CN113283470A - Green vegetable disease classification detection method based on human psychological cognition model - Google Patents
Green vegetable disease classification detection method based on human psychological cognition model Download PDFInfo
- Publication number
- CN113283470A CN113283470A CN202110405593.XA CN202110405593A CN113283470A CN 113283470 A CN113283470 A CN 113283470A CN 202110405593 A CN202110405593 A CN 202110405593A CN 113283470 A CN113283470 A CN 113283470A
- Authority
- CN
- China
- Prior art keywords
- sample
- disease
- samples
- normal
- human
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 201000010099 disease Diseases 0.000 title claims abstract description 62
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 62
- 235000013311 vegetables Nutrition 0.000 title claims abstract description 43
- 241000282414 Homo sapiens Species 0.000 title claims abstract description 30
- 238000001514 detection method Methods 0.000 title claims abstract description 20
- 230000019771 cognition Effects 0.000 title claims abstract description 16
- 238000012549 training Methods 0.000 claims abstract description 23
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 4
- 230000001149 cognitive effect Effects 0.000 claims description 5
- 230000003340 mental effect Effects 0.000 claims 1
- 241000238631 Hexapoda Species 0.000 description 4
- 241000282320 Panthera leo Species 0.000 description 3
- 241000607479 Yersinia pestis Species 0.000 description 3
- 230000007717 exclusion Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- 241000282412 Homo Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 229940088594 vitamin Drugs 0.000 description 1
- 229930003231 vitamin Natural products 0.000 description 1
- 235000013343 vitamin Nutrition 0.000 description 1
- 239000011782 vitamin Substances 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/68—Food, e.g. fruit or vegetables
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)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
A classified detection method of vegetable diseases based on a human psychological cognition model comprises the following steps: step 1: acquiring and processing images, acquiring vegetable sample data of a plurality of disease areas and normal areas, and respectively using the disease area sample x1、x2Drawing a circle for the circle center to find k nearest sample points; step 2: respectively calculating the proportion of the disease samples and the proportion of the normal samples in the nearest k sample points, and making a 2 x 2 list table; and step 3: recalculating sample x using the human relaxed symmetric model in conjunction with the tabulation made in step 21、x2The probability of occurrence of the disease sample in the k nearest neighbor sample points; and 4, step 4: using the result calculated in step 3 as sample xiWeights in the classifier training process; and 5: and repeating the steps to determine the weights of other disease samples and normal samples, and performing final training by using an SVM algorithm. Step 6: and carrying out disease detection on the green vegetables to be detected by using a trained SVM classification detector.
Description
Technical Field
The invention relates to a vegetable disease classification detection method based on a human psychological cognition model, which is considered as systematic error in judgment and decision shared by human beings, and an unreasonable rational mode can make the human beings quickly judge and decide. The method is suitable for the situation that sample data is difficult to monitor and acquire during the identification of the green vegetable diseases.
Background
The green vegetables serving as daily edible vegetables provide various vitamins and mineral substances required by human bodies for human beings, and promote the physical health of the human bodies to a certain extent. The green vegetable is used as a herbaceous plant and is extremely susceptible to different diseases in the growing process. Poor appearance or reduced yield of green vegetables caused by plant diseases and insect pests directly influence the income of vegetable growers who plant vegetables in large areas. In order to avoid and prevent diseases as early as possible, the existing green vegetable disease classification is mainly monitored by a manual identification mode and a camera device, the manual identification is used under the background of large-area green vegetable planting, time and labor are consumed, the fund is consumed, the manual identification can cause careless omission due to fatigue, and the camera device for identifying the diseases and insect pests is arranged in a vegetable field and is easily influenced by natural environments of rain, snow and strong wind or other insects.
In the environment we are in nature, due to cognitive limitations, motivations or adaptation to nature (or the result of natural environment to human training), humans can learn and make appropriate decisions quickly and correctly well from single or unbalanced distribution situations. Therefore, people can quickly capture key features through simple case learning or information exchange. For example, a child can directly learn the characteristics of a lion through a certain lion in a zoo or a picture book, and the lion can be directly identified next time; or the communication habit of 'if A, then B' is passed between people to obtain 'if not B, then not A' information. We generalize the similarity of the cognitive models conforming to the above into "symmetric bias" and "mutually exclusive bias". The loose symmetry model comprises two cognition models of symmetry deviation and mutual exclusion deviation, and is one of human psychological cognition models.
The classifier can be quickly and accurately learned through training of a small number of green vegetable disease data samples through a human psychological cognition model, different weights are assigned to different positive and negative samples of plant diseases and insect pests by the human psychological cognition model in the process, the existing trainer is used for learning samples with different weights to different degrees, the weights of the disease samples in classification are strengthened, the flexibility of determining classification boundaries is finally realized, and the accuracy of the classifier in the green vegetable disease classification detection problem is improved.
The existing classified detection of the vegetable diseases mainly comprises two modes of manual identification and camera device monitoring, and the fatigue of long-time manual identification personnel causes careless omission and simultaneously faces large-area planting area, and a large amount of labor cost is also needed; set up camera device monitoring and receive outdoor natural environment's interference easily, these factors have influenced the income of green vegetable planting family to a certain extent.
Disclosure of Invention
The invention aims to overcome the defects of the existing method and introduces a vegetable disease classification detection method based on a human psychological cognition model.
The method can ensure the flexibility of determining the classification decision surface under the training of the green vegetable disease data set with unbalanced disease samples and normal samples, improves the detection accuracy, provides a method for applying a human psychological cognition model to the training process of the existing algorithm, and provides a new application idea for avoiding the influence of the unbalanced green vegetable disease data samples on the classification result.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a classification detection method for recognizing vegetable diseases by a classifier based on human psychological cognition model improvement comprises the following steps:
step 1: acquiring and processing images to acquire a plurality of vegetable sample data of a diseased area and a normal area, and respectively using a diseased area sample x1、x2Drawing a circle for the circle center to find k nearest sample points;
step 2: respectively calculating the proportion of the disease sample and the normal sample in the nearest k sample points, and making a 2 x 2 list table to represent the sample x1Sample x2The probability of the disease sample and the normal sample appearing in the k nearest neighbor sample points is taken as the probability of the disease sample and the normal sample appearing in the k nearest neighbor sample points;
and step 3: combining the tabulation made in the step 2,recalculating sample x using a loose symmetric model of a person1、x2The probability of the disease sample and the normal sample appearing in the k nearest neighbor sample points is taken as the probability of the disease sample and the normal sample appearing in the k nearest neighbor sample points;
and 4, step 4: using the result calculated in step 3 as sample xiThe larger this value represents the sample x, the weight in the classifier training processiThe higher the accuracy of the decision, the farther away from the decision surface, the higher the weight occupied in the decision;
and 5: and repeating the steps to determine the weights of other disease samples and normal samples, carrying out final training by using an SVM algorithm, and carrying out training learning according to different importance degrees of different samples.
Step 6: and carrying out disease detection on the green vegetables to be detected by using a trained SVM classification detector.
The invention provides a new application idea for preventing and finding the green vegetable diseases as soon as possible by assigning different weights to different green vegetable disease samples by using a human psychological cognition model, helping a classifier to improve classification detection precision under the condition that the green vegetable disease samples are unbalanced and providing a new application idea for preventing and finding the green vegetable diseases as soon as possible.
A person can well quickly grasp key features from single or unbalanced distributed cases to learn correctly and make appropriate decisions. We therefore generalize the model containing "symmetric biases" and "mutually exclusive biases" to a loosely symmetric model, which is one of the human psychocognitive traits. The human psychological cognition model is added into the training process of the green vegetable disease classifier, different weights are given to different samples, the weight of the disease samples in classification is enhanced, the flexibility of determining classification boundaries is realized, and the classification detection precision is improved.
Compared with the prior art, the technical scheme of the invention has the advantages that:
(1) the accuracy of algorithm training can be ensured even if the unbalanced data are concentrated in training
(2) Different samples have different weights in the training process, so that the effect of the key samples in the training process is strengthened
Drawings
FIG. 1 is a flow chart of the present invention
Detailed Description
The present invention will be described in further detail with reference to examples in order to facilitate the understanding and practice of the invention by those of ordinary skill in the art.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a classification detection method for recognizing vegetable diseases by a classifier based on human psychological cognition model improvement comprises the following steps:
step 1: acquiring and processing images to acquire a plurality of vegetable sample data of a diseased area and a normal area, and respectively using a diseased area sample x1、x2Drawing a circle for the circle center to find k nearest sample points;
step 2: respectively calculating the proportion of the disease sample and the normal sample in the nearest k sample points, and making a 2 x 2 list table to represent the sample x1Sample x2The probability of the disease sample and the probability of the normal sample as the disease sample appearing in the k nearest neighbor sample points are respectively expressed by letters a, b, c and d;
and step 3: using the loose symmetry of the human (LS model) in conjunction with the tabulation made in step 2
Recalculate sample xiThe probability of the disease sample and the normal sample appearing in the k nearest neighbor sample points is taken as the probability of the disease sample and the normal sample appearing in the k nearest neighbor sample points;
and 4, step 4: using the value calculated in step 3 as a sample xiWeight in algorithm training process, the larger this value represents sample xiThe higher the accuracy of the decision, the farther away from the decision surface, the higher the weight occupied in the decision;
and 5: and repeating the steps to determine the weights of other disease samples and normal samples, carrying out final training by using an SVM algorithm, and carrying out training learning according to different importance degrees of different samples.
Step 6: and carrying out disease detection on the green vegetables to be detected by using a trained SVM classification detector.
The green vegetable diseases referred to in the present text are referred to in "semantic segmentation and localization of green vegetable disease region image based on deep learning" published in 2020 by jin Lun, Qianlai et al.
The loose symmetry model, symmetry bias, and mutual exclusion bias of the human referred to herein are described in the section "A machine learning model with human cognitive discs capable of learning from small and useful databases", 2017, by Hidetaka Taniguchi, Hiroshi Sato and Tomohiro Shirakawa et al.
The invention relates to a vegetable disease classification detection method based on a human psychological cognition model, which is considered as systematic error in judgment and decision shared by human beings, and an unreasonable rational mode can make the human beings quickly judge and decide. The method is suitable for the situation that sample data is difficult to monitor and acquire during the identification of the green vegetable diseases.
The embodiments described in this specification are merely illustrative of implementations of the inventive concept and the scope of the present invention should not be considered limited to the specific forms set forth in the embodiments but rather by the equivalents thereof as may occur to those skilled in the art upon consideration of the present inventive concept.
Claims (2)
1. A classification detection method for recognizing vegetable diseases by a classifier based on human psychological cognition model improvement comprises the following steps:
step 1: acquiring and processing images to acquire a plurality of vegetable sample data of a diseased area and a normal area, and respectively using a diseased area sample x1、x2Drawing a circle for the circle center to find k nearest sample points;
step 2: respectively calculating the proportion of the disease sample and the normal sample in the nearest k sample points, and making a 2 x 2 list table to represent the sample x1Sample x2The probability of the disease sample and the probability of the normal sample as the disease sample appearing in the k nearest neighbor sample points are respectively expressed by letters a, b, c and d;
and step 3: tabulation made in connection with step 2Using human loose symmetry (LS model)
Recalculate sample xiThe probability of the disease sample and the normal sample appearing in the k nearest neighbor sample points is taken as the probability of the disease sample and the normal sample appearing in the k nearest neighbor sample points;
and 4, step 4: using the value calculated in step 3 as a sample xiWeight in algorithm training process, the larger this value represents sample xiThe higher the accuracy of the decision, the farther away from the decision surface, the higher the weight occupied in the decision;
and 5: and repeating the steps to determine the weights of other disease samples and normal samples, carrying out final training by using an SVM algorithm, and carrying out training learning according to different importance degrees of different samples.
Step 6: and carrying out disease detection on the green vegetables to be detected by using a trained SVM classification detector.
2. The method for detecting the classified vegetable diseases based on the human mental cognitive model according to claim 1, wherein the method comprises the following steps: the psychological cognitive characteristics of people are added into the training process of the classification detection of the green vegetable diseases, the weight occupied by the disease samples during training is strengthened, and the classification detection precision of the classifier in the unbalanced training set is improved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110405593.XA CN113283470B (en) | 2021-04-15 | 2021-04-15 | Vegetable disease classification detection method based on human psychological cognitive model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110405593.XA CN113283470B (en) | 2021-04-15 | 2021-04-15 | Vegetable disease classification detection method based on human psychological cognitive model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113283470A true CN113283470A (en) | 2021-08-20 |
| CN113283470B CN113283470B (en) | 2024-02-20 |
Family
ID=77276816
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110405593.XA Active CN113283470B (en) | 2021-04-15 | 2021-04-15 | Vegetable disease classification detection method based on human psychological cognitive model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113283470B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111738138A (en) * | 2020-06-19 | 2020-10-02 | 安徽大学 | Wheat stripe embroidery disease severity remote sensing monitoring method coupled with meteorological characteristic regional scale |
| CN112464983A (en) * | 2020-10-28 | 2021-03-09 | 吉林大学 | Small sample learning method for apple tree leaf disease image classification |
-
2021
- 2021-04-15 CN CN202110405593.XA patent/CN113283470B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111738138A (en) * | 2020-06-19 | 2020-10-02 | 安徽大学 | Wheat stripe embroidery disease severity remote sensing monitoring method coupled with meteorological characteristic regional scale |
| CN112464983A (en) * | 2020-10-28 | 2021-03-09 | 吉林大学 | Small sample learning method for apple tree leaf disease image classification |
Non-Patent Citations (1)
| Title |
|---|
| HIDETAKA TANIGUCHI等: "A machine learning model with human cognitive biases capable of learning from small and biased datasets", SCIENTIFIC REPORTS, pages 1 - 13 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113283470B (en) | 2024-02-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113069080B (en) | Difficult airway assessment method and device based on artificial intelligence | |
| CN104992142B (en) | A kind of pedestrian recognition method being combined based on deep learning and attribute study | |
| CN108830144B (en) | Lactating sow posture identification method based on improved Faster-R-CNN | |
| Yun et al. | PNN based crop disease recognition with leaf image features and meteorological data | |
| CN108734208B (en) | Multi-source heterogeneous data fusion system based on multi-mode deep migration learning mechanism | |
| Macedo-Cruz et al. | Digital image sensor-based assessment of the status of oat (Avena sativa L.) crops after frost damage | |
| Petrellis | Plant disease diagnosis for smart phone applications with extensible set of diseases | |
| CN109101938B (en) | Multi-label age estimation method based on convolutional neural network | |
| Ahmed et al. | Plant disease detection using machine learning approaches | |
| CN108197643B (en) | Transfer learning method based on unsupervised clustering and metric learning | |
| CN105426875A (en) | Face identification method and attendance system based on deep convolution neural network | |
| CN110135242B (en) | Emotion recognition device and method based on low-resolution infrared thermal imaging depth perception | |
| CN106250829A (en) | Digit recognition method based on lip texture structure | |
| CN111488850B (en) | Neural network-based old people falling detection method | |
| CN110688980A (en) | Human body posture classification method based on computer vision | |
| CN113139481A (en) | Classroom people counting method based on yolov3 | |
| Alfatni et al. | Towards a real-time oil palm fruit maturity system using supervised classifiers based on feature analysis | |
| Prasomphan | Rice Bacterial Infection Detection Using Ensemble Technique on Unmanned Aerial Vehicles Images. | |
| CN113869415A (en) | Problem behavior detection and early warning system | |
| Zolfagharnassab et al. | Classification of oil palm fresh fruit bunches based on their maturity using thermal imaging technique | |
| Ibrahim et al. | Palm leaf nutrient deficiency detection using convolutional neural network (CNN) | |
| CN113283470A (en) | Green vegetable disease classification detection method based on human psychological cognition model | |
| CN113989536A (en) | Tomato disease identification method based on cuckoo search algorithm | |
| CN111739636A (en) | PPAT-based psychological intelligent analysis system | |
| CN115965143A (en) | University student score prediction method based on physiological information feature fusion |
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 |