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

Character image clustering method and device

An image clustering and character technology, applied in the field of image clustering, can solve the problem of low reliability of the clustering results of character images

Pending Publication Date: 2022-03-08
ZHEJIANG DAHUA TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in this portrait clustering method, once the quality of the person image is poor, the reliability of the clustering result of the person image will not be high.

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
  • Character image clustering method and device
  • Character image clustering method and device
  • Character image clustering method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] In order to better understand the technical solutions provided by the embodiments of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation manners.

[0042] To facilitate a better understanding of the technical terms involved in the embodiments of the present application, the following introduces the technical terms involved in the embodiments of the present application.

[0043] 1. The portrait clustering in the embodiment of the present application is a process of grouping multiple portrait images to form multiple sets. Wherein, the person image includes a face image or a human body image.

[0044] 2. The space-time domain division in the embodiment of the present application, the space-time domain includes time and space, and the space-time domain is used to represent the main world dimension of personnel existence and activities. A spatio-temporal domain consists of a set of con...

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 a character image clustering method and device, relates to the technical field of image clustering, and is used for improving the accuracy of character image clustering. According to the character image clustering method, the attribute characteristics of multiple aspects of the checkpoints are processed by using the self-organizing mapping network, so that the superior neurons corresponding to the checkpoints are determined, and the clusters to which the checkpoints belong are determined by using the superior neurons to which the checkpoints belong, so that a mode of performing spatial domain clustering on the character images is provided; the clustering result of the plurality of checkpoints is not influenced by the quality of the figure image, so that the reliability of the checkpoint clustering is improved, and the reliability of the figure image clustering is also improved.

Description

technical field [0001] The present application relates to the technical field of image clustering, in particular to a method and device for clustering images of people. Background technique [0002] Portrait clustering is the process of classifying images of people into different clusters (or classes). The person images in the same cluster have great similarity, while the person images in different clusters have great dissimilarity. Clustering a large number of person images can provide a data basis for later retrieval of images, and can also provide a large amount of sample data for later training of a model for recognizing person images. [0003] At present, the commonly used portrait clustering method focuses on the features of person images. In this portrait clustering method, the features of a large number of person images are generally extracted, and the person images with similar characteristics are classified into one cluster. However, in this portrait clustering m...

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): G06V40/10G06V10/147G06V10/22G06V10/762G06V10/74G06V10/77G06V10/82G06K9/62G06N3/04
CPCG06N3/04G06F18/23G06F18/22G06F18/2135
Inventor 张阳高圣兴陈立力周明伟
Owner ZHEJIANG DAHUA TECH CO LTD