Image classification method based on deep learning feature and maximum confidence path

A technology of deep learning and classification method, applied in the field of pattern recognition, can solve the problems of low classification accuracy, large amount of calculation for large image classification, etc., to achieve good discrimination and robustness, optimize computational complexity, and good results.

Inactive Publication Date: 2015-10-21
XIAMEN UNIV
View PDF3 Cites 29 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 based on deep learning features and ma

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
  • Image classification method based on deep learning feature and maximum confidence path
  • Image classification method based on deep learning feature and maximum confidence path
  • Image classification method based on deep learning feature and maximum confidence path

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] refer to figure 1 and 2 , the implementation steps of the present invention include extracting image features, constructing a visual tree and training a corresponding classifier, and testing three parts of the picture according to the scoring mechanism proposed by the present invention.

[0034] Step 1, train a CNN model

[0035] Download a large image library, such as the ImageNet2012 image classification competition library, and refer to the 7-layer model mentioned by Hinton in ImageNet Classification with Deep Convoutional Neural Networks to train a CNN model

[0036] Step 2, extract features

[0037] Use the CNN model trained in step 1 to extract features from all the images in the experimental database, that is, the output of the last fully connected layer of the CNN is used as the feature of the image for subsequent calculations.

[0038] Step 3, calculate the similarity matrix

[0039] (3a) Calculate the mean vector of each class class variance is the f...

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

An image classification method based on a deep learning feature and a maximum confidence path belongs to the field of mode identification. The method comprises the steps of: training a convolutional neural network on a large enough image library; extracting an image feature by means of the trained convolutional neural network; calculating a mean vector of each class; performing iteration clustering on the mean vector that represents each class by means of a spectrum clustering algorithm so as to construct a visual tree; training svm for each non-leaf node of the tree; and for a given test image, from top to bottom, judging the probability of the test image to the corresponding node, and finding a leaf node with the biggest path probability, namely a final target class. The image feature is extracted by means of CNN, thereby achieving very good discrimination and robustness; a distance calculation formula of two classes is given out, the complexity of calculation is greatly optimized by means of derivation and the similarity of the classes is obtained, so that the visual tree is constructed by iteratively using the spectrum clustering algorithm; and the use of a visual relationship between the classes can achieve very good effects for large image classification.

Description

technical field [0001] The invention belongs to the field of pattern recognition, and in particular relates to an image classification method based on deep learning features and maximum confidence paths that can be used for large-scale image classification. Background technique [0002] In the field of computer vision, image classification is a very important and a very classic research problem. However, as the number of images increases and the types of images increase, large-scale image classification is still a very challenging task. Due to the increase in the number of images, the amount of calculation will also increase, the time required will also increase, and the hardware requirements are also high. If you still use the traditional method to train a multi-class classifier as the final classification basis, there will be calculations. issues of complexity and accuracy. Therefore, it is necessary to design a new classification framework and classification method. ...

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): G06K9/62
CPCG06F18/23
Inventor 曲延云卢畅
Owner XIAMEN UNIV
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