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

Digital image automatic labeling method based on uncertainty analysis

A technology of automatic image annotation and digital image, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve uncertainty, cannot accurately estimate the distribution of classes, and the underlying features of the image cannot fully reflect and match the user's retrieval intention. and other problems to achieve the effect of reducing the wrong prediction rate and improving the correct prediction rate

Inactive Publication Date: 2018-10-16
EAST CHINA JIAOTONG UNIVERSITY
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, due to the multi-label feature of image annotation, some scholars regard it as a multi-label learning problem.
However, there are some defects in the existing methods: First, the underlying features of the image cannot fully reflect and match the user's retrieval intention
Finally, existing algorithms ignore the impact of limited training samples, which make it impossible to accurately estimate the distribution of each class
These problems arise mainly because of the uncertainty in the mapping process from the visual feature space to the semantic concept space

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
  • Digital image automatic labeling method based on uncertainty analysis
  • Digital image automatic labeling method based on uncertainty analysis
  • Digital image automatic labeling method based on uncertainty analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.

[0037] figure 1 It is a business process for implementing an automatic labeling method for digital images based on uncertainty analysis.

[0038] The implementation of the method in this embodiment requires a hardware environment to have a workstation or server that can run deep learning algorithms, and to be equipped with an NVIDIA graphics card. Realize that the language tool used in this embodiment has no special requirement, and C language, C++ language, Python language etc. can realize; There is also no special requirement to operating system platform, Microsoft Windows system, various Linux systems etc. all can be used as operating system operating platform , the invention can be developed into a graphical interface form, and can also be developed into a non-graphical interface form.

[0039] figure 1 It is a functional structural bloc...

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

A digital image automatic labeling method based on uncertainty analysis, including the steps of extracting image features based on a deep convolutional neural network, constructing an image automaticlabeling system based on a variable precision neighborhood rough set, and labeling unlabeled images. The method includes the following steps: collecting the image data and labeling to obtain a training set, and extracting a feature vector of the image through the deep convolutional neural network; obtaining a classification model based on the neighborhood estimation class conditional probability density; in prediction, extracting image features, and estimating the position of the image to be classified by using upper and lower approximation concepts of the rough set; directly judging the membership of the labels for the images located in positive and negative domains, and judging the images in the boundary domain by using a Bayesian decision rule. According to the digital image automatic labeling method based on uncertainty analysis, the position of images to be labeled in the sample space are estimated by introducing upper and lower approximation concepts of the rough set, the error prediction rate of the irrelevant labels is reduced, and the problem of uncertainty existing between the underlying image feature and the high level semantics in image automatic labeling is solved.

Description

technical field [0001] The invention relates to an automatic labeling method for digital images based on uncertainty analysis, which belongs to the technical field of computer image processing. Background technique [0002] With the rapid development of computer technology and the popularity of multimedia applications and social networks, multimedia data on the Internet has grown exponentially. Massive data brings new opportunities and challenges to multimedia application research, especially image-based application research. In order to dig out the required images from the massive image data, it is necessary to have an effective image retrieval mechanism. Automatic image annotation technology allows computers to automatically add semantic tags that can reflect image content to unlabeled images, which is the key to image retrieval. It tries to establish a mapping relationship between the high-level semantic information of the image and the low-level visual features, automa...

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): G06K9/62G06K9/46G06N3/04G06N3/08
CPCG06N3/08G06V10/40G06N3/045G06F18/214
Inventor 余鹰喻建云伍国华王乐为吴新念
Owner EAST CHINA JIAOTONG 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