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

Image labeling method based on multi-label learning, terminal device and storage medium

An image tagging and multi-labeling technology, which is applied in the direction of instruments, character and pattern recognition, computer parts, etc., can solve the problem that the uniqueness of tags cannot meet the needs of image tags

Inactive Publication Date: 2018-09-14
XIAMEN UNIV OF TECH
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In traditional supervised learning, an example is only associated with one label, which represents its unique category. However, the uniqueness of this label cannot satisfy the problem of image labeling, because an image usually contains multiple semantic contents, so There are multiple categories of tags at the same time, for example, an image can include one or more semantic concepts, such as "people", "grass", "sky" and "sunset"; therefore, there is an urgent need for an image that can accurately label Semantic Image Annotation Method

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 based on multi-label learning, terminal device and storage medium
  • Image labeling method based on multi-label learning, terminal device and storage medium
  • Image labeling method based on multi-label learning, terminal device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] Embodiment 1 of the present invention provides an image labeling method based on multi-label learning. The purpose of multi-label learning is to define a classification model f l :x→R(l=1,2,...,L). f l A larger value means that the instance is more likely to have y l Label. The ranking function rank(·,·) can be transformed from the function f(·): For any y k ∈Y,y j ∈Y(k≠j), if f k (x i ) > f j (x i ), then rank(x i ,y k )i ,y j ). Given a threshold σ, we can define a classifier h:x→2 based on f( ) y , for an instance x i ∈ x, if f k (x i )>σ, then y j ∈h(x i ),otherwise

[0069] Such as figure 1 As shown, it is a schematic flow chart of the image labeling method based on multi-label learning described in Embodiment 1 of the present invention, and the method may include the following steps:

[0070] S100: Extract all the labels of the instance, and calculate the label importance degree of each label corresponding to each instance in the multi-label ...

Embodiment 2

[0150] The present invention also provides an image tagging terminal device based on multi-label learning, including a memory, a processor, and a computer program stored in the memory and operable on the processor, and the processor executes the computer program The steps in the above method embodiment of Embodiment 1 of the present invention are realized at the same time.

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 present invention relates to an image labeling method based on multi-label learning, a terminal device and a storage medium. The method comprises the following steps of: S100: extracting all the labels in examples, and calculating the label importance degree of each label corresponding to each example in a multi-label training set through a label propagation method; S200: performing resamplingof the multi-label training set according to the label importance degrees to obtain training subsets; and S300: calculating class attributes of the training subsets, and performing classification according to the class attributes. Aiming at the problems of ambiguity and amounts of images in the image labeling field, multi-label learning is employed to perform labeling of the images, the information of the relative label importance degrees hidden in the training samples is employed to construct more effective class attributes, the image labeling method is employed to construct more effective class attributes corresponding to different labels and construct a classification model of the labels on the class attributes so as to obtain better image classification effects.

Description

technical field [0001] The present invention relates to the technical field of machine learning, in particular to an image labeling method based on multi-label learning, a terminal device and a storage medium. Background technique [0002] With the development of society and the further improvement of technology, a large number of digital images are generated and disseminated every day. To provide related services on such a large-scale image data, one of the core and most difficult tasks is to let the computer understand the image. semantics, and image annotation is the key technology. Image annotation, also known as automatic image annotation, refers to the process in which the computer system automatically associates the concept tags contained in the image with it according to the visual content of the image. It is one of the important fields of content-based image retrieval. Nowadays, although the research in the field of image annotation has achieved a lot of results, w...

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
CPCG06F18/2113G06F18/22G06F18/241G06F18/214
Inventor 翁伟李建敏尹华一朱顺痣吴芸钟瑛
Owner XIAMEN UNIV OF TECH
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