Construction method of maize leaf disease and pest detection model based on image recognition and application
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology for detecting models and construction methods, applied in character and pattern recognition, computer components, instruments, etc.
Inactive Publication Date: 2018-10-16
HENAN AGRICULTURAL UNIVERSITY
View PDF5 Cites 6 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0005] However, in the current field of corn pest control, there is still a lack of a f...
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0036] Embodiment 1: a kind of construction method of the corn leaf part disease and insect pest detection model based on image recognition, comprises the following steps:
[0037] 1) Obtain the learning sample set {(x i ,y i )|i=1, 2,..., N}, where, x i is the input parameter vector of the i-th sample, y i is the pest category of the i-th sample, and the label of the pest category is {1, -1}, where x i It is composed of the parameters of the lesion area S, perimeter P, circularity 0, rectangularity R, and shape complexity E of the corn leaf, y i is the corresponding output category, where y i = 1 means it is the pest, y i =-1 indicates that it is not a pest of this kind;
[0038] Among them, get the input parameter vector x i The process includes the following sub-steps,
[0039] a. Obtain the grayscale image of the corn leaf. When the obtained corn leaf image is in color, grayscale the color image to obtain the grayscale image of the corn leaf. You can also use a black...
Embodiment 2
[0064] Embodiment 2: a method for detecting pests and diseases of corn leaves based on image recognition, comprising the steps of:
[0065] 1. Obtain the sample to be detected, and preprocess the image of the lesion area of the corn leaf according to the method in step 1) in Example 1, so as to obtain the input parameter vector x corresponding to the lesion area of the sample to be detected and to be marked as a new point ;
[0066] 2. the number l of the slack variable ξ, the input parameter vector x of the sample to be detected and the α obtained in step 2) of the embodiment 1 i the optimal value of optimal value of b * , the kernel parameter g, the support vector x of the classifier i Substitute into the following formula:
[0067]
[0068] Solving for y i value, when y i = 1 means it is the pest, y i =-1 means that it is not a pest of this kind.
[0069] The process of using genetic algorithm to obtain the optimal RBF kernel function parameter g and penalty...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
PUM
Login to view more
Abstract
The invention discloses a maize leaf disease and pest detection method based on image recognition. According to the method, the disease and pest type of a to-be-detected maize leaf is obtained; for anacquired learning sample set {(xi,yi)|i=1,2,...,N} of a diseased region of the maize leaf, an optimal hyperplane of a support vector machine (SVM) model is solved through an SMO algorithm, wherein xiis an input parameter vector of the i(th) sample, yi is an output result of the i(th) sample, and xi is composed of parameters including the area S, circumference P, circularity O, rectangularity R and shape complexity E of the diseased region of the maize leaf; and a to-be-detected specimen is obtained and substituted into the optimal hyperplane of the SVM model to obtain a value of yi, whereinyi=1 indicates the disease and pest type, and yi=-1 does not indicate the disease and pest type. An SVM introducing slack variables and classification error penalty factors is adopted to learn a disease and pest image of the maize leaf, so that a large quantity of disease and pest results of the maize leaf are acquired easily in batch through detection equipment.
Description
technical field [0001] The invention relates to the technical field of crop disease and insect pest control, in particular to a construction method and application of a corn leaf disease and insect pest detection model based on image recognition. Background technique [0002] For the prevention and control of crop diseases and insect pests, being able to identify the types of diseases and insect pests in a timely and accurate manner is a prerequisite for effective prevention and control. For corn crops, common diseases are mainly reflected in the leaves, ears, and stems. Among them, the leaf diseases mainly include large leaf spot, small spot, Curvularia leaf spot, brown spot, bacterial stripe, Corn sheath purple spot, corn Alternaria leaf blight, corn round spot, corn spot blight, gray spot, corn ring spot, southern rust, sheath blight, etc. The symptoms of the diseases are different The shape of the corn is reflected in the leaves of the corn. Therefore, by identifying th...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more