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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


