Apple defect detection method and system based on convolutional neural network

A technology of convolutional neural network and defect detection, which is applied in the field of apple defect detection method and system based on convolutional neural network, can solve the problems of defect part segmentation and identification interference, low detection efficiency and accuracy, etc., to improve efficiency, Effects of improving accuracy and reducing costs

Pending Publication Date: 2020-11-27
UNIV OF JINAN +1
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The inventors of the present disclosure found that due to the influence of the fruit stem and calyx of the apple, there is a great interference in the segmentation and recognition of the defective part, and the traditional machine learning method cannot achieve a good recognition effect; and the traditional machine learning method The learning method must segment the defect area, manually extract the features and then hand it over to the classifier for detection, the detection efficiency and accuracy are low

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
  • Apple defect detection method and system based on convolutional neural network
  • Apple defect detection method and system based on convolutional neural network
  • Apple defect detection method and system based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] Such as figure 1 As shown, Embodiment 1 of the present disclosure provides a method for detecting apple defects based on a convolutional neural network, comprising the following steps:

[0037] Get the image data of Apple;

[0038] Preprocessing the acquired image data;

[0039] Input the preprocessed image data into the preset convolutional neural network model to obtain the apple defect detection result;

[0040] Among them, the preprocessing of the acquired image data includes: removing the apple background by using the maximum inter-class variance method, and adjusting the image resolution to preset pixels.

[0041] In detail, include the following:

[0042] S1: image acquisition;

[0043] S2: image preprocessing;

[0044] S3: data set expansion;

[0045] S4: Construct a convolutional neural network model;

[0046] S5: Model training test.

[0047] In S1, in the collection of image training data, a white background is used, and apples are placed on white pap...

Embodiment 2

[0094] Embodiment 2 of the present disclosure provides an apple defect detection system based on a convolutional neural network, including:

[0095] The data acquisition module is configured to: acquire image data of apples;

[0096] The preprocessing module is configured to: preprocess the acquired image data;

[0097] The defect detection module is configured to: input the preprocessed image data into a preset convolutional neural network model to obtain an apple defect detection result;

[0098] Among them, the preprocessing of the acquired image data includes: removing the apple background by using the maximum inter-class variance method, and adjusting the image resolution to preset pixels.

[0099] The working method of the system is the same as the convolutional neural network-based apple defect detection method provided in Embodiment 1, and will not be repeated here.

Embodiment 3

[0101] Embodiment 3 of the present disclosure provides a medium on which a program is stored, and when the program is executed by a processor, the steps in the apple defect detection method based on a convolutional neural network as described in the first aspect of the present disclosure are implemented. The steps are:

[0102] Get the image data of Apple;

[0103] Preprocessing the acquired image data;

[0104] Input the preprocessed image data into the preset convolutional neural network model to obtain the apple defect detection result;

[0105] Among them, the preprocessing of the acquired image data includes: removing the apple background by using the maximum inter-class variance method, and adjusting the image resolution to preset pixels.

[0106] The detailed steps are the same as the convolutional neural network-based apple defect detection method provided in Embodiment 1, and will not be repeated here.

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 provides an apple defect detection method and system based on a convolutional neural network, and belongs to the technical field of fruit defect detection, and the method comprises the following steps: obtaining image data of an apple; preprocessing the acquired image data; and inputting the preprocessed image data into a preset convolutional neural network model to obtain an apple defect detection result, wherein the preprocessing of the acquired image data comprises the following steps: removing an apple background by adopting a maximum between-cluster variance method, and adjusting the image resolution to be a preset pixel. The influence of pedicels and calyxes on defect detection accuracy is reduced, and efficient and accurate defect identification of apples can be realized.

Description

technical field [0001] The present disclosure relates to the technical field of fruit defect detection, in particular to a convolutional neural network-based apple defect detection method and system. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art. [0003] During the growth of apples, various factors often cause defects on the surface of apples, which affect the appearance of apples, and even make them lose their edibility, which greatly affects the quality and sales of apples. It can be seen that the detection of surface defects on fresh apples is particularly important. Traditional detection methods are mostly manual, time-consuming, labor-intensive, and inefficient, and cannot meet the needs of mass production. Therefore, researchers began to seek to develop a fast, non-destructive and efficient apple surface defect detection method to achie...

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): G06T7/00G06T7/136G06T7/194G06T7/90G06N3/08G06N3/06G06N3/04
CPCG06T7/0002G06T7/194G06T7/90G06T7/136G06N3/08G06N3/061G06N3/045
Inventor 申涛赵钦君许铮张玉华张长峰毕淑慧马荔瑶
Owner UNIV OF JINAN
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