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

A tea bud detection method based on deep learning and image edge information

An image edge, deep learning technology, applied in image analysis, image enhancement, image data processing and other directions, can solve the problems of uneven tea quality, high labor intensity, low tea quality, etc., achieve uniform sample, reduce labor intensity, The effect of tea tree damage

Inactive Publication Date: 2019-03-22
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, manual tea picking has disadvantages such as high labor cost, high labor intensity, low efficiency, and uneven tea quality, while traditional mechanical tea picking is simple and extensive, and also has defects such as low tea quality and great damage to tea trees.

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] This embodiment adopts the method of recording the number of pixels in the edge of the image, which specifically includes the following steps:

[0033] Step 1: Obtain the original image with a high-resolution camera;

[0034] Step 2: Use the edge detection algorithm to detect the edge of the original image to obtain the result picture;

[0035] Step 3: Use a sliding window to divide the resulting image into multiple sub-images of the same size;

[0036] Step 4: Calculate the percentage of the number of statistical pixels and the total number of pixels of the result image;

[0037] Calculate the percentage of the number of pixels belonging to the edge of the image in the entire result picture to the total number of pixels in the image, denoted as Pall1; calculate the percentage of the number of pixels belonging to the edge of the image in each sub-image in step 3 to the total number of pixels of the result picture , denoted as Pd1;

[0038] Step five: record the numbe...

Embodiment 2

[0050] This embodiment adopts the method of recording the number of pixels outside the edge of the image, which specifically includes the following steps:

[0051] Step 1: Obtain the original image with a high-resolution camera;

[0052] Step 2: Use the edge detection algorithm to detect the edge of the original image to obtain the result picture;

[0053] Step 3: Use a sliding window to divide the resulting image into multiple sub-images of the same size;

[0054] Step 4: Calculate the percentage of the number of statistical pixels and the total number of pixels of the result image;

[0055] Calculate the percentage of the number of pixels that do not belong to the edge of the image in the entire result picture to the total number of pixels in the image, denoted as Pall2; the number of pixels that do not belong to the edge of the image in the calculation step 3 accounts for the total number of pixels in the result picture The percentage of is denoted as pd2;

[0056] Step ...

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 relates to a tea sprout method, and particularly relates to a tea sprout detection method based on depth learning and image edge information. Firstly image edges are detected by an original edge detection algorithm, and candidate windows are extracted from images after edge detection by using the following two methods: (1) the candidate windows are extracted according to the percentage of the number of the pixels belonging to the image edges in the images of the total number of the pixels of the images; and (2) the candidate windows are extracted according to the percentage of the number of the pixels which do not belong to the image edges in the images of the total number of the pixels. Then the extracted candidate windows are inputted to a trained depth learning network, and tea sprouts are judged. With application of the tea sprout detection method, the effect of the existing tea sprout detection task can be greatly improved, and the method can also be applied to other target detection tasks.

Description

technical field [0001] The invention relates to a method for tea buds, in particular to a method for detecting tea buds based on deep learning and image edge information. Background technique [0002] Tea is the national drink of the Chinese nation. It originated in Shennong, heard about Duke Zhou of Lu, flourished in Tang Dynasty, and flourished in Song Dynasty. Tea is the essence of tea, and its picking technology is an important part of tea culture. Different picking techniques produce completely different tea leaves. At present, tea picking is mainly carried out by hand and traditional machinery. Among them, manual tea picking has disadvantages such as high labor cost, high labor intensity, low efficiency, and uneven tea quality, while traditional mechanical tea picking is simple and extensive, and also has defects such as low tea quality and great damage to tea trees. [0003] In view of the defects of the above two tea-picking processes, and considering the unique ...

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 Patents(China)
IPC IPC(8): G06T7/00G06T7/12G06T7/194
CPCG06T7/0006G06T2207/30188
Inventor 吴晓民任鹏
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
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