Image meaning parsing method based on soft glance learning

A semantic parsing, weakly supervised technology, applied in the field of image semantic parsing based on weakly supervised learning, can solve single problems and achieve the effect of fine-grained image semantic understanding

Active Publication Date: 2013-10-02
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF4 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of this, the present invention proposes an image semantic analysis method based on weakly supervised learning to solve the problem of dividing an image into a s...

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 meaning parsing method based on soft glance learning
  • Image meaning parsing method based on soft glance learning
  • Image meaning parsing method based on soft glance learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] figure 1 is a flow chart of the image semantic analysis method based on weakly supervised learning of the present invention. Such as figure 1 Shown, the present invention comprises the steps:

[0026] Step S1, preprocessing the image.

[0027] In this step, the image with semantic labels is over-segmented into sub-regions, and the visual features and location information of each sub-region are extracted. The visual features adopt the bag-of-words model.

[0028] Step S2, performing dual clustering on the image based on weakly supervised learning. This step is the main part of the present invention, and is used for the preprocessed image

[0029] Step S3. This step is used to output semantic analysis results.

[0030] Step S2 mainly includes the following three steps:

[0031] S2.1, using the double clustering method of joint spectral clustering and discriminative clustering to cluster the image sub-regions obtained by the over-segmentation method;

[0032] S2.2....

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 meaning parsing method based on soft glance learning and aims to realize segmentation of images into a series of complete areas having individual meanings and meaning marking on each area on a basis of a lot of given user marking images. The image meaning parsing method comprises steps that: dual joint spectrum clustering and discrimination clustering methods are utilized to cluster image sub-areas acquired through an over-segmentation method, moreover, a corresponding constraint relation between image grade marking and image area grade marking is utilized to establish a soft glance learning model aiming to have a minimum error, and meaning labels are distributed to clustering sets in each image sub-area. Multiple classifiers acquired through discrimination clustering learning can realize meaning parsing for images without label information. The image meaning parsing method can not only add meaning labels to the images, but also the labels can be added to corresponding areas of the images to realize finer image meaning understanding.

Description

technical field [0001] The invention belongs to the technical field of automatic analysis and understanding of multimedia content, and in particular relates to an image semantic analysis method based on weakly supervised learning. Background technique [0002] Image semantic analysis is a task that combines image segmentation and region labeling. It is a higher-level image understanding technology. It can not only add semantic labels to images, but also add labels to corresponding regions in the image to achieve More fine-grained image semantic understanding. [0003] Image segmentation and region labeling are inseparable and mutually reinforcing. Accurate image segmentation can provide accurate visual feature representation for region labeling. Conversely, good region labeling results can also promote image segmentation, because pixels with the same semantic label belong to the same object. [0004] Most of the existing image semantic analysis methods are based on fully s...

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): G06K9/62G06T7/00
Inventor 卢汉清刘静刘洋
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
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