Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Method for quickly searching ten billion-level images

A technology of images and image samples, which is applied in the fields of computer software and information search, can solve problems such as reducing the accuracy of retrieval, and achieve the effects of reducing edge effects, good stability, and reducing quantity

Pending Publication Date: 2022-06-07
TRS INFORMATION TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Additionally, fringe effects from IVF and unique Gemfield straps can reduce retrieval accuracy

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
  • Method for quickly searching ten billion-level images
  • Method for quickly searching ten billion-level images
  • Method for quickly searching ten billion-level images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only Embodiments of some, but not all, of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0059] It should be noted that the terms "first", "second" and the like in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or sequence. It is to be understood that the data so used may be interchanged under appropriate circums...

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 the technical field of computer software, and relates to the technical field of information search, in particular to a method for quickly searching a 10 billion-level image. Comprising the following steps: processing image sample data, performing image feature extraction on 10 billion-level image sample data by using a deep neural network, and forming a feature vector library of an image after PCA dimension reduction; at least two stages of PQ groups are constructed by using an IVPQ algorithm, each stage of PQ group at least comprises three PQs, and it is ensured that the segmentation numbers of feature vectors are co-prime pairwise, so that a feature vector index database is formed; based on the feature image index database, an optimal candidate set can be obtained during retrieval, similarity calculation and sorting are performed on the optimal candidate set, and finally a final sorting TOPN is output. Compared with FAISS, the method has higher accuracy, in single server operation, the recall rate of Top10 reaches 61.8%, the operation stability is better, 220 real concurrency is supported, the throughput rate reaches 10000 times, the average response time is 30 ms, and the retrieval efficiency is higher.

Description

technical field [0001] The invention relates to the technical field of computer software, to the technical field of information search, and in particular to a method for fast search of tens of billions of images. Background technique [0002] With the rapid development of Internet computers, network resources have entered the eruption stage, especially image resources have often exceeded the range of tens of billions, which brings certain challenges to image retrieval in practical applications. [0003] The original image retrieval method is traditionally based on text, that is, the query function is realized through the image name, text information and index relationship. However, this approach has great limitations. Instead, content-based image retrieval, or CBIR (Content-based image retrieval), is a research branch in the field of computer vision that focuses on large-scale digital image content retrieval. The most typical CBIR system allows the user to enter a picture ...

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): G06F16/583
CPCG06F16/583
Inventor 程涛刘春平肖锋
Owner TRS INFORMATION TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products