An image classification method and device

A classification method and image technology, applied in the field of transfer learning and deep learning, can solve the problem of insufficient image feature extraction and image classification rate, and achieve the effect of alleviating the problem of over-fitting, increasing the amount of features, and improving the accuracy rate

Active Publication Date: 2021-06-01
GUANGDONG UNIV OF TECH
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide an image classification method and device, the purpose of which is to solve the problem of image classification rate caused by over-fitting phenomenon and insufficient image feature extraction in the prior art when using small data sets to train image classification models

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
  • An image classification method and device
  • An image classification method and device
  • An image classification method and device

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0103] As a specific implementation, the above-mentioned hybrid model training module may include:

[0104] An acquisition unit, configured to acquire a small image data set, and input the small data set into the migration model structure;

[0105] The first extraction unit is used to extract the initial features of the small image data set by using the underlying feature extraction layer;

[0106] A feature training unit, configured to use the residual network layer to train the initial features to obtain the first feature map;

[0107] The second extraction unit is used to extract the second feature map of the image small data set by using the multi-scale pooling layer;

[0108] A concatenation unit, configured to concatenate the first feature map and the second feature map to obtain the target feature map;

[0109] The parameter update training unit is used to input the target feature map into the softmax classifier, and use the batch gradient descent method to iterativel...

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 an image classification method and device. Based on a large image data set, the AlexNet model structure is trained; five trained convolutional layers are transferred to a small database to form a bottom layer feature extraction layer, which is combined with a two-layer convolutional layer. The residual network layer, multi-scale pooling layer, feature layer and softmax classifier are constructed to obtain the migration model structure; the image small data set is input into the migration model structure, and the batch gradient descent method is used to update the parameters to train the image classification hybrid model; according to The image classification hybrid model performs classification and obtains classification results. This application transfers the pre-trained convolutional layers on the large data set to the small data set, adds a multi-scale pooling layer, and connects the feature quantities output by the residual network layer and the multi-scale pooling layer into the classification The device increases the amount of features and alleviates the problem of overfitting; and the hybrid model trained based on convolutional neural network and transfer learning can effectively improve the accuracy of image classification.

Description

technical field [0001] The present invention relates to the field of transfer learning and deep learning, in particular to an image classification method and device. Background technique [0002] Convolutional Neural Networks (CNN) is an efficient recognition method. Generally, the basic structure of CNN includes two layers, one is the feature extraction layer, the input of each neuron is connected to the local receptive field of the previous layer, and the local features are extracted. Once the local feature is extracted, the positional relationship between it and other features is also determined; the second is the feature map layer, each calculation layer of the network is composed of multiple feature maps, each feature map is a plane, All neurons on the plane have equal weights. [0003] Transfer learning is the influence of one kind of learning on another kind of learning, which widely exists in the learning of knowledge, skills, attitudes and behavioral norms. Any k...

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): G06K9/62G06N3/08
CPCG06N3/082G06F18/24G06F18/214
Inventor 蔡述庭刘坤陈平李卫军梁天智
Owner GUANGDONG UNIV OF TECH
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