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

Apple grading method and system based on residual network

A classification method, Apple's technology, applied in image analysis, image data processing, instruments, etc., to achieve the effect of alleviating the problem of sudden failure, easy key information, and easy extraction

Pending Publication Date: 2021-11-05
UNIV OF JINAN
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The inventors of the present disclosure found that in the application of existing deep learning in apple detection and classification, some methods have achieved relatively good results in the identification of normal apples, diseased apples, and rotten apples, and the identification of apple leaf diseases. High recognition accuracy, but there is still room for improvement in the accuracy of grading on apple fruit shape

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 grading method and system based on residual network
  • Apple grading method and system based on residual network
  • Apple grading method and system based on residual network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] Such as figure 1 As shown, the present disclosure provides a residual network-based apple grading method including:

[0056] Get the appearance image of the apple;

[0057] According to the obtained appearance image and the preset apple grading network model, the apple grading result is obtained;

[0058] Among them, the Apple hierarchical network model is obtained by training the improved ResNet-50 network; specifically, the improvement of the ResNet-50 network is realized by adding a convolutional attention module and a leaky linear rectification function.

[0059] In this embodiment, the training process of Apple's hierarchical network model is:

[0060] Obtain the appearance image of the apple to obtain the training set; each apple is measured multiple times, and the appearance image of the apple is obtained from multiple sides and different positions on the top surface;

[0061] Data augmentation of appearance images in the training set, including vertical mirro...

Embodiment 2

[0103] In order to verify the effect of this scheme, in this embodiment, the apple grading method based on the residual network proposed in the embodiment 1 is experimentally verified, specifically:

[0104] The red Fuji apple data used in the present embodiment comprises 6759 effective pictures; After the selection of grading standards, a total of 781 special-class, 1,241 first-class, and 1,032 second-class were sorted out.

[0105] Table 1 Grading standard of Red Fuji apple

[0106]

[0107] The above data is randomly divided into training set and verification set according to the ratio of 8:2. The apple grading dataset is shown in Table 2.

[0108] Table 2 Apple Grading Dataset

[0109]

[0110] The experiment was carried out under the Ubuntu 18.04 system, and two 2080Ti graphics card GPUs were used to accelerate the training of the model.

[0111] In order to verify the effectiveness and applicability of the improved ResNet-50 network in the Apple grading system,...

Embodiment 3

[0119] The present embodiment provides a kind of apple grading system based on residual network, including image acquisition module and grading module;

[0120] The image acquisition module is configured to: acquire an appearance image of an apple;

[0121] The grading module is configured to: obtain an apple grading result according to the acquired appearance image and the preset apple grading network model;

[0122] Among them, the Apple hierarchical network model is obtained by training the improved ResNet-50 network; specifically, the improvement of the ResNet-50 network is realized by adding a convolutional attention module and a leaky rectification function.

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 grading method and system based on a residual network. The apple grading method comprises the following steps of: acquiring an appearance image of an apple; and obtaining a grading result of the apple according to the obtained appearance image and a preset apple grading network model. The Apple grading network model is obtained by training an improved residual network; and specifically, the residual network is improved by adding a convolutional attention module and a leaky rectified linear unit. Apple grading based on appearance is realized through the improved residual network. An Otsu method is used to segment an apple image on an HSI color channel, a convolutional attention module and a Leaky ReLU activation function (a leaky rectified linear unit) are added to improve a residual network, the residual network is applied to apple grading, the grading result is compared with grading results of other convolutional neural networks, and it is proved that the improved residual network can better achieve apple grading.

Description

technical field [0001] The disclosure belongs to the technical field of machine vision, and in particular relates to a residual network-based apple grading method and system. Background technique [0002] Apple grading is an important part of the apple industry; during the growth, picking and transportation of apples, more or less rot, diseases and insect pests and crushing damage will affect the quality of apples, and the shape, diameter and color of apples will affect the quality of apples. Therefore, it is particularly important to classify apples; early apple grading uses manual sorting, which not only consumes a lot of manpower, but also has slow sorting speed and low efficiency; therefore, Realizing fast and accurate grading of apples is of great significance to the development of the apple industry. [0003] At present, deep learning has been widely used in fruit quality detection and classification because of its advantages in data processing; deep neural network (D...

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
IPC IPC(8): G06T7/10G06T7/136
CPCG06T7/10G06T7/136G06T2207/20081G06T2207/20084G06T2207/20132G06T2207/20024G06T2207/10024Y02P90/30
Inventor 赵钦君赵雷申涛毕淑慧宋帅博李学斌
Owner UNIV OF JINAN
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