Image marking method based on characteristic scene

A feature scene, image annotation technology, applied in special data processing applications, instruments, electronic digital data processing and other directions, can solve problems such as the inability to guarantee semantic content consistency, to ensure semantic consistency, improve reliability, and increase consistency Effect

Inactive Publication Date: 2011-02-02
HARBIN ENG UNIV
View PDF4 Cites 37 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] For scene classification of learning images, relying only on the visual features of images obviously cannot guarantee the consistency of semantic content

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 marking method based on characteristic scene
  • Image marking method based on characteristic scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Combine below figure 1 The image labeling method based on the feature scene of the present invention is described in more detail:

[0021] Step 1. Use image segmentation algorithm to segment the labeled image used for learning to obtain the visual description of the image region.

[0022] Step 2, perform automatic semantic scene clustering on the annotated images used for learning. The specific method is as follows.

[0023] In the annotated image set for learning, high-density regions are selected as semantic scene clustering centers. The present invention adopts the shared nearest neighbor clustering (Shared Nearest Neighbor, SNN) method to first construct the sample similarity matrix, and the neighbors of each sample can use the intersection of its visual neighbors and semantically marked neighbors. Then, the sparse processing of k-nearest neighbors is performed, and the nearest neighbor graph is constructed. The cluster center is established by counting the link...

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 provides an image marking method based on a characteristic scene, which comprises the steps of: segmenting a marked image used for learning by adopting an image segmenting algorithm, and obtaining vision description of an image region; 2, carrying out automatic semantic scene clustering on the marked image used for learning; 3, generating a characteristic scene space for each scene semantic category; 4, establishing corresponding semantic tree for each characteristic scene space; and 5, projecting an image to be marked in each characteristic scene space, determining the semantic category of the image to be marked for the fitting degree of a mixing model by adopting the projected vision characteristic and obtaining the final marking of the image through the semantic tree for the image for determining the semantic content. The image marking method fully utilizes the marked character information of a learning image, is used for carrying out automatic semantic scene clustering on the marked image used for learning, and ensures that more complete vision description is obtained under the special scene, thereby improving the reliability of automatic semantic marking through the image vision characteristic.

Description

technical field [0001] The invention relates to an automatic image labeling method. Background technique [0002] Image annotation is a challenging task, which has important implications for image analysis, understanding and image retrieval. Through the learning of labeled image sets, a relationship model between semantic concept space and visual feature space is established, and this model is used to label unlabeled image sets. Due to the intricate correspondence between low-level semantics, the accuracy of automatic annotation is low. Under the constraints of the scene, the mapping relationship between annotations and visual features can be simplified, and the reliability of automatic annotations can be improved. [0003] For scene classification of learning images, relying only on the visual features of images obviously cannot guarantee the consistency of semantic content. As a very valuable resource, image annotations better reflect the semantic information of images....

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): G06F17/30
Inventor 刘咏梅
Owner HARBIN ENG UNIV
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