CN115546536A - Ivory product identification method and system - Google Patents
Ivory product identification method and system Download PDFInfo
- Publication number
- CN115546536A CN115546536A CN202211155323.9A CN202211155323A CN115546536A CN 115546536 A CN115546536 A CN 115546536A CN 202211155323 A CN202211155323 A CN 202211155323A CN 115546536 A CN115546536 A CN 115546536A
- Authority
- CN
- China
- Prior art keywords
- ivory
- texture
- image
- sample
- texture 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 102
- 238000012360 testing method Methods 0.000 claims abstract description 31
- 238000012549 training Methods 0.000 claims abstract description 31
- 238000007781 pre-processing Methods 0.000 claims abstract description 24
- 238000011056 performance test Methods 0.000 claims abstract description 7
- 238000009826 distribution Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 19
- 238000012216 screening Methods 0.000 claims description 11
- 241001503485 Mammuthus Species 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 9
- 238000002372 labelling Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 7
- 238000005520 cutting process Methods 0.000 claims description 4
- 230000003287 optical effect Effects 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 4
- 238000013480 data collection Methods 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 239000011521 glass Substances 0.000 claims 1
- 238000003860 storage Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 7
- 238000005259 measurement Methods 0.000 description 6
- 230000011218 segmentation Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 230000006872 improvement Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000003709 image segmentation Methods 0.000 description 4
- 210000003484 anatomy Anatomy 0.000 description 3
- 238000002360 preparation method Methods 0.000 description 3
- 241000406668 Loxodonta cyclotis Species 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 229940023487 dental product Drugs 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 238000000053 physical method Methods 0.000 description 2
- 238000003752 polymerase chain reaction Methods 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 108010075028 Cytochromes b Proteins 0.000 description 1
- 238000001712 DNA sequencing Methods 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 241000283080 Proboscidea <mammal> Species 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 238000004611 spectroscopical analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000004876 x-ray fluorescence Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/54—Extraction of image or video features relating to texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to an ivory product identification method and system, wherein the method comprises the following steps: acquiring original images of a plurality of different kinds of ivory samples, and preprocessing the original images of the object ivory samples to obtain texture images of the ivory samples; marking and classifying ivory sample texture images, establishing an ivory texture image data set, and dividing the ivory texture image data set into a training set and a test set according to a certain proportion; constructing an ivory recognition model, training parameters of the ivory recognition model by using training set data, performing performance test on the ivory recognition model by using test set data, and optimizing the ivory recognition model according to a test result; obtaining an original image of a suspected ivory product, and preprocessing the original image of the suspected ivory product to obtain a suspected ivory texture image; and the ivory recognition model reads the suspected ivory texture image and outputs a recognition result. The ivory recognition model is established by collecting a large number of ivory sample texture images, so that a faster, more stable and more accurate recognition result can be provided.
Description
Technical Field
The invention belongs to the technical field of ivory identification, and particularly relates to an ivory product identification method and system.
Background
In recent years, ivory has been pursued in the east and west world, and many current images (african images, asian images) have been stolen to kill the ivory in order to meet this demand. In recent years, up to 2 ten thousand elephants are subjected to illegal hunting on average every year, and rampant ivory smuggling activities are accompanied by crazy hunting. At present, the ivory trade is completely prohibited in China, commercial processing and selling of ivory are stopped, and any trade mode or behaviors of carrying, mailing and other endangered species and products thereof such as ivory are prohibited except for holding certificates allowing import and export.
At present, the raw materials of ivory products are mainly divided into a real ivory and a mammoth ivory, and a large number of ivory imitation products exist in the market because many animal bone products, even some plant products and industrial synthetic products are similar to the ivory. Therefore, a method for rapidly detecting ivory is required for customs workers to identify ivory during entry and exit inspection, for example, when an ivory sample suspected of being an ivory or mammoth ivory is found.
The existing identification methods of ivory samples can be divided into the following three categories:
(1) A morphological structure based approach. The method takes Shi Leige (Schreger) texture mode as an important identification basis and is always used for distinguishing the ivory products of the elephant and the mammoth. The schradermatograph patterns of the present image and the mammoth have a large difference in the value of the characteristic angle, also called the schrader angle. Generally, the average value of the Schlemn's angle at the outer edge of the mammoth is less than 100 degrees, the average value of the Schlemn's angle of the traditional mammoth is more than 115 degrees, and other imitation materials cannot reproduce the naturally formed Schlemn's angle. The method needs to have professional knowledge and long-term experience accumulation, and judges whether the object to be detected is ivory and classifies the object to be detected by carefully observing the anatomical structure of the ivory product and comparing the anatomical structure with the anatomical structure characteristics of laboratory ivory specimens.
(2) Methods based on physical characteristics. The method uses a hand-held X-ray fluorescence device to detect elemental components of a suspected ivory, thereby distinguishing the ivory preparation of a live elephant from a mammoth. In addition, a multiple high resolution melt (M-HRM) method and identification of ivory articles by composite melt spectroscopy.
(3) Based on molecular biology. The method identifies ivory products by DNA analysis, for example, by Polymerase Chain Reaction (PCR) amplification of three sets of nests in the cytochrome b gene to achieve DNA sequencing for identification purposes. However, the database establishment of DNA requires a lot of time and money, and the detection of DNA takes a relatively long time.
Among the above methods, physical feature-based and molecular biology-based methods generally require a small sampling of the ivory preparation, which can cause irreversible damage to the subject dental preparation. Although the method based on the morphological structure can avoid the damage of the ivory product by directly observing the Schneider angle on the surface of the ivory product, the accuracy of the method is influenced by the experience of an appraiser and different observation methods, so that the time consumption of ivory identification is long, and meanwhile, the ivory judgment mainly depends on the technical experience and level of the appraiser and also directly influences the accuracy of the appraisal result.
Disclosure of Invention
The invention aims to provide an ivory product identification method and system based on ivory texture images and a deep learning model aiming at the problems in the prior art, so as to solve the problems that in the prior art, an object dental product is irreversibly damaged, an accurate Schneider's angle measurement result is relied on, personnel experience is relied on for accumulation, the identification process is complex and time-consuming, and the like, and achieve the purpose of quickly and accurately identifying the object dental product and the imitation thereof.
In order to realize the purpose of the invention, the following technical scheme is adopted:
in a first aspect, the present invention provides a method for identifying ivory products, comprising the following steps:
acquiring original images of a plurality of different kinds of ivory samples, and preprocessing the original images of the object ivory samples to obtain texture images of the ivory samples;
marking and classifying ivory sample texture images, establishing an ivory texture image data set, and dividing the ivory texture image data set into a training set and a test set according to a certain proportion;
constructing an ivory recognition model, training parameters of the ivory recognition model by using training set data, performing performance test on the ivory recognition model by using test set data, and optimizing the ivory recognition model according to a test result;
acquiring an original image of a suspected ivory product, and preprocessing the original image of the suspected ivory product to obtain a suspected ivory texture image;
the ivory recognition model reads the suspected ivory texture image and outputs a recognition result.
In a further improvement, the specific method of pretreatment comprises:
segmenting an original image, and removing useless image edges to obtain a sample image;
cutting the sample image to obtain a plurality of candidate texture images;
screening a plurality of candidate texture images, deleting images with high brightness, non-texture and overlarge background area ratio, and reserving the images with clear texture as selected texture images;
and performing data enhancement on the selected texture image to obtain a final texture image.
The specific method for screening a plurality of candidate texture images, deleting images with high brightness, non-texture and excessive background area ratio and reserving images with clear textures as selected texture images comprises the following steps:
converting the candidate texture image into a gray image, taking the pixels with the gray values higher than a first specified threshold value as high-brightness pixels, counting the number of the high-brightness pixels and calculating the proportion of the high-brightness pixels, deleting the image if the proportion of the high-brightness pixels of the candidate texture image is higher than the first specified threshold value, otherwise, keeping, taking the pixels with the gray values lower than a second specified threshold value as background pixels, counting the number of the background pixels and calculating the proportion of the background pixels, deleting the image if the proportion of the background pixels of the candidate texture image is higher than the second specified threshold value, and otherwise, keeping; and extracting texture features of the candidate texture image to obtain texture feature distribution, wherein if the texture feature distribution does not meet given conditions, the candidate texture image is a non-texture image and deleted, and if not, the candidate texture image is reserved.
In a further improvement, the specific method for performing data enhancement on the selected texture image to obtain a final texture image comprises:
firstly, enhancing the selected texture image to improve the significance of the texture;
and then carrying out multi-angle rotation or mirror image processing on the selected texture image, and obtaining a new texture image every time of processing so as to increase the number of images.
The further improvement is that the texture feature extraction is performed on the candidate texture image to obtain texture feature distribution, if the texture feature distribution does not meet a given condition, the candidate texture image is a non-texture image and deleted, otherwise, the specific method for retaining comprises the following steps:
assuming that I represents a candidate ivory texture image and J represents a standard ivory texture image, performing texture feature extraction on the candidate ivory texture image I to obtain texture feature distribution P (I), and performing texture feature extraction on the standard ivory texture image J to obtain texture feature distribution Q (J), and further calculating Kullback-Leibler divergence of the candidate ivory texture image I and the standard ivory texture image J, wherein the Kullback-Leibler divergence is as follows:
wherein,
Kullback-Leibler divergence representing the distribution of texture features of a candidate ivory texture image I and a standard ivory texture image J when
Less than a given threshold value theta KL Then the candidate ivory texture image I is judged as the texture image and reserved, i.e.
If the texture feature distribution of the candidate ivory texture image I is not satisfied
If yes, the candidate ivory texture image I is a non-texture image and is deleted.
In a further improvement, the specific method for acquiring the original images of the ivory samples of different types comprises the following steps:
preprocessing an ivory sample and placing the ivory sample on an object stage of an image acquisition device;
adjusting the direction of the ivory sample to enable ivory texture to be upward and fully exposed in the visual field of an industrial camera, and then fixing the position of the ivory sample by using a sample fixer;
adjusting the heights of the industrial camera and the magnifier, judging whether to start a light source and adjust the brightness of the light source according to the intensity of ambient light and the brightness of an ivory sample image in a camera picture, and ensuring that ivory textures in the camera picture are clear and visible;
shooting an ivory sample to obtain an original image of the ivory sample, and recording the category and the number of the ivory sample;
in the shooting process, a plurality of primitive images of the ivory sample at different positions are acquired by moving the ivory sample and adjusting the direction of the ivory sample.
The further improvement is that the concrete method for labeling and classifying texture images of the object tooth sample, establishing an ivory texture image data set, and dividing the ivory texture image data set into a training set and a testing set according to a certain proportion comprises the following steps:
labeling a ivory sample category label and a ivory sample number for each ivory sample texture image according to the ivory sample category and number recorded during ivory sample shooting;
the ivory sample category comprises an ivory product, a mammoth ivory product and an ivory imitation;
the ivory texture image data set is divided into a training set and a testing set according to a certain proportion, and meanwhile, all ivory sample texture images marked as the same ivory sample number are ensured to be divided into the training set or the testing set completely and cannot be divided into the two sets simultaneously.
In a second aspect, the present invention provides an ivory product identification system, comprising:
the image acquisition device is used for acquiring original images of a plurality of different kinds of ivory samples and acquiring original images of suspected ivory products;
the image preprocessing module is used for preprocessing an original image of the object tooth sample to obtain a texture image of the ivory sample and preprocessing an original image of the suspected ivory product to obtain a suspected ivory texture image;
the data collection management module is used for labeling and classifying the texture images of the ivory samples, establishing an ivory texture image data set, and dividing the ivory texture image data set into a training set and a test set according to a certain proportion;
the ivory recognition model building module is used for building an ivory recognition model, training parameters of the ivory recognition model by using training set data, performing performance test on the ivory recognition model by using test set data, and optimizing the ivory recognition model according to a test result;
the ivory recognition model is used for reading a suspected ivory texture image and outputting a recognition result.
The image acquisition device comprises a lifting bracket, an industrial camera, a light source module, a magnifying lens, a scale, a sample fixer, an objective table, an image acquisition switch, a wireless communication module and a power supply and interface module;
the industrial camera, the light source module, the image acquisition switch, the wireless communication module and the power supply and interface module form a whole and are connected with the lifting support, so that the height can be adjusted;
the magnifying lens and the scale form a whole and are connected with the lifting support, so that the height can be adjusted;
the optical axes of the magnifier and the industrial camera lens are in the same straight line;
the sample fixer and the objective table form a whole and are fixedly connected with the bottom of the lifting support so as not to move.
In a third aspect, the present invention provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements an ivory product identification method according to any of the first aspect of the present invention.
In a fourth aspect, the present invention provides a computer-readable storage medium comprising a stored computer program, wherein the computer program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform a method for ivory product identification according to any of the first aspect of the present invention.
The invention has the beneficial effects that:
the ivory product identification method is used for identifying by a computer vision method, and can avoid the damage of a sample of the object tooth compared with physical methods such as ivory slice detection and the like. Compared with the ivory identification method which needs to depend on the identification level of technicians, the ivory identification method based on artificial intelligence is established by collecting a large number of ivory sample texture images, and a quicker, more stable and more accurate identification result can be provided. Compared with the ivory identification method based on DNA detection, the method can effectively reduce the identification cost and the time required by identification, and also avoid the loss of ivory samples. Compared with the ivory identification method based on the Schneider angle measurement, the ivory identification method based on the Schneider angle measurement can avoid the problem of identification errors caused by inaccurate angle measurement.
The image acquisition equipment that this application provided can fixed image shoot the light path, simplifies the ivory sample and places the operation to improve the shooting efficiency of ivory image, and can make full use of ambient lighting open the light source light filling as required, realize energy saving.
Drawings
FIG. 1 is a flowchart illustrating the overall steps of a method for identifying ivory products in accordance with the present invention;
FIG. 2 is a flowchart illustrating a method for pre-processing in a method for identifying ivory products according to the present invention;
FIG. 3 is a diagram illustrating an example of a process of preprocessing an original image of an object tooth in the ivory product identification method according to the present invention;
FIG. 4 is a schematic diagram of an ivory product identification system of the present invention;
FIG. 5 is a schematic view of an image capture device in an ivory product identification system of the present invention;
fig. 6 is a schematic diagram of an electronic device according to the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood by those skilled in the art, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Moreover, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Referring to fig. 1 to 6, as shown in fig. 1, a first aspect of an embodiment of the present invention provides a method for identifying an ivory product, including the following steps:
step S1: obtaining original images of a plurality of different kinds of ivory samples;
step S2: preprocessing an original image of the object tooth sample to obtain a texture image of the ivory sample;
and step S3: marking and classifying ivory sample texture images, establishing an ivory texture image data set, and dividing the ivory texture image data set into a training set and a test set according to a certain proportion;
and step S4: adopting a neural network method to construct an ivory recognition model; the ivory recognition model is input as a texture image and output as an ivory recognition result;
step S5: training parameters of the ivory recognition model by using training set data, performing performance test on the ivory recognition model by using test set data, and optimizing the ivory recognition model according to a test result; training and testing the object tooth recognition model repeatedly until the recognition accuracy of the ivory recognition model reaches a given threshold value;
step S6: obtaining an original image of a suspected ivory product, and preprocessing the original image of the suspected ivory product to obtain a suspected ivory texture image;
step S7: the ivory recognition model reads the suspected ivory texture image, the recognition result is output, and the ivory recognition display interface performs visual display on the ivory recognition result.
In some embodiments, the ivory recognition display interface includes a graphical user interface of software, a LED of hardware, an LCD stand-alone display, or a display screen integrated in various terminal devices such as a personal computer, a notebook computer, a tablet computer, and the like.
In some embodiments, the ivory recognition model may be constructed using a convolutional neural network architecture, which should include an input layer, a convolutional layer, a normalized pool, a max pooling layer, a global average pooling layer, an output layer, and so on.
Specifically, as shown in fig. 2 and 3, in the present embodiment, the specific method of the preprocessing in step S2 and step S6 includes:
step S21: segmenting an original image by an image segmentation method, and removing useless image edges to obtain a sample image containing a background;
step S22: cutting the sample image by an image cutting method to obtain a plurality of candidate texture images;
step S23: screening a plurality of candidate texture images by an image screening method, deleting images with high brightness, non-texture and overlarge background area ratio, and reserving the images with clear texture as selected texture images;
step S24: and performing data enhancement on the selected texture image to obtain a final texture image.
In step S22, the requirements for the image cropping method are as follows:
cropping the resolution less than the resolution of the sample image;
the overlapping rate between the candidate texture images obtained by clipping cannot be higher than a given threshold.
In the step S21, the image segmentation method is a manual segmentation method or an automatic segmentation method, in which a worker segments an ivory and a surrounding background region in an original image according to a scale range photographed in the original image through image processing software, an image region obtained after the segmentation is rectangular, and the image does not include a scale.
The automatic segmentation method is realized through computer programming, and the ivory image area in the scale range is automatically segmented and intercepted through an image segmentation algorithm.
In some embodiments, the image segmentation algorithm may employ a level set segmentation method, a deep learning segmentation method, or the like.
Specifically, the image screening method in step S23 includes manual screening and automatic screening.
The manual screening method comprises the steps of observing candidate ivory texture images through human eyes, reserving images containing clear ivory textures, and deleting images containing highlights, non-textures and background areas with large proportion;
the automatic screening method is realized through computer programming, and the specific method is as follows:
firstly, converting a candidate texture image into a gray image, taking pixels with gray values higher than a first specified threshold value as high-brightness pixels, counting the number of the high-brightness pixels and calculating the proportion of the high-brightness pixels, deleting the image if the proportion of the high-brightness pixels of the candidate texture image is higher than the first specified threshold value, otherwise, keeping the pixels with gray values lower than a second specified threshold value as background pixels, counting the number of the background pixels and calculating the proportion of the background pixels, deleting the image if the proportion of the background pixels of the candidate texture image is higher than the second specified threshold value, and otherwise, keeping the image.
The specific method is described in detail below: taking the pixel with the gray value I (x, y) higher than the first designated threshold value alpha as the highlight pixel, counting the number of the highlight pixels and calculating the proportion rho of the highlight pixels α ，ρ α Is in the value range of rho α ∈[0,1]Specifically, the following are shown:
wherein I (x, y) represents the gray scale value of the pixel (x, y), and has x E [1,W ∈]And y E [1,H]W and H are the number of horizontal and vertical pixels of the image, respectively, the value of the first specified threshold value alpha is 230, and the first given threshold value theta is α Is 0.05, and sigma (·) is a function of the value 0-1, as follows:
wherein, (. Cndot.) represents a Boolean expression whose output result is true or false, if the proportion rho of the highlight pixel of the candidate ivory texture image is α Above a first given threshold value theta α I.e. p α >θ α Deleting the image, otherwise, keeping;
taking the pixel with the gray value I (x, y) lower than the second designated threshold value beta as the background pixel, counting the number of the background pixels and calculating the proportion rho of the background pixels β ，ρ β Is in the range of rho β ∈[0,1]The method comprises the following steps:
wherein the value of the second given threshold beta is 80, and the value of the second given threshold theta is β Is 0.25, if the background pixel of the candidate ivory texture image occupies a high proportion rho β At a second given threshold value theta β I.e. p β >θ β If yes, deleting the image, otherwise, keeping;
and extracting texture features of the candidate texture image to obtain texture feature distribution, wherein if the texture feature distribution does not meet given conditions, the candidate texture image is a non-texture image and deleted, and if not, the candidate texture image is reserved.
In some embodiments, the texture feature extraction is performed on the candidate texture image to obtain texture feature distribution, and if the texture feature distribution does not satisfy a given condition, the candidate texture image is a non-texture image and deleted, otherwise, the specific method for retaining includes:
assuming that I represents a candidate ivory texture image and J represents a standard ivory texture image, performing texture feature extraction on the candidate ivory texture image I to obtain texture feature distribution P (I), and simultaneously performing texture feature extraction on the standard ivory texture image J to obtain texture feature distribution Q (J), and further calculating Kullback-Leibler divergence of the candidate ivory texture image I and the standard ivory texture image J as follows:
wherein,
Kullback-Leibler divergence representing the distribution of texture features of a candidate ivory texture image I and a standard ivory texture image J when
Less than a given threshold value theta KL Then the candidate ivory texture image I is judged as a texture image and reserved, i.e.
If the texture feature distribution of the candidate ivory texture image I is not satisfied
If yes, the candidate ivory texture image I is a non-texture image and is deleted.
In this embodiment, the specific method for performing data enhancement on the selected texture image in step S24 to obtain a final texture image includes:
firstly, enhancing the selected texture image by using image enhancement methods such as histogram equalization, automatic contrast and the like, and improving the significance of the texture;
and then performing multi-angle rotation or mirror image processing on the selected texture image, wherein each processing time results in a new texture image to increase the number of images, the multi-angle rotation processing comprises clockwise fixed angle rotation, such as 45 °, 90 °, 135 °, 180 °, 225 °, 270 °, 315 °, and random angle rotation, and the mirror image processing comprises vertical mirror image and horizontal mirror image.
In this embodiment, the specific method for acquiring the original images of the ivory samples of different types in step S1 includes:
firstly, preprocessing an ivory sample, for example, cleaning the ivory sample, and placing the ivory sample on an object stage of an image acquisition device;
then adjusting the direction of the ivory sample to enable ivory grains to face upwards and be fully exposed in the visual field of an industrial camera, and then fixing the position of the ivory sample by using a sample fixer;
by adjusting the heights of the industrial camera and the magnifier, judging whether to start a light source and adjust the brightness of the light source according to the intensity of ambient light and the brightness of an ivory sample image in a camera picture, and ensuring that ivory textures in the camera picture are clear and visible;
then shooting the ivory sample to obtain an original image of the ivory sample, and correspondingly recording the category and the number of the ivory sample;
during shooting, a plurality of primitive images of the ivory sample at different positions can be acquired by moving the ivory sample and adjusting the direction of the ivory sample.
In this embodiment, the specific method for labeling and classifying the texture images of the object tooth sample in step S3, establishing the ivory texture image data set, and dividing the ivory texture image data set into a training set and a test set according to a certain proportion includes:
labeling a ivory sample category label and a ivory sample number for each ivory sample texture image according to the ivory sample category and number recorded during ivory sample shooting;
wherein the ivory sample category comprises a live ivory product, a mammoth ivory product, an ivory imitation and the like; the ivory products can be further subdivided into African ivory products and Asian ivory products according to actual needs, and the ivory imitated products can be further subdivided into categories according to actual needs. Those skilled in the art can classify the samples according to actual needs.
The ivory texture image data set is divided into a training set and a testing set according to the proportion of 9:1, and meanwhile, all ivory sample texture images marked as the same ivory sample number are guaranteed to be divided into the training set or the testing set completely and cannot be divided into the two sets at the same time.
The ivory product identification method is implemented through a computer vision method, and compared with physical methods such as ivory section detection, the ivory product identification method can avoid damage to a sample of the object tooth. Compared with the ivory recognition method which needs to depend on the identification level of technicians, the method for recognizing ivory by the ivory sample texture image based on artificial intelligence is established, and a faster, more stable and more accurate recognition result can be provided. Compared with the ivory identification method based on DNA detection, the method can effectively reduce the identification cost and the time required by identification, and also avoid the loss of ivory samples. Compared with the ivory identification method based on the Schneider angle measurement, the method can avoid the problem of identification errors caused by inaccurate angle measurement.
In a second aspect of the embodiment of the present invention, an ivory product identification system is provided, which corresponds to the ivory product identification method provided by the above embodiment of the present invention, and since the ivory product identification system provided by the embodiment of the present invention corresponds to the ivory product identification method provided by the above embodiment of the present invention, the implementation manner of the aforementioned ivory product identification method is also applicable to the ivory product identification system provided by the present embodiment.
Specifically, as shown in fig. 4 and 5, an ivory product identification system according to an embodiment of the present invention includes:
the image acquisition device 20 is used for acquiring original images of a plurality of different kinds of ivory samples and acquiring original images of suspected ivory products;
the image preprocessing module 30 is used for preprocessing the original image of the ivory sample to obtain a texture image of the ivory sample and preprocessing the original image of the suspected ivory product to obtain a suspected ivory texture image;
the data collection management module 40 is used for labeling and classifying the texture images of the ivory samples, establishing an ivory texture image data set, and dividing the ivory texture image data set into a training set and a test set according to a certain proportion;
the storage module 50 is used for compressing and storing original image data of the object tooth sample and the ivory texture image data set;
the ivory recognition model building module 60 is used for building an ivory recognition model, training parameters of the ivory recognition model by using training set data, performing performance test on the ivory recognition model by using test set data, and optimizing the ivory recognition model according to a test result;
the ivory recognition model is used for reading a suspected ivory texture image and outputting a recognition result.
And the ivory identification interface module 70 is used for visually displaying the identification result.
In this embodiment, the image capturing apparatus 20 may include an image capturing device and a capturing system, wherein the capturing system is installed in a computer device, the image capturing device is connected to the computer device in a communication manner, and the capturing system is used for setting image capturing parameters of the industrial camera.
Specifically, as shown in fig. 5, the image capturing device includes a lifting bracket 201, an industrial camera 202, a light source module 203, a magnifier 204, a scale 205, a sample holder 206, an object stage 207, an image capturing switch 208, a wireless communication module 209, and a power supply and interface module 210.
The industrial camera 202, the light source module 203, the image acquisition switch 208, the wireless communication module 209 and the power supply and interface module 210 form a whole and are connected with the lifting support 201, so that the height is adjustable;
the magnifier 204 and the ruler 205 form a whole and are connected with the lifting support 201, so that the height can be adjusted;
the optical axes of the magnifier 204 and the industrial camera 202 are in the same straight line;
the sample holder 206 and the stage 207 are integrated and fixedly connected with the bottom of the liftable bracket 201.
The light source module 203 has an independent switch and a brightness adjusting knob, the independent switch can control the on and off of the light source, and the brightness adjusting knob can control the increase and decrease of the brightness of the light source.
In some embodiments, the image capture fraction of the industrial camera 202 should be up to 3000 × 3000 pixels, and should not be lower than 1000 × 1000 pixels.
The image acquisition equipment that this embodiment provided can fixed image shoot the light path, simplifies the ivory sample and places the operation to improve the shooting efficiency of ivory image, and can make full use of ambient lighting open the light source light filling as required, realize energy saving.
The embodiment of the invention also correspondingly provides the electronic equipment and a computer readable storage medium.
Fig. 6 is a schematic view of an electronic device according to an embodiment of the invention. The electronic device of this embodiment includes: a processor 11, a memory 12 and a computer program stored in said memory 12 and executable on said processor 11. The processor 11, when executing the computer program, performs the steps in an embodiment of a method for ivory product identification as described above. Alternatively, the processor 11 implements the functions of the modules/units in the above-described device embodiments when executing the computer program.
Illustratively, the computer program may be divided into one or more modules/units, which are stored in the memory and executed by the processor 11 to accomplish the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program in the electronic device.
The electronic device may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that the schematic diagrams are merely examples of an electronic device and do not constitute a limitation of an electronic device, and may include more or fewer components than those shown, or some components in combination, or different components, for example, the electronic device may also include input output devices, network access devices, buses, etc.
The Processor 11 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 Gate or transistor logic device, discrete hardware component, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like that is the control center for the electronic device and that connects the various parts of the overall electronic device using various interfaces and wires.
The memory 12 can be used for storing the computer programs and/or modules, and the processor can implement various functions of the electronic device by operating or executing the computer programs and/or modules stored in the memory and calling the 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 121, an application program 122 (such as a sound playing function, an image playing function, etc.) required for at least one function, 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.
Wherein, the integrated module/unit of the electronic device can be stored in a computer readable storage medium if it is implemented in the form of software functional unit and sold or used as a stand-alone product. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, read-Only Memory (ROM), random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like.
It should be noted that the above-described device embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the apparatus provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (10)
1. An ivory product identification method, comprising the steps of:
acquiring original images of a plurality of different kinds of ivory samples, and preprocessing the original images of the object ivory samples to obtain texture images of the ivory samples;
marking and classifying ivory sample texture images, establishing an ivory texture image data set, and dividing the ivory texture image data set into a training set and a test set according to a certain proportion;
constructing an ivory recognition model, training parameters of the ivory recognition model by using training set data, performing performance test on the ivory recognition model by using test set data, and optimizing the ivory recognition model according to a test result;
obtaining an original image of a suspected ivory product, and preprocessing the original image of the suspected ivory product to obtain a suspected ivory texture image;
and the ivory recognition model reads the suspected ivory texture image and outputs a recognition result.
2. The ivory product identification method as claimed in claim 1, wherein the specific method of preprocessing comprises:
segmenting the original image, and removing useless image edges to obtain a sample image;
cutting the sample image to obtain a plurality of candidate texture images;
screening a plurality of candidate texture images, deleting images with high brightness, non-texture and overlarge background area proportion, and reserving the images with clear textures as selected texture images;
and performing data enhancement on the selected texture image to obtain a final texture image.
3. The ivory product identification method according to claim 2, wherein the specific method for screening a plurality of candidate texture images, deleting images with high brightness, non-texture and excessive background area proportion, and reserving an image with clear texture as the selected texture image comprises the following steps:
converting the candidate texture image into a gray image, taking the pixels with the gray values higher than a first specified threshold value as high-brightness pixels, counting the number of the high-brightness pixels and calculating the proportion of the high-brightness pixels, deleting the image if the proportion of the high-brightness pixels of the candidate texture image is higher than the first specified threshold value, otherwise, keeping, taking the pixels with the gray values lower than a second specified threshold value as background pixels, counting the number of the background pixels and calculating the proportion of the background pixels, deleting the image if the proportion of the background pixels of the candidate texture image is higher than the second specified threshold value, and otherwise, keeping; and extracting texture features of the candidate texture image to obtain texture feature distribution, wherein if the texture feature distribution does not meet given conditions, the candidate texture image is a non-texture image and is deleted, and if not, the candidate texture image is reserved.
4. The ivory product identification method according to claim 2, wherein the specific method for performing data enhancement on the selected texture image to obtain a final texture image comprises:
firstly, enhancing the selected texture image to improve the significance of the texture;
and then carrying out multi-angle rotation or mirror image processing on the selected texture image, and obtaining a new texture image every time of processing so as to increase the number of images.
5. The ivory product identification method according to claim 3, wherein the texture feature extraction is performed on the candidate texture image to obtain a texture feature distribution, and if the texture feature distribution does not satisfy a given condition, the candidate texture image is a non-texture image and deleted, otherwise, the specific method for retaining includes:
assuming that I represents a candidate ivory texture image and J represents a standard ivory texture image, performing texture feature extraction on the candidate ivory texture image I to obtain texture feature distribution P (I), and simultaneously performing texture feature extraction on the standard ivory texture image J to obtain texture feature distribution Q (J), and further calculating Kullback-Leibler divergence of the candidate ivory texture image I and the standard ivory texture image J as follows:
wherein,
Kullback-Leibler divergence representing the distribution of texture features of a candidate ivory texture image I and a standard ivory texture image J when
Less than a given threshold value theta KL Then the candidate ivory texture image I is judged as a texture image and reserved, i.e.
If the texture feature distribution of the candidate ivory texture image I is not satisfied
If yes, the candidate ivory texture image I is a non-texture image and is deleted.
6. The ivory product identification method of claim 1, wherein the specific method of obtaining the original images of a plurality of different types of ivory samples comprises:
preprocessing an ivory sample and placing the ivory sample on an object stage of an image acquisition device;
adjusting the direction of the ivory sample to enable ivory texture to be upward and fully exposed in the visual field of an industrial camera, and then fixing the position of the ivory sample by using a sample fixer;
adjusting the heights of the industrial camera and the magnifier, judging whether to start a light source and adjust the brightness of the light source according to the intensity of ambient light and the brightness of an ivory sample image in a camera picture, and ensuring that ivory textures in the camera picture are clear and visible;
shooting an ivory sample to obtain an original image of the ivory sample, and recording the category and the number of the ivory sample;
in the shooting process, a plurality of primitive images of the ivory sample at different positions are acquired by moving the ivory sample and adjusting the direction of the ivory sample.
7. The ivory product identification method according to claim 6, wherein the concrete method of labeling and classifying texture images of the object tooth sample, establishing an ivory texture image data set, and dividing the ivory texture image data set into a training set and a testing set according to a certain proportion comprises the following steps:
labeling a ivory sample category label and a ivory sample number for each ivory sample texture image according to the ivory sample category and number recorded during ivory sample shooting;
the ivory sample category comprises an ivory product, a mammoth ivory product and an ivory imitation;
the ivory texture image data set is divided into a training set and a testing set according to a certain proportion, and meanwhile, all ivory sample texture images marked as the same ivory sample number are ensured to be divided into the training set or the testing set completely and cannot be divided into the two sets simultaneously.
8. An ivory product identification system, comprising:
the image acquisition device is used for acquiring original images of a plurality of different kinds of ivory samples and acquiring original images of suspected ivory products;
the image preprocessing module is used for preprocessing an original image of the object tooth sample to obtain a texture image of the ivory sample and preprocessing an original image of the suspected ivory product to obtain a suspected ivory texture image;
the data collection management module is used for labeling and classifying the texture images of the ivory samples, establishing an ivory texture image data set, and dividing the ivory texture image data set into a training set and a test set according to a certain proportion;
the ivory recognition model building module is used for building an ivory recognition model, training parameters of the ivory recognition model by using training set data, performing performance test on the ivory recognition model by using test set data, and optimizing the ivory recognition model according to a test result;
the ivory recognition model is used for reading a suspected ivory texture image and outputting a recognition result.
9. The ivory product identification system of claim 8, wherein the image acquisition device comprises a liftable support, an industrial camera, a light source module, a magnifying glass, a ruler, a sample holder, an object stage, an image acquisition switch, a wireless communication module, a power supply and interface module;
the industrial camera, the light source module, the image acquisition switch, the wireless communication module and the power supply and interface module form a whole and are connected with the lifting support, so that the height can be adjusted;
the magnifying lens and the scale form a whole and are connected with the lifting support, so that the height can be adjusted;
the optical axes of the magnifier and the industrial camera lens are in the same straight line;
the sample fixer and the objective table form a whole and are fixedly connected with the bottom of the lifting support so as not to move.
10. An electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing a method of ivory product identification as claimed in any of claims 1 to 7 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211155323.9A CN115546536A (en) | 2022-09-22 | 2022-09-22 | Ivory product identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211155323.9A CN115546536A (en) | 2022-09-22 | 2022-09-22 | Ivory product identification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115546536A true CN115546536A (en) | 2022-12-30 |
Family
ID=84729799
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211155323.9A Pending CN115546536A (en) | 2022-09-22 | 2022-09-22 | Ivory product identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115546536A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117740712A (en) * | 2024-02-19 | 2024-03-22 | 中国海关科学技术研究中心 | Ivory for customs ports and method and system for rapid preliminary screening and identification of products thereof |
| CN117975044A (en) * | 2024-02-20 | 2024-05-03 | 蚂蚁云创数字科技（北京）有限公司 | Image processing method and device based on feature space |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1797420A (en) * | 2004-12-30 | 2006-07-05 | 中国科学院自动化研究所 | Method for recognizing human face based on statistical texture analysis |
| CN101315669A (en) * | 2008-07-15 | 2008-12-03 | 北京石油化工学院 | Floatation foam image processing method and device |
| CN112633297A (en) * | 2020-12-28 | 2021-04-09 | 浙江大华技术股份有限公司 | Target object identification method and device, storage medium and electronic device |
| CN113283446A (en) * | 2021-05-27 | 2021-08-20 | 平安科技（深圳）有限公司 | Method and device for identifying target object in image, electronic equipment and storage medium |
| CN113792827A (en) * | 2021-11-18 | 2021-12-14 | 北京的卢深视科技有限公司 | Target object recognition method, electronic device, and computer-readable storage medium |
-
2022
- 2022-09-22 CN CN202211155323.9A patent/CN115546536A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1797420A (en) * | 2004-12-30 | 2006-07-05 | 中国科学院自动化研究所 | Method for recognizing human face based on statistical texture analysis |
| CN101315669A (en) * | 2008-07-15 | 2008-12-03 | 北京石油化工学院 | Floatation foam image processing method and device |
| CN112633297A (en) * | 2020-12-28 | 2021-04-09 | 浙江大华技术股份有限公司 | Target object identification method and device, storage medium and electronic device |
| CN113283446A (en) * | 2021-05-27 | 2021-08-20 | 平安科技（深圳）有限公司 | Method and device for identifying target object in image, electronic equipment and storage medium |
| CN113792827A (en) * | 2021-11-18 | 2021-12-14 | 北京的卢深视科技有限公司 | Target object recognition method, electronic device, and computer-readable storage medium |
Non-Patent Citations (5)
| Title |
|---|
| 安冬 等: "智慧农业关键技术集成与应用系列丛书 水下图像与视觉智能处理技术及应用", 28 February 2022, 北京：中国农业大学出版社, pages: 264 * |
| 杨帆: "数字图像处理与分析", 31 May 2015, 北京：北京航空航天大学出版社, pages: 307 - 308 * |
| 杨明: "电力系统运行调度的有效静态安全域法", 31 July 2019, 北京：机械工业出版社, pages: 12 * |
| 葛致磊 等: "导弹导引系统原理", 31 March 2016, 北京：国防工业出版社, pages: 134 * |
| 赵玥: "基于图小波变换的纹理分类与SAR图像识别", 中国优秀硕士学士论文全文数据库信息科技辑, no. 08, pages 3 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117740712A (en) * | 2024-02-19 | 2024-03-22 | 中国海关科学技术研究中心 | Ivory for customs ports and method and system for rapid preliminary screening and identification of products thereof |
| CN117740712B (en) * | 2024-02-19 | 2024-04-19 | 中国海关科学技术研究中心 | Ivory for customs ports and method and system for rapid preliminary screening and identification of products thereof |
| CN117975044A (en) * | 2024-02-20 | 2024-05-03 | 蚂蚁云创数字科技（北京）有限公司 | Image processing method and device based on feature space |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103518224B (en) | Method for analysing microbial growth | |
| CN115546536A (en) | Ivory product identification method and system | |
| CN111667455B (en) | AI detection method for brushing multiple defects | |
| CN106909941A (en) | Multilist character recognition system and method based on machine vision | |
| CN109447945B (en) | Quick counting method for basic wheat seedlings based on machine vision and graphic processing | |
| CN110210448B (en) | Intelligent face skin aging degree identification and evaluation method | |
| JP5333570B2 (en) | Image processing apparatus, program, and image processing system | |
| CN108181316B (en) | Bamboo strip defect detection method based on machine vision | |
| CN108109133B (en) | Silkworm egg automatic counting method based on digital image processing technology | |
| CN111879735B (en) | Rice appearance quality detection method based on image | |
| CN112215790A (en) | KI67 index analysis method based on deep learning | |
| CN113723573A (en) | Tumor tissue pathological classification system and method based on adaptive proportion learning | |
| CN108009567B (en) | Automatic excrement character distinguishing method combining image color and HOG and SVM | |
| US20210214765A1 (en) | Methods and systems for automated counting and classifying microorganisms | |
| CN113706490B (en) | Wafer defect detection method | |
| CN109182081A (en) | A kind of unicellular separation system based on image processing model | |
| CN114359539A (en) | Intelligent identification method for high-spectrum image of parasite in sashimi | |
| CN116559111A (en) | Sorghum variety identification method based on hyperspectral imaging technology | |
| CN112581452A (en) | Industrial accessory surface defect detection method and system, intelligent device and storage medium | |
| CN116105691A (en) | Method for batch determination of leaf phenotypic traits and related equipment | |
| Triantoro et al. | Image based water gauge reading developed with ANN Kohonen | |
| CN110569716A (en) | Goods shelf image copying detection method | |
| CN111707672A (en) | Method for detecting surface defects of wind power rotary supporting piece | |
| CN116645351A (en) | Online defect detection method and system for complex scene | |
| CN110910403A (en) | Industrial hemp seed counting method based on image processing |
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 |