Unlock instant, AI-driven research and patent intelligence for your innovation.

Database simplification method and system based on granular ball face clustering image quality evaluation

A technology for image quality assessment and quality assessment, which is applied in the field of image processing, can solve problems such as difficult identification of databases, and achieve the effects of eliminating redundancy, clear organization, and saving storage space

Active Publication Date: 2022-02-01
CHONGQING UNIV OF POSTS & TELECOMM
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is that the existing face database simplification method does not consider factors such as background blur and illumination level to score, so as to screen out the most suitable image for computer recognition, resulting in the simplification of the database still has difficult recognition technology The purpose of this problem is to provide a database reduction method and system based on granule face clustering image quality assessment, which solves the problem that the existing face database reduction method does not consider factors such as the degree of background blur and the degree of illumination for scoring to screen out Imagery best suited for computer recognition, resulting in technical problems with pared-down databases still difficult to recognize

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
  • Database simplification method and system based on granular ball face clustering image quality evaluation
  • Database simplification method and system based on granular ball face clustering image quality evaluation
  • Database simplification method and system based on granular ball face clustering image quality evaluation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] Please refer to figure 1 , the embodiment of the present invention provides a kind of database simplification method based on granule face clustering image quality assessment, comprising:

[0046] S101, converting each image in the face database into a vector;

[0047] S102, inputting the feature matrix formed by the vectors into the deep learning model for training to obtain multiple feature vectors;

[0048] S103, input the plurality of feature vectors into the granule model for clustering to form a plurality of spheres, and the face images represented by the points in one sphere belong to the same person;

[0049] S104, divide the plurality of granules into several groups, and each group includes all face images of a person;

[0050] S105, performing quality assessment on all face images in each group of spheres, and obtaining the score of each image;

[0051] S106. Eliminate face images with scores smaller than a preset score threshold to obtain a simplified data...

Embodiment 2

[0075] Please refer to Figure 5 , the embodiment of the present invention provides a database streamlining system based on image quality assessment of granule face clustering, including:

[0076] A conversion module, which is used to convert each image in the face database into a vector;

[0077] A training module, configured to input the feature matrix formed by the vector into the deep learning model for training to obtain a plurality of feature vectors;

[0078] The clustering module is used to input the multiple eigenvectors into the granule model for clustering to form a plurality of spheres, and the face images represented by points in one sphere belong to the same person;

[0079] A grouping module, configured to divide the plurality of granules into several groups, each group including all face images of a person;

[0080] A quality evaluation module is used to evaluate the quality of all face images in each group of spheres to obtain a score for each image;

[008...

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 database simplification method and system based on granular ball face clustering image quality evaluation. The method comprises the following steps: converting each image in a face database into a vector; inputting a feature matrix formed by the vectors into a deep learning model for training to obtain a plurality of feature vectors; inputting the plurality of feature vectors into a granular ball model for clustering to form a plurality of granular balls, the face images represented by points in one granular ball belonging to the same person; dividing the plurality of pellets into a plurality of groups, wherein each group comprises all face images of one person; performing quality evaluation on all face images in each group of pellets to obtain a score of each image; and removing the face images of which the scores are smaller than a preset score threshold to obtain a simplified database. According to the method, scoring is carried out by considering factors such as background fuzzy degree and illumination degree, so that the image most suitable for computer recognition is screened out, and the simplified database is easy to process and recognize.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a database simplification method and system for image quality assessment based on granule face clustering. Background technique [0002] The trend of globalization in today's world is becoming more and more obvious. Various countries have established their own face recognition systems one after another. The trend of big data has become irresistible. We cannot do without the support of big data in all aspects of our lives, such as online shopping, shopping platforms It will roughly analyze the user's preferences based on the daily clicks of the extracted user, and then recommend the items that the user wants on the home page. Face data is a very important sector in the field of big data. Face recognition technology is almost always used in social life fields such as access control systems and monitoring systems, especially the face payment technology that has become more ...

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): G06F16/55G06V40/16G06V10/762
CPCG06F16/55
Inventor 夏书银李东根张勇付京成
Owner CHONGQING UNIV OF POSTS & TELECOMM