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

An Optimal Image Set Selection Method for Group Image Insertion

An image collection and image technology, which is applied to instruments, computing, character and pattern recognition, etc., can solve problems such as low efficiency, and achieve the effect of high search efficiency and manpower saving.

Active Publication Date: 2022-03-04
XIDIAN UNIV
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the subjective judgment is generally made through the human eye, and the efficiency is low.

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
  • An Optimal Image Set Selection Method for Group Image Insertion
  • An Optimal Image Set Selection Method for Group Image Insertion
  • An Optimal Image Set Selection Method for Group Image Insertion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] Below in conjunction with accompanying drawing and specific embodiment, the present invention is described in further detail:

[0027] refer to figure 1 , the present invention comprises the steps:

[0028] Step 1) Extract the SIFT features of the training image:

[0029] Select multiple training images from the image sample library according to the requirements, use the SIFT feature extraction function provided in the opencv library to extract the SIFT features of each training image, and save the extracted SIFT feature vectors to a set of SIFT feature vectors for training images ;

[0030] Step 2) Build a visual dictionary:

[0031] Cluster the SIFT feature vectors in the SIFT feature vector set of the training image to obtain multiple clusters, and use the cluster center of each cluster as a visual word to obtain a visual dictionary composed of multiple visual words ;

[0032] Among them, the clustering uses the K-means clustering method to cluster the SIFT feat...

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 present invention proposes a method for selecting an optimal image set for group image insertion, aiming to select the image set with the highest similarity to the image to be inserted, and the implementation steps are: extracting the SIFT feature of the training image; establishing a visual dictionary; Get the SIFT feature of each image in each image set of the group image; obtain the visual word histogram of each image set; obtain the visual word histogram of the image to be inserted; calculate the similarity of each image set in the image to be inserted and the group image; Pick the best set of images to insert. The present invention explores the relationship between the image to be inserted and the image set, and can select the image set with the highest similarity for the image added to the group image, and can be used for image insertion in the scene of cloud group image management and image database management Happening.

Description

technical field [0001] The invention belongs to the technical field of image coding, and relates to a method for selecting an optimal image set, in particular to a method for selecting an optimal image set based on a bag-of-words model for group image insertion, which can be used for cloud group image management and image database management In the case of inserting an image into a group image in a scene, the image set with the highest similarity can be selected for the image to be inserted. Background technique [0002] In the last ten years. With the rapid development of Internet-related industries, multimedia content such as digital images has also shown explosive growth. According to the report of Facebook, the world's largest social network service company, its stored photos have exceeded 220 billion, and it is increasing at a rate of 300 million per day. The huge amount of image and video data has brought great pressure on bandwidth storage and other aspects. To this...

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 Patents(China)
IPC IPC(8): G06V10/46G06V10/50G06V10/762G06K9/62
CPCG06V10/464G06V10/50G06F18/23213
Inventor 吴炜许冬梅
Owner XIDIAN UNIV