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

A Navel Orange Image Segmentation Method Based on Reverse Harmony Search

A technology for image segmentation and navel orange, which is applied in image analysis, image enhancement, image data processing, etc., to achieve the effect of improving segmentation accuracy

Active Publication Date: 2020-06-05
JIANGXI UNIV OF SCI & TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It overcomes to a large extent the disadvantage that traditional harmony search is easily trapped in local optimum when it is applied to optimize the cluster center of navel orange image segmentation, and the invention can improve the segmentation accuracy of navel orange image

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
  • A Navel Orange Image Segmentation Method Based on Reverse Harmony Search
  • A Navel Orange Image Segmentation Method Based on Reverse Harmony Search
  • A Navel Orange Image Segmentation Method Based on Reverse Harmony Search

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0047] Step 1, input a picture such as figure 1 Shown navel orange image IM, image IM is converted to the image IMN of YCrCb color space then, and extracts the Cb color component value of each pixel in the image IMN as navel orange image segmentation data;

[0048] Step 2, the user initializes the parameters, sets the number of navel orange image segmentation categories D=2, the size of the harmony library HMS=20, the selection probability of the harmony library HMCR=0.95, the disturbance probability PAR=0.6, and the maximum number of evaluations MAX_FEs=80;

[0049] Step 3, let the current evolution algebra t=0, and let the current evaluation times FEs=0;

[0050] Step 4, randomly generate the initial harmony library Where: individual subscript i=1,2,...,HMS, and for Harmony Bank HM tThe i-th individual in ; individual The cluster centers of D segmentation categories are stored, where for individual The jth cluster center in , its random initialization formula is: ...

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 navel orange image segmentation method based on reverse harmony search. The invention adopts the reverse harmony search to optimize the cluster center of navel orange image segmentation. In the reverse harmony search, the search operation based on the reverse learning strategy is first performed to generate new individuals, and then the generated new individuals compete with the worst individual in the harmony library, and the search process is repeated until the termination condition is met. Finally, the obtained optimal individual is decoded as the cluster center of navel orange image segmentation, and then the navel orange image segmentation can be realized. The invention can improve the segmentation accuracy of the navel orange image.

Description

technical field [0001] The invention relates to the field of image segmentation, in particular to a navel orange image segmentation method based on reverse harmony search. Background technique [0002] Navel orange is a very delicious fruit, and it is rich in nutrients, containing a variety of nutrients needed by the human body. However, the cultivation of navel oranges is a very labor-intensive industry. In order to realize the large-scale and industrialization of navel orange planting, it is necessary to integrate automation and intelligent technology into all aspects of navel orange planting. Machine vision technology is an important technology for intelligently growing navel oranges. Navel orange image segmentation method is the basis of navel orange machine vision technology. The image segmentation method of navel orange plays a very important role in the automatic and intelligent production process of navel orange. For example, automatic detection of navel orange di...

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): G06T7/11G06K9/62
CPCG06T7/11G06T2207/10024G06T2207/30188G06F18/2321
Inventor 郭肇禄章银娥王洋尹宝勇杨火根鄢化彪余法红
Owner JIANGXI UNIV OF SCI & TECH