Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Bamboo variety recognition method based on artificial intelligence deep learning

A deep learning and artificial intelligence technology, applied in character and pattern recognition, instruments, biological neural network models, etc., to avoid sampling errors and improve accuracy

Active Publication Date: 2019-06-07
INT CENT FOR BAMBOO & RATTAN +1
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In recent years, artificial intelligence has developed rapidly. SENet, the champion model of the 2017 ILSVRC image classification competition, has reduced the error rate of TOP5 to 2.251% on the ImageNet test set, which has greatly improved, but no one has applied this model to bamboo species. Classification

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
  • Bamboo variety recognition method based on artificial intelligence deep learning
  • Bamboo variety recognition method based on artificial intelligence deep learning
  • Bamboo variety recognition method based on artificial intelligence deep learning

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0093]Take the complete bamboo ring at the internode part of the high breast of the bamboo, use the method provided by the embodiment of the present invention to train the SENet model after polishing and scanning, and then use the trained SENet model to process the bamboo pictures to be classified. The model training takes 24 hours, and the recognition time for each picture is about 1 second. The results show that the method provided by the embodiment of the present invention can accurately identify the bamboo species for the bamboo pictures to be classified. The probability distribution of bamboo species obtained by using the SENeT model is as follows:

[0094] Diaoluo Ni bamboo: Diaoluo Ni bamboo 99.96%, Ci bamboo 0.02%, Pao bamboo 0.01%, Datou Dian bamboo 0.01%, Moso bamboo 0.01%, Ma bamboo 0.0%, Thai bamboo 0.0%, Apas bamboo 0.0%, sand Luodan bamboo 0.0%, pear bamboo 0.0%;

[0095] Datoudian bamboo: Datoudian bamboo 100.0%, Saluo single bamboo 0.0%, Moso bamboo 0.0%, Apas...

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 embodiment of the invention provides a bamboo variety recognition method based on artificial intelligence deep learning. The method comprises: obtaining cross section pictures of to-be-classifiedbamboos; marking the maximum cross section area of the bamboo in the cross section picture by using a rectangular frame; sampling the picture in the rectangular frame for multiple times by adopting asliding window to obtain a plurality of sample images; inputting each sample image into a pre-trained model to obtain the probability distribution of the type of the bamboo corresponding to each sample image, and repeating the step until the probability distribution of the variety of the bamboo corresponding to all the sample images is obtained; calculating the average value of the probability distributions of the bamboo varieties corresponding to all the sample images to obtain the final probability distributions of the bamboo varieties; and according to the bamboo variety corresponding to the maximum probability value in the final probability distribution, identifying the types of the to-be-classified bamboos. According to the method, the trained algorithm model is adopted, and through multi-position sampling and independent judgment, the bamboo variety recognition precision is further improved.

Description

technical field [0001] The embodiment of the present invention relates to the technical field of plant classification, in particular to a bamboo species identification method based on artificial intelligence deep learning. Background technique [0002] At present, the methods for classifying plants such as bamboo mainly include classical morphological classification, anatomical feature classification, molecular biotechnology classification and computer-aided identification classification. [0003] Classical morphological classification is based on the morphological and structural characteristics of plant reproductive organs, such as flowers, fruits, seeds, and plant vegetative organs, such as roots, stems, and leaves. "Flora of China", Volume 9, Volume 1 "Angiosperms - Dicotyledonous Plants - Gramineae - Poaceae - Bambooideae" compiled by Geng Bojie and others in 1996, recorded in detail the original and a few introduced species in my country. Bamboo, a total of more than 50...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/02
Inventor 王汉坤易武坤黎静田根林岳祥华余雁石俊利
Owner INT CENT FOR BAMBOO & RATTAN
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com