Unlock instant, AI-driven research and patent intelligence for your innovation.

Image labeling method and device based on deep convolutional network based on unbalanced learning

A deep convolution and unbalanced technology, applied in the field of image labeling, can solve problems such as difficult image labeling

Active Publication Date: 2019-05-17
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, how to design more powerful image features and take into account the non-uniform distribution of image category labels has always been a difficult point in the field of image annotation.

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 labeling method and device based on deep convolutional network based on unbalanced learning
  • Image labeling method and device based on deep convolutional network based on unbalanced learning
  • Image labeling method and device based on deep convolutional network based on unbalanced learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In order to make the purpose, technical solutions and advantages of the present invention clearer, the following in conjunction with specific examples, and with reference to the appended figure 1 , to further describe the present invention in detail.

[0031] The present invention proposes a deep convolutional network image labeling method and device based on unbalanced learning.

[0032] First, the present invention constructs a deep convolutional network to extract the depth features of the image. A deep convolutional network mainly consists of three components: a convolutional layer, a downsampling layer, and a fully connected layer. The convolutional layer deconvolutes the input image with a trainable convolution kernel (the first stage is the input image, and the subsequent stage is the feature map), and then adds a bias to obtain the convolutional layer. The neuron weights of the convolutional layer on the same feature map surface are the same, which reduces the...

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 deep convolutional network image labeling method and device based on unbalanced learning. The method includes: step 1, preprocessing the image to be recognized to obtain the original pixels of the image to be recognized; step 2, converting the image to be recognized The original pixels of the image to be recognized are input into the deep convolutional neural network to obtain the depth feature representation information of the image to be recognized; step 3, using the depth feature representation information to predict the annotation information of the image to be recognized. The image labeling method described in the present invention not only takes into account the distribution of words in the image dictionary, but also extracts the original pixels of the image layer by layer through a deep convolutional network, which is more accurate than the traditional labeling method.

Description

technical field [0001] The invention relates to the technical field of image labeling, in particular to a deep convolutional network image labeling method based on unbalanced learning. Background technique [0002] In the era of big data, the information resources that people can access are showing explosive growth, and massive images and video information are born on the Internet every day. In order to effectively organize, query and browse such a large-scale image resource, image retrieval technology emerges as the times require. Text-Based Image Retrieval (TBIR) is an important image retrieval method. For TBIR, it requires users to submit text as a query, therefore, image retrieval needs to obtain the textual semantic information of images in advance. Image tagging is an effective method to obtain semantic information of images, and it is widely used, for example, in social media, a large number of images are tagged by users. However, there are a large number of unlabe...

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
CPCG06N3/084G06F18/214
Inventor 张文生杨阳
Owner INST OF AUTOMATION CHINESE ACAD OF SCI