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

Garbage classification method based on hybrid convolutional neural network

A convolutional neural network and garbage classification technology, applied in the field of garbage classification and recycling, can solve the problems of long training time and low garbage classification accuracy, and achieve the effect of improving representation ability, shortening training time, and good fitting.

Active Publication Date: 2020-05-12
QIQIHAR UNIVERSITY
View PDF3 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem that the existing method has low accuracy and long training time for garbage classification

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
  • Garbage classification method based on hybrid convolutional neural network
  • Garbage classification method based on hybrid convolutional neural network
  • Garbage classification method based on hybrid convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0027] Specific implementation mode one: as figure 1 As shown, a kind of garbage classification method based on hybrid convolutional neural network described in this embodiment comprises the following steps:

[0028] Step 1, load the garbage image, and preprocess the garbage image to obtain the preprocessed garbage image;

[0029] Step 2, building a hybrid convolutional neural network, inputting the preprocessed garbage image obtained in step 1 into the hybrid convolutional neural network for training, to obtain a trained hybrid convolutional neural network;

[0030] The structure of the hybrid convolutional neural network is:

[0031] Starting from the input end of the hybrid convolutional neural network, the hybrid convolutional neural network sequentially includes the first network module, the second network module, the third network module, the fourth network module, the flattening layer, the first fully connected layer, the first The batch normalization layer after the fu...

specific Embodiment approach 2

[0035] Specific embodiment 2: The difference between this embodiment and specific embodiment 1 is that in the first step, the garbage image is preprocessed to obtain the preprocessed garbage image; the specific process is:

[0036] Obtain the preprocessed garbage image by performing data enhancement and normalization processing on the loaded garbage image;

[0037] The data augmentation method includes randomly zooming, flipping, translating and rotating the garbage image.

[0038] Generally speaking, a more successful neural network requires a large number of parameters, and making these parameters work properly requires a large amount of data for training, but in reality there is often not so much data. Considering that the trash image database TrashNet has relatively few samples, data enhancement is performed on the trash image during preprocessing to increase the number of training samples. It can not only increase the amount of training data and improve the generalizatio...

specific Embodiment approach 3

[0039] Specific implementation mode three: the difference between this implementation mode and specific implementation mode one is:

[0040] Batch normalization is added after each convolutional layer and fully connected layer to further enhance the feature extraction ability of the model, which can effectively avoid gradient disappearance and gradient explosion, and reduce the structural complexity of the model.

[0041] The convolutional layer is used to extract image features, and the BN layer is used to improve the generalization ability of the network, disrupt the training data and speed up the convergence speed of the model. During training, BN is calculated based on each small batch. The mean and variance corresponding to each batch of data during training are recorded, and they are used to calculate the mean and variance of the entire training set. The calculation formula is:

[0042]

[0043]

[0044] E[x]←E β [μ β ]

[0045]

[0046] Among them, m refers ...

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 garbage classification method based on a hybrid convolutional neural network, and belongs to the technical field of garbage classification and recovery. The method solves theproblems that an existing method is low in garbage classification precision and long in required training time. According to a hybrid convolutional neural network model, a convolutional layer, batchstandardization, a maximum pooling layer and a full connection layer are flexibly applied, and BN batch standardization is applied to each convolutional layer and each full connection layer, so that the feature extraction capability of the model is further enhanced, the effect of each layer is brought into full play, and a relatively good classification result is obtained. By utilizing the regularization effect of the BN layer, the maximum pooling layer is properly added to perform statistics on the features, the feature dimension is reduced, the representation capability is improved, fittingcan be well performed, the convergence speed is high, the parameter quantity is small, the calculation complexity is low, and the method has obvious advantages compared with a traditional convolutional neural network. Meanwhile, an optimizer of SGDM + Nesterov is adopted in the model, and finally the classification accuracy of the model on the image reaches 92.6%. The method can be applied to household garbage classification.

Description

technical field [0001] The invention belongs to the technical field of garbage sorting and recycling, and in particular relates to a garbage sorting method based on a hybrid convolutional neural network. Background technique [0002] Garbage sorting and recycling occupies a very important position in daily life. With the improvement of people's living standards, there are more and more daily garbage. In the past, garbage classification was carried out manually. With the rise of artificial intelligence, the use of deep learning and other intelligent technologies to automatically classify garbage has been widely welcomed. Lulea Technical University started a project in 1999 to develop a system for recycling metal scrap using mechanical shape identifiers. SIFT and profile shape features are used in a Bayesian computational framework, and the system is based on the Flickr material database. Jinqiang Bai and others designed a new type of garbage-picking robot. The robot can use...

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): G06K9/62G06N3/04
CPCG06N3/045G06F18/213G06F18/214Y02W30/10
Inventor 石翠萍谭聪苗凤娟刘文礼王天毅
Owner QIQIHAR UNIVERSITY
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