CN103177266A - Intelligent stock pest identification system - Google Patents
Intelligent stock pest identification system Download PDFInfo
- Publication number
- CN103177266A CN103177266A CN2013101172782A CN201310117278A CN103177266A CN 103177266 A CN103177266 A CN 103177266A CN 2013101172782 A CN2013101172782 A CN 2013101172782A CN 201310117278 A CN201310117278 A CN 201310117278A CN 103177266 A CN103177266 A CN 103177266A
- Authority
- CN
- China
- Prior art keywords
- insect
- image
- storing
- module
- stored product
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 241000607479 Yersinia pestis Species 0.000 title abstract description 13
- 238000000605 extraction Methods 0.000 claims abstract description 14
- 241000238631 Hexapoda Species 0.000 claims description 76
- 238000000034 method Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 8
- 230000000877 morphologic effect Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 238000012706 support-vector machine Methods 0.000 claims description 7
- 210000001015 abdomen Anatomy 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000007621 cluster analysis Methods 0.000 claims description 3
- 238000003708 edge detection Methods 0.000 claims description 3
- 230000002068 genetic effect Effects 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 claims description 3
- 238000005452 bending Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 claims description 2
- 230000008676 import Effects 0.000 claims description 2
- 230000009467 reduction Effects 0.000 claims description 2
- 239000000284 extract Substances 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000011161 development Methods 0.000 abstract description 2
- 238000007689 inspection Methods 0.000 abstract description 2
- 238000007781 pre-processing Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000007786 learning performance Effects 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses an intelligent stock pest identification system which comprises a universal stereoscopic microscopic camera shooting system, a central processor, a stock pest image preprocessing module, a stock pest image characteristic extraction module and a stock pest image identification and classification module. The system has the beneficial effects that several novel characteristic parameters, namely four proportional relations, are provided on the basis of original shape characteristic parameters, lots of pests can be identified and classified due to the increase of the characteristic parameters, and the determination on similar types is added on the basis of identification and classification, so that the pests can be found from similar types when being wrongly identified, the accuracy of pest identification is further improved, the development of machine vision is promoted, and the working efficiency of related work units, such as quarantine and inspection bureau and customs, is improved.
Description
Technical field
The present invention relates to agricultural pests kind recognition technology field, particularly relate to a kind of stored product insect intelligent identifying system.
Background technology
Traditional Tibetan storing insect identification, generally by detecting the expert, according to knowledge and experience, be characterized as foundation with the Main Morphology of hiding the storing insect, formulate it about section, genus and key to species, the testing staff,, progressively screens and classifies with known experience by the artificial visual interpretation by microscope, body times magnifier.The method is time-consuming, effort not only, and needs the researcher to have abundant Tibetan storing insect professional knowledge and classification experience.Therefore the present invention is based on image and process and mode identification technology, automatically detect hiding storing insect image, can reach the automatic classification that common Tibetan storing insect is carried out evaluation automatically and its kind.The patent No.: 201210406153, patented claim day: 2012.10.23, open (bulletin) day: 2013.02.13, the color-based of invention and the identification of the agricultural pests of model and method of counting.Described insect recognition system can be completed identification and the counting of 8 kinds of common insects.Deficiency is pest species identification Limited Number, and can not completes the differentiation of similar kind.According to above requirement, need a kind of new insect automatic recognition classification system that a large amount of various pests are identified, and can find out its similar kind.
Summary of the invention
The objective of the invention is to overcome current insect recognition system and provide a kind of stored product insect intelligent identifying system identifying the deficiency on kind number and recognition correct rate.
The technical solution adopted in the present invention is: the stored product insect intelligent identifying system, system comprises omnipotent stereoscopic microscope camera system, and central processing unit is hidden storing insect image pretreatment module, hide storing insect image characteristics extraction module, hide storing insect image recognition sort module;
Described omnipotent stereoscopic microscope camera system is responsible for the collection of image, and the image after collection imports central processing unit into, and processes;
Described Tibetan storing insect image pretreatment module is carried out figure image intensifying, image segmentation, edge detection process to the insect image that collects;
Described Tibetan storing insect image characteristics extraction module provides the calculating of the various morphological feature parameters of hiding the storing insect and the dimensionality reduction of characteristic parameter;
Described Tibetan storing insect discriminator module provides BP neural network, support vector machine (SVM) classification and identification algorithm.
Further, the model of described omnipotent stereoscopic microscope camera system is M205A.
Further, described central processing unit model is Duo 2 double-core T5450.
Further, described Tibetan storing insect image pretreatment module is to utilize matlab and vc++ to programme the insect image is carried out denoising, cuts apart rim detection.
Further, the insect morphological feature that described Tibetan storing insect image characteristics extraction module is extracted comprises area, girth, complexity, elongation, rectangular degree, equivalent circular area radius, the Area Ratio of insect feeler and trunk, the girth ratio of insect feeler and trunk, insect cephalothorax area and belly Area Ratio, insect cephalothorax girth and belly girth than and 7 HU bending moment not.
Further, the insect morphological feature that described Tibetan storing insect image characteristics extraction module is extracted is selected and analyzes, and adopts genetic algorithm, PCA algorithm, cluster analysis.
Further, hide storing insect discriminator module insect is carried out discriminator.
Further, according to the kind of the feature judgement insect of hiding the extraction of storing insect image characteristics extraction module, and the similar kind that can mate this insect.
compared with prior art, the invention has the beneficial effects as follows: proposed the i.e. 4 kinds of proportionate relationships of several New Characteristics parameters on the basis of parameters for shape characteristic in the past, the increase of characteristic parameter can be carried out discriminator to a large amount of insects, and increased the differentiation of similar kind on the basis of discriminator, still can find insect from similar kind like this when the identification pest species is wrong, further improved the accuracy rate of insect identification, for contribution has been made in the development of machine vision, also improved work efficiency for related work unit such as inspection and quarantine bureau and customs etc.
Description of drawings
In order to be illustrated more clearly in technical scheme of the present invention, during the below will describe embodiment, the accompanying drawing of required use is done to introduce simply, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skills, under the prerequisite of not paying creative work, can also obtain according to these accompanying drawings other accompanying drawing.
Fig. 1 is process flow diagram of the present invention;
Embodiment
In order more clearly to understand technical scheme of the present invention, the present invention is further described below in conjunction with accompanying drawing.
Native system is the stored product insect intelligent identifying system, comprise omnipotent stereoscopic microscope camera system, image processing software, central processing unit is hidden storing insect image pretreatment module, hides storing insect image characteristics extraction module, hide storing insect image recognition sort module, the model of described omnipotent stereoscopic microscope camera system is M205A, and described central processing unit model is Duo 2 double-core T5450, below in conjunction with accompanying drawing, the present invention is elaborated.
Accompanying drawing one is the native system process flow diagram.At first native system utilizes the methods such as morphology, comprehensive operator to carry out the pre-service of individual images, carries out the figure image intensifying, image segmentation, edge detection process; The genetic stability feature of sign insect is a kind of is to utilize its morphological feature, another kind of HUShi invariant moment features; Through after above-mentioned feature extraction, obtain effectively to describe one group of high dimensional data that the characteristic set of individual various morphosis forms, and the kind of hiding the storing insect is a large amount of, so such target identification will be the classification and identification of a higher-dimension, mass data.The methods such as employing principal component analysis are carried out initial analysis to similar form kind individuality, as comparison and the reference of follow-up method; Cluster analysis, by to the responsive subspace analysis of sample characteristics, to cluster later stage sample point of " unsteadiness " between different classes of--namely be difficult to determine the sample point of category attribute, analyze with the K-neighbour method selection classification interface that combines with Support Vector Machine, optimize the selection of classification boundary surface, the clustering algorithm of further investigated responsive subspace theory and higher-dimension, mass data; Classification and Identification based on BP neural network and SVM: the good automatic classification that has based on the BP neural network and again learning performance improve the learning ability of recognizer; SVM can realize the input space is transformed in higher dimensional space, obtains the lineoid of optimal classification in this higher dimensional space.
The above is only better embodiment of the present invention, therefore all equivalences of doing according to the described structure of patent claim of the present invention, feature and principle change or modify, is included in patent claim of the present invention.
Claims (8)
1. stored product insect intelligent identifying system, it is characterized in that: system comprises omnipotent stereoscopic microscope camera system, central processing unit is hidden storing insect image pretreatment module, hides storing insect image characteristics extraction module, hides storing insect image recognition sort module;
Described omnipotent stereoscopic microscope camera system is responsible for the collection of image, and the image after collection imports central processing unit into, and processes;
Described Tibetan storing insect image pretreatment module is carried out figure image intensifying, image segmentation, edge detection process to the insect image that collects;
Described Tibetan storing insect image characteristics extraction module provides the calculating of the various morphological feature parameters of hiding the storing insect and the dimensionality reduction of characteristic parameter;
Described Tibetan storing insect discriminator module provides BP neural network, support vector machine (SVM) classification and identification algorithm.
2. stored product insect intelligent identifying system according to claim 1, it is characterized in that: the model of described omnipotent stereoscopic microscope camera system is M205A.
3. stored product insect intelligent identifying system according to claim 1, it is characterized in that: described central processing unit model is Duo 2 double-core T5450.
4. stored product insect intelligent identifying system according to claim 1, it is characterized in that: described Tibetan storing insect image pretreatment module is to utilize matlab and vc++ to programme the insect image is carried out denoising, cuts apart rim detection.
5. stored product insect intelligent identifying system according to claim 1, it is characterized in that: the insect morphological feature that described Tibetan storing insect image characteristics extraction module is extracted comprises area, girth, complexity, elongation, rectangular degree, equivalent circular area radius, the Area Ratio of insect feeler and trunk, the girth ratio of insect feeler and trunk, insect cephalothorax area and belly Area Ratio, insect cephalothorax girth and belly girth than and 7 HU bending moment not.
6. stored product insect intelligent identifying system according to claim 5 is characterized in that: the insect morphological feature that described Tibetan storing insect image characteristics extraction module is extracted is selected and analyzes, and adopts genetic algorithm, PCA algorithm, cluster analysis.
7. stored product insect intelligent identifying system according to claim 1, is characterized in that: hide storing insect discriminator module insect is carried out discriminator.
8. stored product insect intelligent identifying system according to claim 7 is characterized in that: according to the kind of hiding the feature judgement insect that storing insect image characteristics extraction module extracts, and the similar kind that can mate this insect.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2013101172782A CN103177266A (en) | 2013-04-07 | 2013-04-07 | Intelligent stock pest identification system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2013101172782A CN103177266A (en) | 2013-04-07 | 2013-04-07 | Intelligent stock pest identification system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103177266A true CN103177266A (en) | 2013-06-26 |
Family
ID=48637107
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2013101172782A Pending CN103177266A (en) | 2013-04-07 | 2013-04-07 | Intelligent stock pest identification system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103177266A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104573699A (en) * | 2015-01-21 | 2015-04-29 | 中国计量学院 | Trypetid identification method based on medium field intensity magnetic resonance dissection imaging |
CN104573745A (en) * | 2015-01-21 | 2015-04-29 | 中国计量学院 | Fruit fly classification method based on magnetic resonance imaging |
CN104573746A (en) * | 2015-01-21 | 2015-04-29 | 中国计量学院 | Fruit fly type identification method based on magnetic resonance imaging |
CN104573734A (en) * | 2015-01-06 | 2015-04-29 | 江西农业大学 | Rice pest intelligent recognition and classification system |
CN105894131A (en) * | 2016-04-28 | 2016-08-24 | 广东石油化工学院 | Fruit-piercing moth rapid early-warning method |
CN109102004A (en) * | 2018-07-23 | 2018-12-28 | 鲁东大学 | Cotton-plant pest-insects method for identifying and classifying and device |
CN110363103A (en) * | 2019-06-24 | 2019-10-22 | 仲恺农业工程学院 | Identifying pest method, apparatus, computer equipment and storage medium |
CN110490861A (en) * | 2019-08-22 | 2019-11-22 | 石河子大学 | A kind of recognition methods and system of the aphid on yellow plate |
CN112668490A (en) * | 2020-12-30 | 2021-04-16 | 浙江托普云农科技股份有限公司 | Yolov 4-based pest detection method, system, device and readable storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030026484A1 (en) * | 2001-04-27 | 2003-02-06 | O'neill Mark | Automated image identification system |
CN101701906A (en) * | 2009-11-13 | 2010-05-05 | 江苏大学 | Method and device for detecting stored-grain insects based on near infrared super-spectral imaging technology |
CN101701915A (en) * | 2009-11-13 | 2010-05-05 | 江苏大学 | Device and method for detecting stored-grain insects based on visible light-near infrared binocular machine vision |
CN101976350A (en) * | 2010-10-20 | 2011-02-16 | 中国农业大学 | Grain storage pest detection and identification method based on video analytics and system thereof |
CN102084794A (en) * | 2010-10-22 | 2011-06-08 | 华南农业大学 | Method and device for early detecting crop pests based on multisensor information fusion |
-
2013
- 2013-04-07 CN CN2013101172782A patent/CN103177266A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030026484A1 (en) * | 2001-04-27 | 2003-02-06 | O'neill Mark | Automated image identification system |
CN101701906A (en) * | 2009-11-13 | 2010-05-05 | 江苏大学 | Method and device for detecting stored-grain insects based on near infrared super-spectral imaging technology |
CN101701915A (en) * | 2009-11-13 | 2010-05-05 | 江苏大学 | Device and method for detecting stored-grain insects based on visible light-near infrared binocular machine vision |
CN101976350A (en) * | 2010-10-20 | 2011-02-16 | 中国农业大学 | Grain storage pest detection and identification method based on video analytics and system thereof |
CN102084794A (en) * | 2010-10-22 | 2011-06-08 | 华南农业大学 | Method and device for early detecting crop pests based on multisensor information fusion |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104573734A (en) * | 2015-01-06 | 2015-04-29 | 江西农业大学 | Rice pest intelligent recognition and classification system |
CN104573746B (en) * | 2015-01-21 | 2017-10-17 | 中国计量学院 | Trypetid category identification method based on magnetic resonance imaging |
CN104573746A (en) * | 2015-01-21 | 2015-04-29 | 中国计量学院 | Fruit fly type identification method based on magnetic resonance imaging |
CN104573745A (en) * | 2015-01-21 | 2015-04-29 | 中国计量学院 | Fruit fly classification method based on magnetic resonance imaging |
CN104573745B (en) * | 2015-01-21 | 2017-10-03 | 中国计量学院 | Fruit-fly classified method based on magnetic resonance imaging |
CN104573699A (en) * | 2015-01-21 | 2015-04-29 | 中国计量学院 | Trypetid identification method based on medium field intensity magnetic resonance dissection imaging |
CN104573699B (en) * | 2015-01-21 | 2017-11-24 | 中国计量学院 | Trypetid recognition methods based on middle equifield intensity magnetic resonance anatomy imaging |
CN105894131A (en) * | 2016-04-28 | 2016-08-24 | 广东石油化工学院 | Fruit-piercing moth rapid early-warning method |
CN109102004A (en) * | 2018-07-23 | 2018-12-28 | 鲁东大学 | Cotton-plant pest-insects method for identifying and classifying and device |
CN110363103A (en) * | 2019-06-24 | 2019-10-22 | 仲恺农业工程学院 | Identifying pest method, apparatus, computer equipment and storage medium |
CN110363103B (en) * | 2019-06-24 | 2021-08-13 | 仲恺农业工程学院 | Insect pest identification method and device, computer equipment and storage medium |
CN110490861A (en) * | 2019-08-22 | 2019-11-22 | 石河子大学 | A kind of recognition methods and system of the aphid on yellow plate |
CN112668490A (en) * | 2020-12-30 | 2021-04-16 | 浙江托普云农科技股份有限公司 | Yolov 4-based pest detection method, system, device and readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Liu et al. | Detection of aphids in wheat fields using a computer vision technique | |
CN103177266A (en) | Intelligent stock pest identification system | |
CN109952614B (en) | Biological particle classification system and method | |
CN111178197B (en) | Mass R-CNN and Soft-NMS fusion based group-fed adherent pig example segmentation method | |
He et al. | Application of deep learning in integrated pest management: A real-time system for detection and diagnosis of oilseed rape pests | |
Wu et al. | Detection and counting of banana bunches by integrating deep learning and classic image-processing algorithms | |
Sarvini et al. | Performance comparison of weed detection algorithms | |
Revathi et al. | Cotton leaf spot diseases detection utilizing feature selection with skew divergence method | |
Junos et al. | An optimized YOLO‐based object detection model for crop harvesting system | |
Jambhekar | Red blood cells classification using image processing | |
CN112598713A (en) | Offshore submarine fish detection and tracking statistical method based on deep learning | |
CN103136504A (en) | Face recognition method and device | |
CN104021384B (en) | A kind of face identification method and device | |
Chen et al. | Locating crop plant centers from UAV-based RGB imagery | |
Singh et al. | A review on: Various techniques of plant leaf disease detection | |
Rustia et al. | Online semi-supervised learning applied to an automated insect pest monitoring system | |
CN112036384B (en) | Sperm head shape recognition method, device and equipment | |
CN104050460B (en) | The pedestrian detection method of multiple features fusion | |
CN106023159A (en) | Disease spot image segmentation method and system for greenhouse vegetable leaf | |
Li | Content-based microscopic image analysis | |
CN110458022A (en) | It is a kind of based on domain adapt to can autonomous learning object detection method | |
CN104573701B (en) | A kind of automatic testing method of Tassel of Corn | |
Narayan et al. | An optimal feature subset selection using GA for leaf classification | |
CN106326914B (en) | A kind of more classification methods of pearl based on SVM | |
Yang et al. | Shape-based classification of environmental microorganisms |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C12 | Rejection of a patent application after its publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130626 |