is characterized by comprising the following steps:
s100, acquiring a gray scale image of the SEM image;
s200, obtaining an edge line of the gray-scale image through an edge detection algorithm;
s300, dividing the gray graph into a plurality of sub-graphs through edge lines, and forming a sub-graph set by all the sub-graphs;
s400, calculating a molecular clustering value of each subgraph in the subgraph set;
and S500, calculating the probability of the soft agglomerated molecules according to the molecular agglomeration values of the sub-images and outputting the probability.
2. The method for identifying soft agglomerated molecules based on SEM image as claimed in claim 1, wherein in S100, the method for obtaining the gray scale image of SEM image is as follows: inputting a first SEM image, and obtaining a gray scale image of the first SEM image through a gray scale image algorithm and marking the gray scale image as a first gray scale image; inputting a second SEM image, and obtaining a gray scale image of the second SEM image through a gray scale image algorithm and marking the gray scale image as a second gray scale image; the first SEM image is an SEM image obtained before physical or chemical treatment, and the second SEM image is an SEM image obtained after physical or chemical treatment.
3. The method for identifying soft agglomerated molecules based on SEM image as claimed in claim 1, wherein in S200, the method for obtaining the edge line of the gray scale image by the edge detection algorithm comprises: obtaining a plurality of edge lines on the first gray scale image by using an edge detection algorithm for the first gray scale image, and taking a set of the plurality of edge lines on the first gray scale image as a first edge line set; and obtaining a plurality of edge lines on the second gray scale image by using an edge detection algorithm for the second gray scale image, and taking a set of the plurality of edge lines on the second gray scale image as a second edge line set.
4. The method for soft agglomerated molecule recognition based on SEM image as claimed in claim 1, wherein in S300, the gray graph is divided into a plurality of sub-graphs by edge lines, and the sub-graph set is formed by all sub-graphs as follows: on the first gray scale map, defining a geometric figure formed by taking one or more edge lines belonging to a first edge line set as edges on the first gray scale map as a first sub-figure, wherein the first sub-figure is a sub-figure of the first gray scale map, and defining a set formed by one or more first sub-figures on the first gray scale map as a first sub-figure set; and on the second gray scale map, defining a geometric figure formed by taking one or more edge lines belonging to the second edge line set as edges on the second gray scale map as a back sub-figure, wherein the back sub-figure is a sub-figure of the second gray scale map, and a set formed by one or more first sub-figures on the second gray scale map is marked as a second sub-figure set.
5. The method for soft agglomerated molecule recognition based on SEM image as claimed in claim 1, wherein in S400, the method for calculating the molecular agglomeration value for multiple subgraphs is as follows:
marking a first subgraph set as a set Aset, the number of elements in the set Aset is n, a variable i represents the serial number of the elements in the set Aset, i belongs to [1, n ], the element with the serial number of i in the set Aset is marked as Aset (i), a second subgraph set is a set Bset, the number of the elements in the set Bset is m, a variable j represents the serial number of the elements in the set Bset, j belongs to [1, m ], and the element with the serial number of j in the set Bset is marked as Bset (j);
setting an initialization vector Mr, wherein the numerical value of each element in the initialization vector Mr represents an initial probability value, and the size of the initialization vector Mr is k-dimension;
wherein, the value of k in the Mr is obtained by defining a Min () function as a function of finding the smallest element in one or more input arrays, vectors, sequences, sets or the smallest element in a plurality of input values, a len () function is a function of calculating the number of the elements in one or more input arrays, vectors, matrices, sequences, sets, as Aset (i) and Bset (j) are both obtained from the image of the gray-scale map and are composed of pixels, len (Aset (i)) represents the number of pixels in Aset (i), len (Aset (i)) } represents a set composed of the number of pixels in each element in the set Aset, len (Bset (j)) represents the number of pixels in Bset (j), len (Bset () } represents a set composed of the number of pixels in each element in the set Aset, the avg () function is a function for obtaining a rounded down arithmetic mean, avg ({ len (Aset (i)) }) represents a rounded down arithmetic mean for obtaining the number of pixel points in each element in Aset, avg ({ len (Bset (j)) }) represents a rounded down arithmetic mean for obtaining the number of pixel points in each element in Bset, and Min (avg ({ len (Aset (i)) }), avg ({ len (Bset (j)) })) represents the smallest of two values for obtaining avg ({ len (Aset (i)) }) and avg ({ len (Bset (j)) }), and the value of k is Min (avg ({ len (Aset (i)) }), avg ({ len (bs (j)) });
defining the molecular clustering value as a numerical value for measuring soft agglomerated molecules in subgraphs, and calculating the molecular clustering value of a plurality of subgraphs of the first gray level graph by the following specific steps:
s401-1, starting a program; acquiring an initialization vector Mr; acquiring a set Aset; setting the initial value of i as 1; setting an empty array Tset; go to S401-2;
s401-2, acquiring an element with sequence number i in the set Aset as Aset (i), further acquiring the number of pixel points in Aset (i) as an, setting ai to represent the sequence number of the pixel points in Aset (i), wherein ai belongs to [1, an ], and marking the pixel value of the pixel point with sequence number ai in Aset (i) as A (ai); setting ai as 1; setting an empty array tseq; go to S401-31;
s401-31, judging whether constraint conditions (an-ai) ≧ k-1 are met, if yes, turning to S401-32, and if not, turning to S401-33;
s401-32, acquiring a k-dimensional array composed of pixel values of all pixel points with sequence numbers ai to ai + k-1 in Aset (i) as an array V (ai); go to S401-4;
s401-33, acquiring pixel values of a total of an-ai +1 pixel points from the serial number ai to the serial number an in the Aset (i), and connecting k- (an-ai +1) numerical values which are zero to form a k-dimensional array which is an array V (ai); go to S401-4;
s401-4, setting a variable q to represent the sequence number of an array or an element in a vector with a dimension of k, wherein q belongs to [1, k ], V (ai) q represents an element with the sequence number of q in an array V (ai), and Mr (q) represents an element with the sequence number of q in an initialization vector Mr; setting a variable t (ai) to be a variable used in the process of calculating the array V (ai), wherein the formula for calculating t (ai) according to the initialization vector Mr and the array V (ai) is as follows:
adding the t (ai) obtained by the calculation into an array tseq; go to S401-5;
s401-5, judging whether the number of elements in the array tseq is larger than or equal to an, if so, turning to S401-6, otherwise, turning to S401-7;
s401-6, calculating and obtaining the arithmetic mean of each element in the array tseq as t _ i, adding t _ i into the array Tset, and taking t _ i as an element with the sequence number of i in the array Tset; go to S401-8;
s401-7, increasing the value of ai by 1; go to S401-31;
s401-8, judging whether i < n is met, if so, increasing the value of i by 1 and then turning to S401-2, otherwise, turning to S401-9;
s401-9, outputting the Tset; ending the program;
the Tset obtained in the steps S401-1 to S401-9 is a molecular clustering value obtained by calculating a plurality of subgraphs of the first gray scale map;
the specific steps of calculating the molecular clustering value of the multiple subgraphs of the second gray scale map are as follows:
s402-1, starting a program; acquiring an initialization vector Mr; acquiring a set Bset; setting a variable j, and enabling an initial value of the j to be 1; setting an empty array Lset; go to S402-2;
s402-2, acquiring an element with a sequence number j in a set Bset as Bset (j), further acquiring the number of pixel points in the Bset (j) as bm, setting bj to represent the sequence number of the pixel points in the Bset (j), setting bj to be [1, bm ], and recording the pixel value of the pixel point with the sequence number bj in the Bset (j) as B (bj); setting the initial value of bj as 1; setting an empty array lseq; go to S402-31;
s402-31, judging whether constraint conditions (bm-bj) ≧ k-1 are met, if yes, turning to S402-32, and if not, turning to S402-33; s402-32, acquiring a k-dimensional array composed of pixel values of k pixel points with sequence numbers bj to bj + k-1 in Bset (j) as an array W (bj); go to S402-4;
s402-33, obtaining pixel values of bm-bj +1 pixel points with sequence number bj to sequence number bm in Bset (j), and connecting k- (bm-bj +1) numerical values with zero in the following to form a k-dimensional array W (bj); go to S402-4;
s402-4, setting a variable q to represent the sequence number of an array or an element in a vector with a dimension of k, wherein q belongs to [1, k ], W (bj) q represents an element with the sequence number of q in an array W (bj), and Mr (q) represents an element with the sequence number of q in an initialization vector Mr; setting variables l (bj) as variables used in the process of calculating the arrays W (bj), wherein the formula for calculating l (bj) according to the initialization vector Mr and the arrays W (bj) is as follows:
adding l (bj) obtained by the calculation into an array lseq; go to S402-5;
s402-5, judging whether the number of elements in the array lseq is larger than or equal to bm, if so, turning to S402-6, otherwise, turning to S402-7;
s402-6, calculating and solving the arithmetic mean of each element in the array lseq as l _ j, and adding l _ j into the array Lset as an element with the sequence number of j in the array Lset; go to S402-8;
s402-7, increasing the value of bj by 1; go to S402-31;
s402-8, judging whether j < m is met, if so, increasing the value of j by 1, and then turning to S402-2, otherwise, turning to S402-9;
s402-9, outputting Lset; ending the program;
and the Lset obtained in the steps S402-1 to S402-9 is a molecular clustering value obtained by calculating a plurality of subgraphs of the second gray scale map.
6. The method for identifying soft agglomerated molecules based on SEM image as claimed in claim 5, wherein in S500, the method for calculating and outputting the probability of the existence of soft agglomerated molecules according to the molecular agglomeration value of each subgraph is as follows: calculating the probability of existence of soft agglomerated molecules according to the molecular agglomeration values of the sub-images of the first gray-scale image and the second gray-scale image, defining the actual change degree from the molecular agglomeration values of the sub-images of the first gray-scale image to the molecular agglomeration values of the sub-images of the second gray-scale image as rho, wherein the function exp () is an exponential function with the natural number e as the base, the function log () is a logarithmic function with the natural number 2 as the base, and the calculation formula of rho is as follows:
defining the change degree of each dimension value in the initialization vector Mr as beta, and calculating the beta according to the formula:
the probability of the existence of the soft aggregation molecules is recorded as lambda, and the formula for calculating the probability lambda of the existence of the soft aggregation molecules on the basis of the obtained rho and beta is as follows:
and the obtained lambda is the probability of the existence of soft aggregation molecules calculated according to the molecular aggregation values of the sub-images, whether the lambda is greater than eta is judged, if so, the judgment result is that the soft aggregation molecules exist in the second SEM image, if so, the judgment result is that the soft aggregation molecules do not exist in the second SEM image, and the lambda value and the corresponding judgment result are output through an output device of a computer or stored through a memory, wherein eta is the probability threshold of the soft aggregation molecules, and the value range of the probability threshold of the soft aggregation molecules is [0.5,1 ].
7. A soft agglomerated molecule recognition system based on SEM images is characterized by comprising: a processor, a memory and a computer program stored in the memory and operable on the processor, wherein the processor implements the steps of the SEM image-based soft agglomerated molecule identification method of claim 1 when executing the computer program, and the SEM image-based soft agglomerated molecule identification system can be operated in a desktop computer, a notebook, a palm computer and a computing device of a cloud data center.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111101266.1A CN113936021B (en) | 2021-09-18 | 2021-09-18 | Soft aggregation molecule identification method and system based on SEM image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111101266.1A CN113936021B (en) | 2021-09-18 | 2021-09-18 | Soft aggregation molecule identification method and system based on SEM image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113936021A true CN113936021A (en) | 2022-01-14 |
| CN113936021B CN113936021B (en) | 2022-07-05 |
Family
ID=79276196
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111101266.1A Active CN113936021B (en) | 2021-09-18 | 2021-09-18 | Soft aggregation molecule identification method and system based on SEM image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113936021B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6720564B1 (en) * | 2002-12-05 | 2004-04-13 | The University Of Connecticut | Method and apparatus for fingerprint detection and analysis |
| CN104475239A (en) * | 2014-12-18 | 2015-04-01 | 江苏博迁新材料有限公司 | Grading device and grading method for ultra-fine powder |
| US20170161545A1 (en) * | 2015-05-28 | 2017-06-08 | Tokitae Llc | Image analysis systems and related methods |
| CN110378313A (en) * | 2019-07-26 | 2019-10-25 | 玖壹叁陆零医学科技南京有限公司 | Cell mass recognition methods, device and electronic equipment |
| CN111189864A (en) * | 2020-01-13 | 2020-05-22 | 中国石油天然气股份有限公司 | EPMA-WDX full-rock mineral identification and plane imaging method and device |
| CN113240676A (en) * | 2021-07-13 | 2021-08-10 | 深圳奥雅设计股份有限公司 | Intelligent regulation and control method and system of intelligent street lamp based on big data |
-
2021
- 2021-09-18 CN CN202111101266.1A patent/CN113936021B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6720564B1 (en) * | 2002-12-05 | 2004-04-13 | The University Of Connecticut | Method and apparatus for fingerprint detection and analysis |
| CN104475239A (en) * | 2014-12-18 | 2015-04-01 | 江苏博迁新材料有限公司 | Grading device and grading method for ultra-fine powder |
| US20170161545A1 (en) * | 2015-05-28 | 2017-06-08 | Tokitae Llc | Image analysis systems and related methods |
| CN110378313A (en) * | 2019-07-26 | 2019-10-25 | 玖壹叁陆零医学科技南京有限公司 | Cell mass recognition methods, device and electronic equipment |
| CN111189864A (en) * | 2020-01-13 | 2020-05-22 | 中国石油天然气股份有限公司 | EPMA-WDX full-rock mineral identification and plane imaging method and device |
| CN113240676A (en) * | 2021-07-13 | 2021-08-10 | 深圳奥雅设计股份有限公司 | Intelligent regulation and control method and system of intelligent street lamp based on big data |
Non-Patent Citations (6)
| Title |
|---|
| STAVROS TSANTILIS ET AL.: "Soft- and Hard-Agglomerate Aerosols Made at High Temperatures", 《AMERICAN CHEMICAL SOCIETY》 * |
| 何春霞等: "纳米SiC/PTFE复合材料微观结构SEM图像处理及分析", 《武汉科技大学学报》 * |
| 倪中华等: "纳米胶体团聚现象的分子动力学模拟", 《中国科学》 * |
| 李梦宇: "半导体材料SEM图像的识别与量化", 《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》 * |
| 毛项迪等: "一种基于梯度信息的SEM图像重建方法", 《计算机科学》 * |
| 王智等: "扫描电镜纳米颗粒粒径自动检测算法", 《计量学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113936021B (en) | 2022-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110097086B (en) | Image generation model training method, image generation method, device, equipment and storage medium | |
| Warif et al. | SIFT-symmetry: a robust detection method for copy-move forgery with reflection attack | |
| Backes et al. | Texture analysis and classification: A complex network-based approach | |
| CN111275129A (en) | Method and system for selecting image data augmentation strategy | |
| US10147015B2 (en) | Image processing device, image processing method, and computer-readable recording medium | |
| US9092697B2 (en) | Image recognition system and method for identifying similarities in different images | |
| US9025889B2 (en) | Method, apparatus and computer program product for providing pattern detection with unknown noise levels | |
| Shamir | Evaluation of face datasets as tools for assessing the performance of face recognition methods | |
| CN111709426B (en) | Diatom recognition method based on contour and texture | |
| CN111523341B (en) | Binarization method and device for two-dimensional code image | |
| CN107527348B (en) | Significance detection method based on multi-scale segmentation | |
| CN113936021B (en) | Soft aggregation molecule identification method and system based on SEM image | |
| CN117036445B (en) | Depth estimation method, device, computer equipment and medium based on random distribution | |
| CN111652277A (en) | False positive filtering method, electronic device and computer readable storage medium | |
| CN109740638B (en) | Method and device for clustering two-dimensional histogram of EM algorithm | |
| Hasan et al. | Application of binary particle swarm optimization in automatic classification of wood species using gray level co-occurence matrix and K-Nearest neighbor | |
| CN107464257B (en) | Wide base line matching method and device | |
| CN109815791B (en) | Blood vessel-based identity recognition method and device | |
| CN111753723B (en) | Fingerprint identification method and device based on density calibration | |
| CN108038864B (en) | Method and system for extracting animal target image | |
| CN116663648B (en) | Model training method, device, equipment and storage medium | |
| CN114745155B (en) | Network abnormal flow detection method, device and storage medium | |
| CN111178289B (en) | Method and system for shortening iris recognition time consumption | |
| Nezhinsky et al. | Efficient and robust shape retrieval from deformable templates | |
| KM | Multi-Resolution Feature Embedded Level Set Model for Crosshatched Texture Segmentation |
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 |