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

Precision enhancing method for visual media semantic indexing

A precision enhancement, media technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as difficult to use semantic concept correlation, influence effect, etc.

Active Publication Date: 2016-07-20
TSINGHUA UNIV
View PDF2 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the process of enhancing the semantic index of visual media, the above three points should be guaranteed as much as possible, so as to ensure the flexible application of the enhancement method on visual big data. Otherwise, it is difficult to make good use of the correlation of semantic concepts in the process of index enhancement. , thus affecting the expected effect of

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
  • Precision enhancing method for visual media semantic indexing
  • Precision enhancing method for visual media semantic indexing
  • Precision enhancing method for visual media semantic indexing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The precision enhancement method for visual media semantic index proposed by the present invention comprises the following steps:

[0061] (1) Perform semantic indexing on the objects and scenes contained in the initial visual media to obtain the detection confidence value of the initial visual media semantic index, and construct a matrix C according to the detection confidence value, and the rows in the matrix C correspond to A sample in video media c i , 1≤i≤N, such as an image or a video shot, the column in the matrix C corresponds to an object or scene v j , 1≤j≤M, any element c in the matrix C ij Indicates sample c i the contained object or scene v j The detection confidence value, wherein, N represents the number of samples, and M represents the number of objects or scenes;

[0062] (2) Set a detection confidence threshold, compare the detection confidence value in the above matrix C with the set detection confidence threshold, if the detection confidence valu...

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 relates to a precision enhancing method for visual media semantic indexing, and belongs to the technical field of visual media processing.The method comprises the steps that semantic indexing is carried out on objects and scenes contained in visual media at first, a confidence coefficient matrix is built, some elements are screened out through threshold value judgment, a weighing non-negative matrix factorization method is applied to reestimate the screened matrix, and overall precision is enhanced; a similarity propagating method is adopted according to an overall precision enhanced result, and a similarity relation between samples is utilized for overall precision enhancing.The precision enhancing method has the advantages that the accuracy of visual media semantic indexing is enhanced by means of various kinds of semantic relations, the method does not depend on a large number of annotation data sets and knowledge bases and has the strong flexibility and adaptability, overall precision enhancing and local precision enhancing are organically combined, and the flexibility and effect of the method are improved; the algorithm is low in calculation complexity, strong in extendibility and suitable for practical industrial application.

Description

technical field [0001] The invention relates to a precision enhancement method for semantic indexing of visual media, belonging to the technical field of visual media processing. Background technique [0002] The semantic indexing of visual media based on content analysis has gone beyond the simple application of several independent concept detectors, but more effective semantic retrieval by combining multiple concept information and post-processing the concept detection results. Due to the limitations of the training sample set itself, such as the sparsity and inaccuracy of manual annotation, the method based on a specific training sample set to improve the accuracy of visual media often faces difficulties in obtaining accurate concept correlation (such as The law of simultaneous appearance of concepts, ontological association, etc.). [0003] At present, a kind of visual media indexing method that utilizes the relationship between concepts is a multi-label training method...

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
CPCG06F16/783
Inventor 王鹏孙立峰杨士强
Owner TSINGHUA UNIV
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