Dragoneye insect identification method based on regional suggestion network

An identification method and technology for insects, applied in the field of identification, can solve the problems of complex background and identification difficulties in pictures of Odonata insects, and achieve the effect of enhancing the ability to extract effective features and solving identification difficulties.

Active Publication Date: 2021-07-27
CHONGQING NORMAL UNIVERSITY
View PDF16 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the purpose of the present invention is to overcome the defects in the prior art and provide a method for identifying Odonata insects based on the region suggestion network, which can mak

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
  • Dragoneye insect identification method based on regional suggestion network
  • Dragoneye insect identification method based on regional suggestion network
  • Dragoneye insect identification method based on regional suggestion network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] Below in conjunction with accompanying drawing, the present invention is further described, as figure 1 Shown:

[0036] The Odonata insect identification method based on the region suggestion network of the present invention comprises the following steps:

[0037] S1. Collect images of Odonata insects, and clean and organize the images of Odonata insects to obtain a data set of Odonata insect images; among them, the acquisition methods of Odonata insect image data include field shooting, laboratory shooting and network downloading, etc. Therefore, the finally obtained data set of Odonata images does not have the characteristics of an equal number of Odonata images under given conditions, and the overall data is distributed in a long tail.

[0038] S2. The data set of Odonata insect images is enhanced to obtain the enhanced data set;

[0039] S3. Dividing the enhanced data set according to a set ratio to obtain a training set, a verification set, and a test set of imag...

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

No PUM Login to view more

Abstract

The invention discloses a dragoneye insect identification method based on regional suggestion network, which comprises the following steps of: S1, cleaning and sorting dragonproof insect images to obtain a data set of the dragonproof insect images; S2, performing enhancement processing on the data set of the dragoneye insect image to obtain an enhanced data set; S3, dividing the enhanced data set to obtain a training set, a verification set and a test set of dragoneye insect images; S4, constructing a deep convolutional network model based on the regional suggestion network; S5, training a deep convolutional network model by using the training set and the verification set to obtain a trained network model; and S6, inputting the test set into the trained network model, and outputting and obtaining a classification result of the test set. According to the method, the identification processing is simple and fast, a large amount of labor cost is saved, and the problem of difficult identification caused by complex background of dragoneye insect pictures in a natural environment is solved.

Description

technical field [0001] The invention relates to the field of recognition, in particular to a method for recognizing Odonata insects based on a region suggestion network. Background technique [0002] The existing automatic recognition algorithm of Odonata uses the manually designed features as the classification basis, and uses the traditional recognition method to build the recognition framework, which can only recognize the specimen pictures of several kinds of dragonflies, and the recognition rate is low. Dragonfly pictures do not have the ability to identify; [0003] Existing insect automatic recognition algorithms are often divided into two steps to achieve. The first step is detection. That is, the implementation of the detection algorithm for the target to be identified is implemented first. This process relies on a large amount of manual labeling information, which is time-consuming and labor-intensive, resulting in a high initial cost. The second step is identif...

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
no application Login to view more
IPC IPC(8): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/00G06V10/40G06N3/045G06F18/24G06F18/214
Inventor 皮家甜于昕彭明杰吴志友
Owner CHONGQING NORMAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap