CN114445659A - Method for identifying authenticity of spina date seeds based on image color and texture characteristics - Google Patents

Method for identifying authenticity of spina date seeds based on image color and texture characteristics Download PDF

Info

Publication number
CN114445659A
CN114445659A CN202210066184.6A CN202210066184A CN114445659A CN 114445659 A CN114445659 A CN 114445659A CN 202210066184 A CN202210066184 A CN 202210066184A CN 114445659 A CN114445659 A CN 114445659A
Authority
CN
China
Prior art keywords
image
color
jujube kernel
jujube
spina date
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
Application number
CN202210066184.6A
Other languages
Chinese (zh)
Other versions
CN114445659B (en
Inventor
张霞
郭盛
王天舒
严辉
马新飞
段金廒
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Chinese Medicine
Original Assignee
Nanjing University of Chinese Medicine
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing University of Chinese Medicine filed Critical Nanjing University of Chinese Medicine
Priority to CN202210066184.6A priority Critical patent/CN114445659B/en
Priority claimed from CN202210066184.6A external-priority patent/CN114445659B/en
Publication of CN114445659A publication Critical patent/CN114445659A/en
Application granted granted Critical
Publication of CN114445659B publication Critical patent/CN114445659B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Image Analysis (AREA)
  • Spectrometry And Color Measurement (AREA)

Abstract

The invention discloses a method for identifying authenticity of spina date seeds based on image color and texture characteristics, belongs to the technical field of medicinal material identification, and specifically comprises the steps of collecting samples, collecting image data, extracting image color characteristics and image texture characteristics, and obtaining an identification model by adopting an integrated algorithm; firstly, extracting texture characteristics of image colors and gray level relations between adjacent pixel points, and then obtaining an authenticity spine date seed identification model through integrated algorithm training. The identification method is accurate and efficient, overcomes the defect of dependence on expensive precision instruments and equipment for identification, and provides a method reference for controlling the quality of the spina date seeds.

Description

Method for identifying authenticity of spina date seeds based on image color and texture characteristics
Technical Field
The invention belongs to the technical field of medicinal material identification; relates to an identification method of true and false wild jujube seeds based on image color and texture characteristics.
Background
The spina date seed is a dry mature seed of a Rhamnaceae plant Ziziphus jujuba (Ziziphus jujuba var. spinosa Hu ex H.F.Chou), is sweet, sour and neutral in taste, is a common heart-nourishing and nerve-soothing traditional Chinese medicine in clinical traditional Chinese medicine, and has the effects of nourishing heart, benefiting liver, calming heart, soothing nerves, arresting sweating and promoting the production of body fluid. Modern researches show that the spina date seed has definite efficacy of preventing and treating insomnia, and is one of the most common compatible medicines in a plurality of insomnia prevention and treatment formulas for a long time. The zizyphus vulgaris kernels (or called Yunnan ziziphus jujuba kernels and Burma zizyphus kernels) of the same genus plants as the spina ziziphus jujuba (Z. mauritiana Lam.) are mature seeds, and are often used as local conventional medicinal materials in Yunnan and peripheral areas of the production area for treating insomnia, and the zizyphus vulgaris is not produced and is not commonly used in other areas of China and is not income the national legal medicine standard.
With increasing market demand of wild jujube and the atrophy of wild jujube resources, the price of wild jujube medicinal materials is rising. Because the character characteristics of the wild jujube kernel and the wild jujube kernel are similar, the phenomenon that the wild jujube kernel is faked or adulterated is frequently found in the market. The traditional identification method mainly takes professional personnel to identify the shape and color characteristics of the two. Such methods rely on the experience and subjective feeling of professionals and are not conducive to efficient and large-scale detection of traditional Chinese medicines. In addition, medicinal material market research finds that illegal vendors fry or dye the jujube kernel to increase the similarity of appearance and characters of the jujube kernel and the wild jujube kernel, so that the traditional experience identification depending on color, fullness and the like is difficult to effectively identify the jujube kernel and the wild jujube kernel. The methods of distinguishing the truth of the wild jujube seed and the false substance thereof based on the UPLC-MS/MS method and the stable isotope technology, etc. of the scholars depend on expensive precision instruments, have higher detection cost and are not beneficial to popularization and application in the medicinal material market.
Disclosure of Invention
The invention aims to provide a method for identifying true or false wild jujube seeds. In order to solve the problems that the identification method is not beneficial to popularization, the detection cost is high and the like, the method for quickly identifying the true and false wild jujube seeds based on the image color and the texture characteristics is established so as to provide support for standardizing the market of wild jujube seeds.
In order to achieve the purpose, the invention provides the following technical scheme:
a method for identifying true or false wild jujube seeds based on image color and texture features specifically comprises the following steps:
step 1, collecting samples: selecting wild jujube kernels and raw products of different batches, frying, dyeing, frying and dyeing the wild jujube kernels in four forms;
step 2, image data acquisition: collecting high-definition images of wild jujube kernel and raw jujube kernel, parching, dyeing, parching and dyeing, and labeling wild jujube kernel, raw jujube kernel, parched jujube kernel, dyed jujube kernel, parched jujube kernel and dyed jujube kernel correspondingly;
step 3, extracting image color features: converting an original color image from an RGB color space to an HSV color space, and respectively calculating the color distribution of the image according to formulas (1) to (3) to form a color feature vector of the image;
Figure BDA0003480193210000021
Figure 100002_1
Figure 100002_2
where i is a color component, i ═ 1 is an H component (hue), i ═ 2 is an S component (saturation), i ═ 3 is a V component (lightness), and p is a color componentijIs the value of the color component i on the pixel j, N is the number of the pixel points of the image, mui，δi，siRespectively calculating a first moment, a second moment and a third moment of the image;
step 4, extracting image texture features:
step 4.1, calculating the gray value of the original image by adopting a formula (4):
wherein, gcRepresenting the gray value of the ith row and jth column pixel, Rc,Gc,BcRespectively representing RGB tristimulus values of ith row and jth column of the original image;
wherein G isc＝Rc*0.299+Gc*0.587+Bc*0.114 (4)
Step 4.2, calculating a relation value of local pixel points of the gray level image:
let the gray value of P adjacent pixel points with radius R be g0,g1,...,gP-1In turn with gcMaking a comparison if the ratio gcIf it is large, the pixel point is set to 1, otherwise, it is set to 0, and then U (LBP) is obtained according to the formula (5)P,R) Obtaining LBP according to equation 6P,R；
Figure 100002_3
Wherein the content of the first and second substances,
Figure BDA0003480193210000032
Figure BDA0003480193210000033
step 4.3, calculating the LBP texture characteristic vector of the image gray level relation value:
the value range of the gray level relation value of the image is {0,1,2,3,4,5,6,7,8,9}, a histogram of the gray level relation of the image is counted, and the LBP texture feature vector of the image can be obtained;
and 5, obtaining an identification model by adopting an integrated algorithm:
combining image color and texture features to obtain an image mixed feature vector, respectively randomly splitting wild jujube kernel and wild jujube kernel samples into training samples and test samples, training the training data by adopting an integrated algorithm to obtain an authenticity wild jujube seed identification model, inputting the feature vector of the test sample into the model, and predicting the authenticity identification result.
As a further preferable scheme of the method for identifying the authenticity of the wild jujube seeds based on the image color and the texture characteristics, in the step 1, the wild jujube seeds are respectively collected from 3 batches of inner dune of Hebei, Shandong Linyi and Shanxi Yanan, and 1 batch (produced from Shandong Jining) is collected from the Anhuo Zhou medicinal material market in Anhui, wherein each batch is 1 kg; the physiological jujube kernel, the fried jujube kernel, the dyed jujube kernel, the fried and dyed jujube kernel are 4 batches, each batch is 1kg, the physiological jujube kernel, the fried and dyed jujube kernel are all collected from the Anhui Bozhou medicinal material market, and the production place is Yunnan Ruili.
As a further preferable scheme of the method for identifying the authenticity of the spina date seeds based on the image color and the texture characteristics, in the step 2, a Canon full-frame digital camera is adopted to shoot pictures of the spina date seeds and the spina date seeds.
As a further preferable scheme of the method for identifying the authenticity of the wild jujube seeds based on the image color and the texture characteristics, in the step 5, the images of the wild jujube seeds and the raw jujube seeds are subjected to characteristic extraction, and the authenticity of the wild jujube seeds is identified after a model is obtained through boosting integration algorithm training in machine learning.
Compared with the prior art, the invention has the beneficial effects that:
the invention relates to an authenticity spine date seed identification method based on image color and texture characteristics, which extracts the texture characteristics of gray level relation between image color and adjacent pixel points and obtains an authenticity spine date seed identification model through integrated algorithm training. The identification method is accurate and efficient, overcomes the defect of dependence on expensive precision instruments and equipment for identification, and provides a method reference for controlling the quality of the spina date seeds.
Drawings
FIG. 1 is a flow chart of the operation of an embodiment of the present invention;
FIG. 2 is a diagram of the spine date seed and the four morphological patterns of "raw product, stir-fried, dyed, stir-fried and dyed" spine date seed according to the embodiment of the present invention;
FIG. 3 is a schematic diagram of image feature extraction according to an embodiment of the present invention;
FIG. 4 is a graph showing the identification results of the wild jujube kernel and the raw physical jujube kernel, the wild jujube kernel and the stir-fried physical jujube kernel, the wild jujube kernel and the dyed physical jujube kernel, and the wild jujube kernel and the stir-fried and dyed physical jujube kernel according to the embodiment of the present invention;
FIG. 5 shows the identification results of spine date seed and spine date seed in the present invention.
Detailed Description
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.
The present invention is illustrated below by specific examples, and the experimental methods described in the following examples are all conventional methods unless otherwise specified; the reagents and materials are commercially available, unless otherwise specified.
The instrument used in the invention: a canon full-frame digital camera (EOS 5DS R) is suitable for a 24-35mm wide-angle lens.
As shown in fig. 1 to 5, a method for identifying authenticity of a wild jujube seed based on image color and texture features specifically comprises the following steps:
step 1, collecting medicinal material samples: the wild jujube seed medicinal materials are respectively collected from 3 batches of inner mounds of Hebei, Shandong Yiyi and Shanxi Yanan, and 1 batch of medicinal materials (produced from Shandong Jinning) collected from the Bozhou market of Anhui province, wherein each batch is 1kg, and dried mature seeds of Ziziphus jujuba Mill. var. spinosa (Bunge) Hu ex H.F.Chou of Rhamnaceae are identified by professor of Jinkuang storehouse; 4 batches of jujube kernel medicinal materials (including physiological jujube kernel, fried jujube kernel, dyed jujube kernel, fried jujube kernel and dyed jujube kernel, each 1kg) in different treatment modes are all collected from the Zhou Anhui medicinal material market, produced in Yunnan Ruili, identified as dry mature seeds of Ziziphus mauritiana Lam of Rhamnaceae plant by professor of Jinstorehouse in section.
Step 2, collecting images of the medicinal material samples: 350 grains of 4 batches of spina date seed medicinal materials are randomly taken, 350 grains of four specifications of raw product, stir-frying, dyeing, stir-frying and dyeing are randomly taken for 4 batches of spina date seed medicinal materials, and pictures of each spina date seed and each spina date seed medicinal material (1400 spina date seeds and 1400 spina date seed kernels) are shot by adopting an Canon full-frame digital camera (EOS 5DS R). When the identification models of the spina date seed and the spina date seed are established and verified, the same number of photos of the medicinal materials are respectively taken: 350 parts of spina date seeds, 350 parts of raw physical jujube seeds, 350 parts of spina date seeds, 350 parts of fried physical jujube seeds, 350 parts of spina date seeds, 350 parts of dyed physical jujube seeds, 350 parts of spina date seeds, 350 parts of fried and dyed physical jujube seeds and 1400 parts of spina date seeds, wherein 1400 parts of raw and fried, dyed, fried and dyed are processed in four different processing modes.
Step 3, image color feature extraction: the RGB color space of an original image is converted into HSV color space by using an RGB2HSV function of a sketch color programming library, and then the color distribution of the image is respectively calculated by using formulas (1) to (3) to form a color feature vector of the image.
Figure BDA0003480193210000061
Figure 6
Figure 5
Where i is a color component, i ═ 1 is an H component (hue), i ═ 2 is an S component (saturation), i ═ 3 is a V component (lightness), and p isijIs the value of the color component i on the pixel j, N is the number of the pixel points of the image, mui，δi，siRespectively calculating a first moment, a second moment and a third moment of the image;
for example, the color feature vector for the spine date seed numbered "szr-003" is [ 0.310.230.650.420.250.320.450.260.32 ].
Step 4, extracting image texture features:
step 4.1, calculating the gray value of the original image by adopting a formula 4, wherein gcRepresenting the gray value of the pixel in the ith row and the jth column, Rc,Gc,BcRespectively representing original imagesRGB tristimulus values of ith row and jth column;
wherein G isc＝Rc*0.299+Gc*0.587+Bc*0.114 (4)
Step 4.2, calculating a relation value of local pixel points of the gray level image: let the gray value of P adjacent pixel points with radius R be g0,g1,...,gP-1In turn with gcMaking a comparison if the ratio gcIf it is large, the pixel point is set to 1, otherwise, it is set to 0, and then U (LBP) is obtained according to the formula 5P,R) Obtaining LBP according to equation 6P,R；
Figure 4
Wherein the content of the first and second substances,
Figure BDA0003480193210000071
Figure BDA0003480193210000072
4.3, calculating LBP texture characteristic vectors of the image gray level relation values; the value range of the gray scale relation value of the image is {0,1,2,3,4,5,6,7,8,9}, and the LBP texture feature vector of the image can be obtained by counting the histogram of the gray scale relation of the image.
For example, the texture feature vector for the spine date seed numbered "szr-003" is [ 0.040.060.040.110.140.140.070.080.190.13 ].
And 5, mixing the characteristics of image color and texture: the image color features and texture features are combined into a blended feature, for example, the texture feature vector for the spine date seed numbered "szr-003" is [ 0.310.230.650.420.250.320.450.260.320.040.060.040.110.140.140.070.080.190.13 ].
Step 6, establishing an authenticity spine date seed identification model: respectively randomly splitting the wild jujube kernel sample and the wild jujube kernel sample into a training sample (80%) and a testing sample (20%), training the mixed feature vector of the training image by adopting an integration algorithm to obtain an authenticity wild jujube kernel identification model, inputting the mixed feature vector of the testing image into the model, and predicting the authenticity identification result.
350 pieces of spina date seed pictures are respectively identified with 350 pieces of pictures of four different treatment modes of unprocessed product, stir-frying, dyeing, stir-frying and dyeing, the test data accounts for 20 percent and is 350 multiplied by 20 percent, 70 pieces, and F1-score (F1 score) for identifying spina date seed-physiological date seed, spina date seed-stir-fried and tidy date seed, spina date seed-dyed and tidy date seed and spina date seed-stir-fried and tidy date seed is 0.93 or more. In all the spina date seeds (1400 grains) and the four different processing modes of the spina date seeds (1400 grains), the spina date seeds and the spina date seeds for testing are 1400 multiplied by 20 to 280, the Precision (Precision), Recall rate (Recall) and F1-score (F score) of the spina date seeds and the spina date seeds for testing are all 0.95 or more, and therefore the true and false spina date seed identification model based on the image color and local texture characteristics can intelligently and better distinguish the spina date seeds and the spina date seeds.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.

Claims (4)

1. A method for identifying true or false wild jujube seeds based on image color and texture features is characterized by comprising the following steps: the method specifically comprises the following steps:
step 1, collecting samples: selecting wild jujube kernels and raw products of different batches, frying, dyeing, frying and dyeing the wild jujube kernels in four forms;
step 2, image data acquisition: collecting high-definition images of wild jujube kernel and raw jujube kernel, parching, dyeing, parching and dyeing, and labeling wild jujube kernel, raw jujube kernel, parched jujube kernel, dyed jujube kernel, parched jujube kernel and dyed jujube kernel correspondingly;
step 3, extracting image color features: converting an original color image from an RGB color space to an HSV color space, and respectively calculating the color distribution of the image according to formulas (1) to (3) to form a color feature vector of the image;
Figure FDA0003480193200000011
Figure 1
Figure 2
where i is a color component, i ═ 1 is an H component (hue), i ═ 2 is an S component (saturation), i ═ 3 is a V component (lightness), and p is a color componentijIs the value of the color component i on the pixel j, N is the number of the pixel points of the image, mui，δi，siRespectively calculating a first moment, a second moment and a third moment of the image;
step 4, extracting image texture features:
step 4.1, calculating the gray value of the original image by adopting a formula (4):
wherein, gcRepresenting the gray value of the ith row and jth column pixel, Rc,Gc,BcRespectively representing RGB tristimulus values of ith row and jth column of the original image;
wherein G isc＝Rc*0.299+Gc*0.587+Bc*0.114 (4)
Step 4.2, calculating a relation value of local pixel points of the gray level image:
let the gray value of P adjacent pixel points with radius R be g0,g1,...,gP-1In turn with gcMaking a comparison if the ratio gcIf it is large, the pixel point is set to 1, otherwise, it is set to0, obtaining U (LBP) according to the formula (5)P,R) Obtaining LBP according to the formula (6)P,R；
Figure 3
Wherein the content of the first and second substances,
Figure FDA0003480193200000022
Figure FDA0003480193200000023
step 4.3, calculating the LBP texture characteristic vector of the image gray level relation value:
the value range of the gray level relation value of the image is {0,1,2,3,4,5,6,7,8,9}, a histogram of the gray level relation of the image is counted, and the LBP texture feature vector of the image can be obtained;
and 5, obtaining an identification model by adopting an integrated algorithm:
combining image color and texture features to obtain an image mixed feature vector, respectively randomly splitting wild jujube kernel and wild jujube kernel samples into training samples and test samples, training the training data by adopting an integrated algorithm to obtain an authenticity wild jujube seed identification model, inputting the feature vector of the test sample into the model, and predicting the authenticity identification result.
2. The method for identifying the authenticity of the spina date seed based on the color and the texture characteristics of the image according to claim 1, wherein the method comprises the following steps of: in the step 1, the spina date seed medicinal materials are respectively collected from 3 batches of inner mound of Hebei, Shandong Linyi and Shanxi Yanan, and 1 batch (produced from Shandong Jining) is collected from the Anhuo Zhou medicinal material market, wherein each batch is 1 kg; the physiological jujube kernel, the fried jujube kernel, the dyed jujube kernel, the fried and dyed jujube kernel are 4 batches, each batch is 1kg, the physiological jujube kernel, the fried and dyed jujube kernel are all collected from the Anhui Bozhou medicinal material market, and the production place is Yunnan Ruili.
3. The method for identifying the authenticity of the spina date seed based on the color and the texture characteristics of the image according to claim 1, wherein the method comprises the following steps of: in step 2, a Canon full-frame digital camera is used to take pictures of the spina date seed and the fructus Jujubae seed.
4. The method for identifying the authenticity of the wild jujube seeds based on the color and the texture characteristics of the image as claimed in claim 1, wherein: in step 5, feature extraction is carried out on the images of wild jujube kernels and raw jujube kernels, fried, dyed, fried and dyed in four morphological manners, and identification of true and false wild jujube kernels is realized after a model is obtained through boosting integration algorithm training in machine learning.
CN202210066184.6A 2022-01-20 True and false spine date seed identification method based on image color and texture characteristics Active CN114445659B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210066184.6A CN114445659B (en) 2022-01-20 True and false spine date seed identification method based on image color and texture characteristics

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210066184.6A CN114445659B (en) 2022-01-20 True and false spine date seed identification method based on image color and texture characteristics

Publications (2)

Publication Number Publication Date
CN114445659A true CN114445659A (en) 2022-05-06
CN114445659B CN114445659B (en) 2024-07-12

Family

ID=

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101692052A (en) * 2009-08-31 2010-04-07 江苏大学 Hyperspectrum image technique-based method and hyperspectrum image technique-based device for identifying true and false famous tea
WO2011088594A1 (en) * 2010-01-25 2011-07-28 Thomson Licensing Video encoder, video decoder, method for video encoding and method for video decoding, separately for each colour plane
WO2015024383A1 (en) * 2013-08-19 2015-02-26 成都品果科技有限公司 Similarity acquisition method for colour distribution and texture distribution image retrieval
CN107292339A (en) * 2017-06-16 2017-10-24 重庆大学 The unmanned plane low altitude remote sensing image high score Geomorphological Classification method of feature based fusion
CN110895693A (en) * 2019-09-12 2020-03-20 华中科技大学 Authentication method and authentication system for anti-counterfeiting information of certificate
WO2020096368A1 (en) * 2018-11-09 2020-05-14 Samsung Electronics Co., Ltd. Image resynthesis using forward warping, gap discriminators, and coordinate-based inpainting
CN111931700A (en) * 2020-09-10 2020-11-13 华中农业大学 Corn variety authenticity identification method and identification system based on multiple classifiers
CN113011467A (en) * 2021-02-25 2021-06-22 南京中医药大学 Angelica sinensis medicinal material producing area identification method based on image structure texture information

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101692052A (en) * 2009-08-31 2010-04-07 江苏大学 Hyperspectrum image technique-based method and hyperspectrum image technique-based device for identifying true and false famous tea
WO2011088594A1 (en) * 2010-01-25 2011-07-28 Thomson Licensing Video encoder, video decoder, method for video encoding and method for video decoding, separately for each colour plane
WO2015024383A1 (en) * 2013-08-19 2015-02-26 成都品果科技有限公司 Similarity acquisition method for colour distribution and texture distribution image retrieval
CN107292339A (en) * 2017-06-16 2017-10-24 重庆大学 The unmanned plane low altitude remote sensing image high score Geomorphological Classification method of feature based fusion
WO2020096368A1 (en) * 2018-11-09 2020-05-14 Samsung Electronics Co., Ltd. Image resynthesis using forward warping, gap discriminators, and coordinate-based inpainting
CN110895693A (en) * 2019-09-12 2020-03-20 华中科技大学 Authentication method and authentication system for anti-counterfeiting information of certificate
CN111931700A (en) * 2020-09-10 2020-11-13 华中农业大学 Corn variety authenticity identification method and identification system based on multiple classifiers
CN113011467A (en) * 2021-02-25 2021-06-22 南京中医药大学 Angelica sinensis medicinal material producing area identification method based on image structure texture information

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
康晓兵;魏生民;: "基于谱相关性的数字图像真伪鉴别", 计算机工程与应用, no. 10, 1 April 2011 (2011-04-01) *
陶佳;王芳;沈红岩;高媛;: "基于改进局部二值模式算法的中草药图像鉴别", 河北农业大学学报, no. 02, 15 March 2020 (2020-03-15) *

Similar Documents

Publication Publication Date Title
CN102435713B (en) Automatic detection system for quality of traditional Chinese medicine
Yao et al. Quality variation of Goji (fruits of Lycium spp.) in China: a comparative morphological and metabolomic analysis
Zheng et al. A least-squares support vector machine (LS-SVM) based on fractal analysis and CIELab parameters for the detection of browning degree on mango (Mangifera indica L.)
CN105160346B (en) A kind of greasy recognition methods of curdy fur on tongue based on texture and distribution characteristics
CN103578098B (en) Method and device for extracting commodity body in commodity picture
CN110516668A (en) A kind of honey adulteration detection method and device based on high light spectrum image-forming technology
Zhang et al. Computerized facial diagnosis using both color and texture features
CN107154058A (en) A kind of method for guiding user to reduce magic square
CN109919224A (en) A kind of discrimination method of the Chinese medicine that interweaves truth with fiction based on artificial intelligence
CN110991463B (en) Multi-scale guide filtering feature extraction method under guidance of super-pixel map
Rao et al. Identification of medicinal plants using deep learning
Philip et al. Rice grain classification using Fourier transform and morphological features
CN114445659A (en) Method for identifying authenticity of spina date seeds based on image color and texture characteristics
CN106845505A (en) A kind of dried orange peel detection method based on deep learning
Wang et al. Image enhancement for crop trait information acquisition system
CN114445659B (en) True and false spine date seed identification method based on image color and texture characteristics
Castelo-Quispe et al. Optimization of brazil-nuts classification process through automation using colour spaces in computer vision
Chaugule et al. Evaluation of shape and color features for classification of four paddy varieties
Sonia et al. Medicinal Plants Classification by VisualCharacteristics of Leaves Using CNN
Xing et al. Research on image recognition technology of traditional Chinese medicine based on deep transfer learning
CN113989137A (en) Method for extracting pigmentation of facial skin image and forming spectrum of brown region
CN106991289A (en) A kind of capsule endoscope image auxiliary interpretation method
CN113011467A (en) Angelica sinensis medicinal material producing area identification method based on image structure texture information
Kaur et al. Automatic classification of turmeric rhizomes using the external morphological characteristics
CN107403181B (en) Lean meat and fat meat self-adaptive separation method based on Guangdong style sausage hyperspectral image

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