CN111160414A - A high-precision identification method of crop disease and insect pest images - Google Patents

A high-precision identification method of crop disease and insect pest images Download PDF

Info

Publication number
CN111160414A
CN111160414A CN201911271371.2A CN201911271371A CN111160414A CN 111160414 A CN111160414 A CN 111160414A CN 201911271371 A CN201911271371 A CN 201911271371A CN 111160414 A CN111160414 A CN 111160414A
Authority
CN
China
Prior art keywords
coverage
image
features
sampling
feature
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
CN201911271371.2A
Other languages
Chinese (zh)
Other versions
CN111160414B (en
Inventor
高燕
何瑞
唐聃
曾琼
岳希
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.)
Chengdu University of Information Technology
Original Assignee
Chengdu University of Information Technology
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 Chengdu University of Information Technology filed Critical Chengdu University of Information Technology
Priority to CN201911271371.2A priority Critical patent/CN111160414B/en
Publication of CN111160414A publication Critical patent/CN111160414A/en
Application granted granted Critical
Publication of CN111160414B publication Critical patent/CN111160414B/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
    • G06F18/21—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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Forestry; Mining

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Health & Medical Sciences (AREA)
  • Business, Economics & Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Mining & Mineral Resources (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Agronomy & Crop Science (AREA)
  • Animal Husbandry (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Image Analysis (AREA)

Abstract

本发明涉及一种高精度农作物病虫害图像的识别方法，具体是先对图像进行细化的特征提取，把这些提取到的特征构成一个特征集，再将该特征集里面的特征构造不同的图形，接着通过多维度神经节点依次对每个图形进行覆盖并把在该多维度神经节点覆盖范围里面的特征从特征集里面剥离出去，然后依前述过程逐一对特征空间集里面构造的每个图形进行覆盖，直到将特征集里面的所有特征剥离空为止，此时根据得出的最终覆盖范围来推导出图像识别的不连续落差覆盖率即识别的精确度。本发明构思合理，提高了识别的维度，能在大量异构数据集中很好的提取图像的特征并进行分类识别，不存在随着图像数据量的增大而降低了识别精度的问题，显著提高了图像识别精确度。

Figure 201911271371

The invention relates to a high-precision identification method for crop diseases and insect pests images. Specifically, the image is firstly extracted with refined features, the extracted features are formed into a feature set, and then different graphics are constructed from the features in the feature set. Then, each graph is covered in turn by the multi-dimensional neural node, and the features in the coverage of the multi-dimensional neural node are stripped from the feature set, and then each graph constructed in the feature space set is covered one by one according to the aforementioned process. , until all the features in the feature set are stripped to empty, at this time, according to the final coverage obtained, the discontinuous drop coverage of image recognition, that is, the recognition accuracy, is deduced. The invention has a reasonable conception, improves the dimension of recognition, can well extract the features of images in a large number of heterogeneous data sets and perform classification and recognition, and does not have the problem of reducing the recognition accuracy with the increase of the amount of image data, and significantly improves the image recognition accuracy.

Figure 201911271371

Description

High-precision crop disease and insect pest image identification method
Technical Field
The invention relates to the technical field of image recognition, in particular to a high-precision crop disease and insect pest image recognition method.
Background
Computer vision technology was used mainly for the recognition and analysis of two-dimensional images in the fifties of the last century, and scientists began to study the recognition of three-dimensional images using computer vision technology in the sixties. Until the eighties of the last century, more scholars put forward many new theories and research methods in the computer vision aspect, which also lays a foundation for the application and research of the computer vision technology in the agriculture aspect. In the early days, people can not well apply the computer vision technology to the intelligent agriculture, especially to the identification of crop diseases and insect pests. Early agricultural pest identification was mainly against manual recording and photographing techniques, which severely affected timely treatment of crop pests.
In the aspect of agricultural application, the early image pattern recognition technology is mainly applied to the aspects of crop quality monitoring, crop growth environment control, crop classification and the like. But there is little technology and scientific research associated with the identification and classification of crop pests in smart agriculture. On the basis, some scientists abroad begin to research and experiment on the identification and classification of crop diseases and insect pests by the computer vision technology earlier, while the research and application of the computer vision technology in China are late due to the immaturity of the early technology, and the development and the application of the computer vision technology are mainly monitored and recorded by agricultural experts on site and the conditions of the crop diseases and insect pests, so that the application of the intelligent identification technology for the diseases and insect pests is not wide.
The most important of intelligent pest and disease identification is to extract the features of each image, and the traditional pest and disease image identification mainly utilizes a convolutional neural network mode to perform classification identification. The method comprises the steps of classifying and identifying the collected image features by utilizing the hierarchy of a convolutional neural network system structure and the learning characteristic of the neural network structure, and classifying the image by utilizing a softmax function (also called polynomial logistic regression). However, in the case where image data is particularly large, the prediction performance of the classification method using the softmax function is low. To obtain higher image recognition accuracy through the convolutional neural network mode, more learning parameters in the convolutional neural network and training data amount in the convolutional neural network mode are needed, so that the recognition complexity is increased, and the image data classification complexity is increased. Besides, under the condition that the image pixel and size are not changed, if the depth of the structure of the convolutional neural network is continuously increased, the accuracy of image recognition cannot be improved along with the increase of the structure depth.
At present, an image feature extraction method and a Bionic Pattern (BPR) identification method based on a Convolutional Neural Network (CNN) are mainly available.
The image feature extraction method based on the convolutional neural network mainly comprises forward propagation and backward propagation of the convolutional neural network, wherein the forward propagation and the backward propagation are carried out on the convolutional neural network, the convolutional layer with the alternating function and an architecture of the convolutional neural network are used, an output layer is arranged in the architecture, each character class in the output layer is represented by a single node, after the convolutional neural network is trained, only parameters in large connecting layers are reserved, so that feature vectors in the large connecting layers are extracted by the parameters, and then the feature vectors are classified and identified by a classifier. The image feature extraction method based on the convolutional neural network mainly uses the learning characteristic of the neural network, simultaneously needs to be divided into a plurality of layers, the corresponding training methods of each layer are different, but the image data needs to be concentrated and normalized, so that if images with different sizes are available, the images cannot be trained together and can only be divided, and the convolutional neural network only has the learning function but does not have the memory function, so that the convolutional neural network is used for processing common two-dimensional images, but is not ideal for the processing capability of videos or natural languages.
The bionic mode recognition model method is a model method based on material recognition, which simulates the cognitive function of human beings, so as to classify images and finally recognize the images according to the classifications; the classification process of the bionic mode recognition is mainly that complex geometric figures are constructed in a pixel space, then convolutional nerves are used for covering the figures, the minimum distance of each base point in the figures is found out at the same time, and finally the images covered by the latitude are calculated for classification, and then the images are recognized; the bionic pattern recognition model method is a method focusing on classification recognition, and comprises the steps of constructing complex geometric figures in a pixel space and covering the figures by using convolution nerves, wherein in the covering process, the coverage rate is reduced when the space dimension is increased, and in the case of overlarge data set, the coverage of the space figures becomes troublesome, so that the efficiency is reduced, and the recognition accuracy is reduced.
In view of the foregoing, there is a need for further improvements and innovations in the prior art.
Disclosure of Invention
The invention aims to provide a high-precision crop pest and disease image identification method which is reasonable in conception on the premise of an original CNN (convolutional neural network) model and a BPR (bionic pattern recognition) model, can be used for covering each single shape by using multi-dimensional neural nodes so as to remove the limitation on image identification dimensionality, improves the identification dimensionality, can well extract the characteristics of an image in a large number of heterogeneous data sets and perform classification identification, does not have the problem that the identification precision is reduced along with the increase of the image data quantity, and obviously improves the image identification precision.
The technical scheme of the invention is as follows:
the method for identifying the high-precision crop disease and insect pest image specifically comprises the steps of firstly extracting the refined features of the image, forming a feature set by the extracted features, constructing different graphs by the features in the feature set, then sequentially covering each graph through multi-dimensional nerve nodes, stripping the features in the coverage range of the multi-dimensional nerve nodes from the feature set, then covering each graph constructed in a feature space set one by one through the multi-dimensional nerve nodes according to the process until all the features in the feature set are stripped to be empty, and deriving the discontinuous fall coverage rate of image identification, namely the identification accuracy according to the obtained final coverage range.
The high-precision crop disease and insect pest image identification method specifically comprises the following steps:
(1) constructing a training set H, H ═ H1，H2，…，HLWhere the training set contains N classes, HKIs the kth class, contains N sampling points, HK＝{L1，L2，…，LN}；
(2) Calculate HKDistance between any two sampling points, and from HKFind two sampling points M in11And M12Let ρ (M)11，M12) Is the smallest Hi，Hi∈SK{ρ(Hi，Hj) In which H isi≠Hj；
(3) Find out the third sampling point M13，M13∈HK-{M11，M12But not at sample M11And sample M12On the straight line of the component, then connecting M13，M11And M12The three sampling points form a plane triangle A1；
(4) The triangular pixel region A is then neuron-pair1Coverage, size of covered space P1＝{Y|ρYF1＜Fh，Y∈RnWhere ρ YF1Denotes Y and F1The distance between them;
(5) judging whether each sampling point in H is at P1If the sampling point is in the coverage area, stripping the sampling point from the H, and allowing the H to standK＝HK-{Li|Li∈P1}；
(6) From the set HKThen find a new sampling point M21And let the new sampling point M21And M13、M11、M12Distance between the three sampling pointsThe sum of the distances is minimum;
(7) for { M13，M11，M12Two of the three samples are renamed to M22And M23Knowing the two sampling points M22And M23Is and sample point M21Two sampling points with the shortest distance, and then M22，M23，M21Joined to form a second planar triangle A2；
(8) Using neurons to pixel triangle region A2Coverage, size of covered space P2Set HKValue of (A) becomes HK＝HK-{M21}；
(9) Repeating the steps (5) to (7) to find another sampling point Mi，Mi∈HKThe newly found sample point is then marked as Mi1And separating M as in step (7)i1The nearest two sampling points are respectively marked as Mi2And Mi3；
(10) Then connect Mi3，Mi1And Mi2The three sampling points form a plane triangle Ai(ii) a Covering this with neurons, the size of the covered space PiSet HKValue of (A) becomes HK＝HK-{Mi}；
(11) And finally, judging whether the HK set is an empty set, if not, repeating the steps (9) - (10) until the HK set is empty, and if so, deducing discontinuous fall coverage rate of image recognition, namely recognition accuracy according to the obtained final coverage range of the K classes.
The high-precision crop disease and pest image identification method comprises the following steps: the image recognition method uses multi-dimensional neural nodes to overlay each single shape; the multidimensional neural nodes and single shapes are defined as follows:
① setting A0，A1，…，As(S.ltoreq.N) is an N-dimensional feature space VSPoints, vectors, within which are mutually uncorrelated
Figure BDA0002314027080000041
Have no linear correlation, i.e. have linear independence; there is one set of pixel points
Figure BDA0002314027080000042
Ω S is A0，A1，…，AsAn S-dimension single shape for a vertex;
② setting Q to be a polyhedron within a feature space, where feature space VSSatisfy, y ∈ VSand/Q. While the distance between y and the polyhedron Q satisfies the equation L (y, Q) ═ Lmin|Lmin＝min(L(x，y))，
Figure BDA0002314027080000043
Figure BDA0002314027080000044
If there is one R satisfying
Figure BDA0002314027080000045
When Ah is more than 0, R can be called probability coverage to the polyhedron;
when the Q in the definition of steps ① and ② is a line, then R is a straight-through neuron, when Q is a planar triangle, then R is a three-dimensional neuron, and when Q is a tetrahedron, then R is a four-dimensional neuron.
Has the advantages that:
the high-precision crop disease and insect pest image identification method does not reduce the identification precision along with the increase of the image data quantity. In the method, the image data set is classified, N triangular areas are constructed in multiple dimensions, and the triangular areas constructed by the N triangular areas are covered by the neural network, so that the limitation on the image identification dimension is removed, and the identification dimension is effectively improved. Meanwhile, the characteristics of the image can be well extracted from a large number of heterogeneous data sets and classified and identified, and the accuracy of image identification is greatly improved. Because the image is divided into different blocks in image recognition, each block contains as little pixel information as possible, the invention can extract the image features as accurately as possible in the process of splitting and extracting the image features, and can perform coverage classification as comprehensively as possible in the process of coverage classification, thereby saving the complexity of the recognition work and more importantly improving the accuracy of the image recognition.
Drawings
FIG. 1 is a flow chart of the high-precision crop pest image identification method of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention are described below clearly and completely, and it is obvious that the described embodiments are some, not all embodiments of the present invention. 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.
In smart agriculture, pest recognition of crops plays a crucial role. In order to ensure the accuracy of identification, the identification method of the high-precision crop disease and insect pest image uses multidimensional neural nodes to cover each single shape; wherein the multidimensional neural nodes and the single shape are defined as follows:
(1) setting A0，A1，…，As(S.ltoreq.N) is an N-dimensional feature space VSPoints within which are not related to each other, then vectors
Figure BDA0002314027080000051
Neither has a linear dependence, that is to say a linear independence. There is one set of pixel points
Figure BDA0002314027080000052
Ω S is A0，A1，…，AsIs an S-dimensional single shape of the vertex. That is, the line segment, the plane figure and the polyhedron are respectively regarded as a one-dimensional, two-dimensional and multi-dimensional simple figure in the multi-dimensional spaceIn single form.
(2) Let Q be a polyhedron within a feature space, where feature space VSSatisfy, y ∈ VSand/Q. While the distance between y and the polyhedron Q satisfies the equation L (y, Q) ═ Lmin|Lmin＝min(L(x，y))，
Figure BDA0002314027080000053
Figure BDA0002314027080000061
If there is one R satisfying
Figure BDA0002314027080000062
Ah > 0, then we can call this R as probabilistic coverage for the polyhedron.
When Q within the above definition is a line segment, then R is a straight-through neuron; when Q is a plane triangle, R is a three-dimensional neuron; when Q is a tetrahedron, R is a four-dimensional neuron.
Whether a certain identification method has good practicability or not needs to be measured, the identification complexity under the condition that the image data set is large and the accuracy of the identified result need to be considered; on the basis, the image can be subjected to refined feature extraction firstly, a feature space is constructed according to the extracted features, then a plurality of different graphs are constructed in the feature space, the graphs are covered, and then accurate classification and identification are carried out according to the feature coverage, so that the identification efficiency is high, and the accuracy is high.
As shown in fig. 1, the method for identifying high-precision crop pest and disease images of the present invention specifically includes the steps of performing refined feature extraction on an image, forming a feature set by using the extracted features, constructing different patterns by using the features in the feature set, sequentially covering each pattern by using multidimensional neural nodes, stripping the features in the coverage range of the multidimensional neural nodes from the feature set, covering each pattern constructed in a feature space set one by using the multidimensional neural nodes according to the process until all the features in the feature set are stripped to be empty, and deriving the discontinuous fall coverage rate of image identification, namely the identification precision, according to the obtained final coverage range.
The invention relates to a high-precision crop disease and insect pest image identification method, which specifically comprises the following steps:
(1) constructing a training set H, H ═ H1，H2，…，HLWhere the training set contains N classes, HKIs the kth class, contains N sampling points, HK＝{L1，L2，…，LN}；
(2) Calculate HKDistance between any two sampling points, and from HKFind two sampling points M in11And M12Let ρ (M)11，M12) Is the smallest Hi，Hi∈SK{ρ(Hi，Hj) In which H isi≠Hj；
(3) Find out the third sampling point M13，M13∈HK-{M11，M12But not at sample M11And sample M12On the straight line of the component, then connecting M13，M11And M12The three sampling points form a plane triangle A1；
(4) The triangular pixel region A is then neuron-pair1Coverage, size of covered space P1＝{Y|ρYF1＜Fh，Y∈RnWhere ρ YF1Denotes Y and F1The distance between them;
(5) judging whether each sampling point in H is at P1If the sampling point is in the coverage area, stripping the sampling point from the H, and allowing the H to standK＝HK-{Li|Li∈P1}；
(6) From the set HKThen find a new sampling point M21And let the new sampling point M21And M13、M11、M12The sum of the distances of the three sampling points is minimum;
(7) for { M13，M11，M12Two of the three samples are renamed to M22And M23Knowing the two sampling points M22And M23Is and sample point M21Two sampling points with the shortest distance, and then M22，M23，M21Joined to form a second planar triangle A2；
(8) Using neurons to pixel triangle region A2Coverage, size of covered space P2Set HKValue of (A) becomes HK＝HK-{M21}；
(9) Repeating the steps (5) to (7) to find another sampling point Mi，Mi∈HKThe newly found sample point is then marked as Mi1And separating M as in step (7)i1The nearest two sampling points are respectively marked as Mi2And Mi3；
(10) Then connect Mi3，Mi1And Mi2The three sampling points form a plane triangle Ai(ii) a Covering this with neurons, the size of the covered space PiSet HKValue of (A) becomes HK＝HK-{Mi}；
(11) Finally, judge HKAnd (4) whether the set is an empty set or not, if not, repeating the steps (9) - (10) until the set is empty, and if so, deducing discontinuous fall coverage rate of image recognition, namely recognition accuracy according to the obtained final coverage range of the K classes.
The method has reasonable conception, and uses the multi-dimensional neural nodes to cover each single shape so as to remove the limitation on the dimension of image recognition, improve the dimension of recognition, well extract the characteristics of the image in a large number of heterogeneous data sets and carry out classification recognition, avoid the problem of reducing the recognition precision along with the increase of the image data volume, and obviously improve the image recognition precision.

Claims (3)

1.一种高精度农作物病虫害图像的识别方法，其特征在于，具体是先对图像进行细化的特征提取，把这些提取到的特征构成一个特征集，再将该特征集里面的特征构造不同的图形，接着通过多维度神经节点依次对每个图形进行覆盖并把在该多维度神经节点覆盖范围里面的特征从特征集里面剥离出去，然后依前述过程通过多维度神经节点逐一对特征空间集里面构造的每个图形进行覆盖，直到将特征集里面的所有特征剥离空为止，此时根据得出的最终覆盖范围来推导出图像识别的不连续落差覆盖率即识别的精确度。1. A method for identifying images of high-precision crop diseases and insect pests, characterized in that, firstly, the image is refined by feature extraction, the extracted features are formed into a feature set, and then the features in the feature set are structured differently. Then, through the multi-dimensional neural nodes, each graph is covered in turn, and the features in the coverage of the multi-dimensional neural nodes are stripped from the feature set, and then the feature space sets are paired one by one through the multi-dimensional neural nodes according to the aforementioned process. Each image constructed in it is covered until all the features in the feature set are stripped and empty. At this time, the discontinuous drop coverage of image recognition, that is, the recognition accuracy, is deduced according to the final coverage obtained. 2.如权利要求1所述的高精度农作物病虫害图像的识别方法，其特征在于，具体包括以下步骤：2. the identification method of the high-precision crop disease and insect pest image as claimed in claim 1, is characterized in that, specifically comprises the following steps: (1)构造一个训练集H，H＝{H1，H2，…，HL}，其中训练集中包含了N个类，HK是第k个类，包含了N个采样点，HK＝{L1，L2，…，LN}；(1) Construct a training set H, H = {H 1 , H 2 , . ={L 1 , L 2 ,...,L N }; (2)计算HK中任意两个采样点之间的距离，并从HK中找两个采样点M11和M12，令ρ(M11，M12)为最小的Hi，Hi∈SK{ρ(Hi，Hj)}，其中Hi≠Hj；(2) Calculate the distance between any two sampling points in HK, and find two sampling points M 11 and M 12 from HK , let ρ (M 11 , M 12 ) be the smallest H i , H i ∈ S K {ρ(H i , H j )}, where H i ≠H j ; (3)找出第三个采样点M13，M13∈HK-{M11，M12}但不在采样M11和采样M12组成的直线上面，然后连接M13，M11和M12这三个采样点组成一个平面的三角形A1；(3) Find the third sampling point M 13 , M 13 ∈ H K -{M 11 , M 12 } but not on the straight line formed by sampling M 11 and sampling M 12 , and then connect M 13 , M 11 and M 12 The three sampling points form a plane triangle A 1 ; (4)再用神经元对三角形像素区域A1覆盖，覆盖的空间大小P1＝{Y|ρYF1＜Fh，Y∈Rn}，其中ρYF1表示Y和F1之间的距离；(4) The triangular pixel area A 1 is covered by neurons again, and the covered space size P 1 ={Y|ρYF 1 <Fh, Y∈R n }, where ρYF 1 represents the distance between Y and F 1 ; (5)判断H里面的每个采样点是否都在P1的覆盖范围里面，如果在覆盖范围里面，就把这个采样点从H里面剥离，并让HK＝HK-{Li|Li∈P1}；(5) Determine whether each sampling point in H is within the coverage of P 1 , if it is within the coverage, strip this sampling point from H, and let H K =H K -{L i |L i ∈ P 1 }; (6)从集合HK里面再找一个新采样点M21，并让该新采样点M21与M13、M11、M12这三个采样点的距离之和值最小；(6) Find a new sampling point M 21 from the set HK , and let the sum of the distances between the new sampling point M 21 and the three sampling points M 13 , M 11 and M 12 be the smallest; (7)对{M13，M11，M12}这三个采样点里面的两个采样点进行重新命名为M22和M23，已知这两个采样点M22和M23是和采样点M21距离最短的两个采样点，然后把M22，M23，M21连接起来组成第二个平面三角形A2；(7) Rename two sampling points in the three sampling points {M 13 , M 11 , M 12 } as M 22 and M 23 , it is known that these two sampling points M 22 and M 23 are sum sampling Point M 21 is the two sampling points with the shortest distance, and then connect M 22 , M 23 , and M 21 to form a second plane triangle A 2 ; (8)再用神经元对像素三角形区域A2覆盖，覆盖的空间大小P2，集合HK的值变为HK＝HK-{M21}；(8) The pixel triangle area A 2 is covered by neurons again, and the covered space size is P 2 , and the value of the set HK becomes HK = HK -{M 21 } ; (9)重复步骤(5)-(7)找出另外一个采样点Mi，Mi∈HK，然后将新找的采样点标记为Mi1、并且像步骤(7)那样把离Mi1最近的两个采样点分别标记为Mi2和Mi3；(9) Repeat steps (5)-(7) to find another sampling point M i , M i ∈ H K , then mark the newly found sampling point as M i1 , and set the distance from M i1 as in step (7) The two nearest sampling points are marked as M i2 and M i3 ; (10)然后连接Mi3，Mi1和Mi2这三个采样点组成一个平面的三角形Ai；再用神经元对此进行覆盖，覆盖的空间大小Pi，集合HK的值变为HK＝HK-{Mi}；(10) Then connect the three sampling points M i3 , M i1 and M i2 to form a plane triangle A i ; then cover this with neurons, the covered space size P i , the value of the set H K becomes H K =H K -{M i }; (11)最后判HK集合是否是空集，如果不是空集就重复步骤(9)-(10)直到为空，如果为空就根据得出的K类的最终的覆盖范围来推导出图像识别的不连续落差覆盖率，即识别的精确度。(11) Finally, determine whether the H K set is an empty set. If it is not an empty set, repeat steps (9)-(10) until it is empty. If it is empty, deduce the image according to the final coverage of the K class. The identified discontinuity drop coverage, that is, the identification accuracy. 3.如权利要求1所述的高精度农作物病虫害图像的识别方法，其特征在于：所述图像识别方法使用多维度神经节点来对每个单一形状进行覆盖；所述多维度神经节点和单一形状定义如下：3. The method for recognizing high-precision images of crop diseases and insect pests as claimed in claim 1, wherein the image recognition method uses a multi-dimensional neural node to cover each single shape; the multi-dimensional neural node and a single shape Defined as follows: ①设定A0，A1，...，As(S≤N)是N维特征空间VS里面互相不相关的点，向量
Figure FDA0002314027070000025
(i＝1，2，…，S)都不具有线性相关性即具有线性独立性；则存在一个像素点集
Figure FDA0002314027070000021
ΩS是以A0，A1，…，As为顶点的S维度单一形状；①Set A 0 , A 1 ,...,A s (S≤N) to be the uncorrelated points in the N-dimensional feature space V S , the vector
Figure FDA0002314027070000025
(i=1, 2, .
Figure FDA0002314027070000021
ΩS is a single shape of S dimension with A 0 , A 1 , . . . , A s as vertices; ②设定Q是特征空间里面的一个多面体，其中特征空间VS满足，y∈VS/Q。同时y和多面体Q之间的距离满足等式
Figure FDA0002314027070000022
Figure FDA0002314027070000023
如果存在一个R满足
Figure FDA0002314027070000024
Ah＞0，就可把R叫做对多面体的概率覆盖；②Set Q to be a polyhedron in the feature space, where the feature space V S satisfies, y∈V S /Q. At the same time the distance between y and the polyhedron Q satisfies the equation
Figure FDA0002314027070000022
Figure FDA0002314027070000023
If there exists an R satisfying
Figure FDA0002314027070000024
Ah>0, R can be called the probability coverage of the polyhedron; 当上述步骤①和②定义里面的Q是一个线段的时候，那么R就是一个直通型神经元；当Q是一个平面三角形的时候，R就是一个三维神经元；当Q是一个四面体的时候，R就是一个四维度神经元。When Q in the definitions of steps ① and ② above is a line segment, then R is a straight-through neuron; when Q is a plane triangle, R is a three-dimensional neuron; when Q is a tetrahedron, R is a four-dimensional neuron.
CN201911271371.2A 2019-12-12 2019-12-12 High-precision crop disease and insect pest image identification method Active CN111160414B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911271371.2A CN111160414B (en) 2019-12-12 2019-12-12 High-precision crop disease and insect pest image identification method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911271371.2A CN111160414B (en) 2019-12-12 2019-12-12 High-precision crop disease and insect pest image identification method

Publications (2)

Publication Number Publication Date
CN111160414A true CN111160414A (en) 2020-05-15
CN111160414B CN111160414B (en) 2021-06-04

Family

ID=70557079

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911271371.2A Active CN111160414B (en) 2019-12-12 2019-12-12 High-precision crop disease and insect pest image identification method

Country Status (1)

Country Link
CN (1) CN111160414B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115205194A (en) * 2022-04-20 2022-10-18 浙江托普云农科技股份有限公司 Method, system and device for detecting coverage rate of sticky trap based on image processing
CN117557914A (en) * 2024-01-08 2024-02-13 成都大学 A method for identifying crop diseases and insect pests based on deep learning

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080244769A1 (en) * 2007-03-26 2008-10-02 Eby William H Soybean cultivar s060295
CN107067043A (en) * 2017-05-25 2017-08-18 哈尔滨工业大学 A kind of diseases and pests of agronomic crop detection method
WO2019106638A1 (en) * 2017-12-03 2019-06-06 Seedx Technologies Inc. Systems and methods for sorting of seeds
CN110084790A (en) * 2019-04-17 2019-08-02 电子科技大学成都学院 Bionic pattern identifies the algorithm improvement differentiated in iconography pneumonia
CN110517311A (en) * 2019-08-30 2019-11-29 北京麦飞科技有限公司 Pest and disease monitoring method based on leaf spot lesion area

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080244769A1 (en) * 2007-03-26 2008-10-02 Eby William H Soybean cultivar s060295
CN107067043A (en) * 2017-05-25 2017-08-18 哈尔滨工业大学 A kind of diseases and pests of agronomic crop detection method
WO2019106638A1 (en) * 2017-12-03 2019-06-06 Seedx Technologies Inc. Systems and methods for sorting of seeds
CN110084790A (en) * 2019-04-17 2019-08-02 电子科技大学成都学院 Bionic pattern identifies the algorithm improvement differentiated in iconography pneumonia
CN110517311A (en) * 2019-08-30 2019-11-29 北京麦飞科技有限公司 Pest and disease monitoring method based on leaf spot lesion area

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115205194A (en) * 2022-04-20 2022-10-18 浙江托普云农科技股份有限公司 Method, system and device for detecting coverage rate of sticky trap based on image processing
CN117557914A (en) * 2024-01-08 2024-02-13 成都大学 A method for identifying crop diseases and insect pests based on deep learning
CN117557914B (en) * 2024-01-08 2024-04-02 成都大学 A method for identifying crop diseases and insect pests based on deep learning

Also Published As

Publication number Publication date
CN111160414B (en) 2021-06-04

Similar Documents

Publication Publication Date Title
CN109902590B (en) Pedestrian re-identification method for deep multi-view characteristic distance learning
CN108509920B (en) CNN-based face recognition method for multi-patch multi-channel joint feature selection learning
CN111008618B (en) Self-attention deep learning end-to-end pedestrian re-identification method
CN109241995B (en) An Image Recognition Method Based on Improved ArcFace Loss Function
CN111898432B (en) Pedestrian detection system and method based on improved YOLOv3 algorithm
CN103207910B (en) Image retrieval method based on hierarchical features and genetic programming relevance feedback
CN113538390A (en) Quick identification method for shaddock diseases and insect pests
CN110188635A (en) A Plant Disease and Pest Recognition Method Based on Attention Mechanism and Multi-level Convolutional Features
CN110991349B (en) A Lightweight Vehicle Attribute Recognition Method Based on Metric Learning
CN110110596B (en) Hyperspectral image feature extraction, classification model construction and classification method
CN107408211A (en) Method for distinguishing is known again for object
CN115909052A (en) Hyperspectral remote sensing image classification method based on hybrid convolutional neural network
CN113392748B (en) Remote sensing image cultivated land information extraction method based on convolutional neural network
CN113033520A (en) Tree nematode disease wood identification method and system based on deep learning
CN109344699A (en) Disease identification method of winter jujube based on hierarchical deep convolutional neural network
CN107977660A (en) Region of interest area detecting method based on background priori and foreground node
CN113032613B (en) A 3D model retrieval method based on interactive attention convolutional neural network
CN114972208A (en) YOLOv 4-based lightweight wheat scab detection method
CN111160414B (en) High-precision crop disease and insect pest image identification method
CN106844739A (en) A kind of Remote Sensing Imagery Change information retrieval method based on neutral net coorinated training
Ma et al. Research on fish image classification based on transfer learning and convolutional neural network model
CN109614896A (en) A method for semantic understanding of video content based on recurrent convolutional neural network
CN114187590A (en) Method and system for identifying target fruits under homochromatic system background
CN115731579A (en) Individual recognition method of terrestrial animals based on cross-attention Transformer network
CN108230330A (en) A kind of quick express highway pavement segmentation and the method for Camera Positioning

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant