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

Image interested region clustering method and device, computing equipment and storage medium

A region of interest and clustering method technology, applied in the field of image region of interest clustering device, image region of interest clustering, computing equipment and storage media, can solve problems such as image error, large amount of calculation, noise interference, etc. Achieve the effect of improving accuracy, reducing calculation amount, and reducing calculation time consumption

Active Publication Date: 2020-04-10
TENCENT TECH (SHENZHEN) CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This type of clustering method has a large amount of computation, and it takes a lot of time to solve large-scale and complex distribution clustering problems.
Moreover, this type of clustering algorithm is susceptible to noise interference, and often clusters images that do not contain regions of interest by mistake

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
  • Image interested region clustering method and device, computing equipment and storage medium
  • Image interested region clustering method and device, computing equipment and storage medium
  • Image interested region clustering method and device, computing equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] Before describing embodiments of the present invention, several terms used herein are explained. These concepts should be known to those skilled in the art, and their detailed descriptions are omitted herein for the sake of brevity.

[0033] 1. Feature extraction: convert the original image into a feature vector, which can reduce data redundancy, discover more meaningful potential variables, and help generate a deeper understanding of the data.

[0034] 2. Convolutional neural network: A type of feedforward neural network that includes computation and has a deep structure. It is one of the representative algorithms of deep learning and can be used as a "feature extractor" in machine learning.

[0035] Embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0036] figure 1 An example application scenario 100 for clustering image regions of interest according to an embodiment of the present invention is shown...

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 an image interested region clustering method and device, computing equipment and a computer-readable storage medium. The image interested region clustering method comprises the following steps: for each image interested region in an image interested region set, creating a corresponding index sequence; for any two image interested regions in the image interested region set,determining an order distance between the two image interested regions based on the repetition degree between a group of adjacent image interested regions of the two image interested regions; and clustering each image interested region in the image interested region set based on the determined order distance. According to the method, the clustering time consumption can be reduced and the clustering accuracy can be improved.

Description

technical field [0001] The present invention relates to image clustering technology, in particular to an image region of interest clustering method, an image region of interest clustering device, a computing device and a storage medium. Background technique [0002] Clustering refers to the division of a collection of physical or abstract objects into classes consisting of similar objects. A cluster generated by clustering is a collection of data objects that are similar to each other and different from objects in other clusters. [0003] With the development of computer and network technology, we often need to face a large amount of image data, and often hope to cluster image data with the same or similar objects together, such as in applications such as photo album management. Conventional clustering methods first extract the features of the region of interest in the image, and then measure the similarity of features by Euclidean distance or cosine distance to achieve clu...

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
IPC IPC(8): G06K9/62G06K9/00
CPCG06V40/172G06V40/161G06V40/168G06F18/23
Inventor 郭梓铿
Owner TENCENT TECH (SHENZHEN) CO LTD