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

Large-scale human face image searching method

A face image, large-scale technology, applied in the field of face image retrieval

Inactive Publication Date: 2013-03-20
NANJING UNIV
View PDF1 Cites 61 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Purpose of the invention: In order to solve the problems in the prior art, the present invention proposes a large-scale face image retrieval method, thereby effectively solving the problem of fast and accurate retrieval of face images under large-scale data

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
  • Large-scale human face image searching method
  • Large-scale human face image searching method
  • Large-scale human face image searching method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0095] This embodiment includes the following parts:

[0096] 1. Location of key points of face image:

[0097] Using Active Shape Models (ASM) to locate the key points in the face image, this module is mainly divided into two steps: model training and key point search.

[0098] Principal component analysis (PCA) is used in the process of training the model.

[0099] Principal component analysis is an exploratory statistical analysis method that concentrates the information scattered on a set of variables into a few comprehensive indicators (principal components). It uses principal components to describe the internal structure of the data set, which actually plays a role in data dimensionality reduction Function, this method selects the eigenvectors corresponding to the first few largest eigenvalues ​​of the original data covariance matrix to form a set of bases to achieve the purpose of best characterizing the original data. Consider the vector x in the n-dimensional space. In order...

Embodiment 2

[0180] Image 6 For the retrieval diagram of Example 2, the source of the image of the person in the figure is the public LFW database. In the figure, 1 is the original face image, the box in the figure represents the face block, 2 represents the extracted features, including local features and global special features, 3 represents the trained dictionary, 4 is the preliminary search result obtained from the dictionary, that is, the candidate In the face image set, 5 is the face image reference set. According to the face image reference set, the preliminary retrieval results are reordered, and 6 is the final retrieval result. The face in 6 and the face in 1 are the same person, which means the retrieval is successful.

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 a large-scale human face image searching method. The method comprises the following steps of preprocessing human face images; extracting local characteristics from the human face images; extracting overall geometrical characteristics from the human face images; quantifying the local characteristics; quantifying the overall geometrical characteristics; establishing a reverse index; searching a candidate human face image set; and re-arranging the candidate human face image set. By the method, an index for a large-scale human face image database can be established, quick human face research is realized, and the research efficiency is realized. In addition, the accuracy of human face research is improved by embedding an auxiliary information characteristic quantifying and candidate human face image set re-arranging algorithm. Effective and accurate large-scale human face image search is realized by the method, so that the method has higher use value.

Description

Technical field [0001] The invention belongs to the field of face image retrieval, in particular to a large-scale face image retrieval method. Background technique [0002] In recent years, with the rise of Weibo and social networking sites and the demand for public safety, face image data has rapidly grown to a massive scale. In such a massive face database, a part of the face images that you are interested in can be retrieved It has become an urgent need, and large-scale face retrieval has gradually become a research focus. Large-scale facial image retrieval requires that the algorithm has good scalability to the data scale. In addition, retrieval efficiency, recall rate, and accuracy are general indicators to evaluate retrieval performance. Not only does it require high retrieval efficiency, but also ensures accurate retrieval Sex. [0003] For large-scale face retrieval problems, if the traditional face recognition method is used directly, high-dimensional and complex feature...

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): G06F17/30G06K9/46G06K9/62
Inventor 杨育彬毛晓蛟钱洪波
Owner NANJING 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