Unlock instant, AI-driven research and patent intelligence for your innovation.

Adaboost and NCC combined complete wheat ear identification method and system

A recognition method and combined technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of recognition result set inclusion, calculation of grain number of wheat ears, etc., to ensure pertinence, accuracy and function The effect of homogenization

Inactive Publication Date: 2017-11-24
HEFEI INSTITUTES OF PHYSICAL SCIENCE - CHINESE ACAD OF SCI
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods have the problem that the recognition result set contains a large number of incomplete ear targets, and these ear targets cannot be used to calculate the number of ear grains

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
  • Adaboost and NCC combined complete wheat ear identification method and system
  • Adaboost and NCC combined complete wheat ear identification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] refer to figure 2 , A complete wheat ear recognition system combining Adaboost and NCC provided in this embodiment includes: an image input module, a candidate target recognition module, a completeness judgment module and a complete wheat ear output module.

[0034] The image input module is used to obtain the wheat image to be identified. In this embodiment, the image input module includes an image acquisition unit and an image preprocessing unit, the image acquisition unit is used to load the wheat image to be processed, and the image preprocessing unit is used to preprocess the loaded wheat image, so as to improve the follow-up processing efficiency . Candidate object recognition module includes LBP feature extraction unit, classifier training unit and ear detection unit. The LBP feature extraction unit is connected to the image preprocessing unit to obtain the preprocessed wheat image as the feature extraction object. The LBP feature extraction unit is used to i...

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 an Adaboost and NCC combined complete wheat ear identification method. The method comprises the following steps of: S1, setting a complete wheat ear template and setting a similar threshold value; S2, obtaining a wheat ear sample and extracting textural features of the wheat ear sample through rotation&uniform invariant LBP; S3, using an Adaboost training classifier for the textural features of the wheat ear sample; S4, carrying out wheat ear identification on an obtained wheat image through the classifier and extracting candidate targets of a complete wheat ear; and S5, carrying out NCC similarity analysis on the candidate targets and the complete wheat ear template one by one, extracting a complete wheat ear target from the candidate targets according to the comparison result of a similarity and the similarity threshold value and outputting the complete wheat ear target. Through the method, the complete wheat ear target can be obtained, so that the aim of calculating characteristic parameters such as wheat grain number and the like by using the wheat ear target is achieved.

Description

technical field [0001] The invention relates to the technical field of intelligent agriculture, in particular to a method and system for identifying complete ears of wheat combining Adaboost and NCC. Background technique [0002] With the development of agricultural intelligence, there is a demand for a method to identify visually complete ears of wheat (non-occluded, incomplete collection) in the actual wheat field image, so that the subsequent calculation of the number of ears of wheat through the target image of wheat ears has emerged. Common existing technologies are: Adaboost-based wheat ear recognition method (2014, Zhao Feng et al. Research on wheat ear recognition based on color features and Adaboost algorithm), wheat ear recognition method based on neural network (2012, Lu Xingjun. Research on wheat ear recognition based on image processing technology), etc. However, these methods have the problem that the recognition result set contains a large number of incomplet...

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): G06K9/62
CPCG06F18/2414G06F18/214
Inventor 孔斌王宁徐海明杨静李伟王儒敬王灿
Owner HEFEI INSTITUTES OF PHYSICAL SCIENCE - CHINESE ACAD OF SCI