Image classification method and system based on hierarchical multi-task learning

A technology of multi-task learning and classification method, applied in the field of image classification methods and systems based on hierarchical multi-task learning, can solve the problem of ignoring the hierarchy of image categories, and achieve the effect of avoiding data imbalance and improving efficiency

Inactive Publication Date: 2019-10-08
NANJING UNIV OF POSTS & TELECOMM
View PDF9 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when dealing with image classification tasks, most classification algorithms usually process each image category separately, thus ignoring the hierarchical structure between image categories

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 and system based on hierarchical multi-task learning
  • Image classification method and system based on hierarchical multi-task learning
  • Image classification method and system based on hierarchical multi-task learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043]The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0044] Such as figure 1 As shown, the present invention provides a kind of image classification method based on layered multi-task learning, in practical application, concrete steps are as follows:

[0045] (1) Use the existing public dataset CIFAR-100, which contains 100 image categories, each category contains 600 images, and the image scale is normalized to 224×224 pixels; for the training sample set The image is marked with a hierarchical category from coarse to fine, corresponding to a 3-layer classification tree composed of hierarchical nodes, such as figure 2 As shown, among them, the unclassified uncategorized label at the bottom level corresponds to the root node of the classification tree, the fine category label at the top level corresponds to the leaf node of the classification tree, and the coarse category ...

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 system based on hierarchical multi-task learning. The method comprises the following steps of: firstly, carrying out hierarchical category labeling on images in a training sample set from coarse to fine by utilizing a relation between image categories through experience knowledge of experts in some professional fields; secondly, constructing a hierarchical deep convolutional neural network comprising a feature extraction module, a coarse classification layer and a fine classification layer; secondly, training the coarse classificationlayer and the fine classification layer by adopting a multi-task learning algorithm; and finally, classifying the input test images by using the trained hierarchical deep convolutional neural network.The hierarchical structure information between the image categories is combined with the convolutional neural network, the hierarchical deep convolutional neural network is designed, and a multi-tasklearning algorithm is utilized to realize coarse-to-fine classification of the images.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an image classification method and system based on hierarchical multi-task learning. Background technique [0002] Image classification is a fundamental problem in the field of pattern recognition. Image classification is a method of dividing images into different categories according to the characteristics of the image itself. Image classification in pattern recognition mainly refers to the process of using computer to replace human visual judgment and understanding, and automatically classifying image categories through some specific algorithms. [0003] In image datasets, there may be a problem that the visual separability of image classes is not uniform, that is, some classes are more difficult to distinguish than others. For example, it is easy to distinguish between apples and buses, but it is difficult to distinguish apples from oranges. In fact, both apples and oranges ...

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): G06K9/62
CPCG06F18/2411G06F18/24323G06F18/214
Inventor 卢官明王备备卢峻禾闫静杰
Owner NANJING UNIV OF POSTS & TELECOMM
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