Target retrieval method based on group of randomized visual vocabularies and context semantic information

A visual dictionary and semantic information technology, applied in computer components, secure communication devices, character and pattern recognition, etc., can solve problems such as high computational complexity, achieve enhanced differentiation, reduce semantic gap, and solve computational complexity Effect

Inactive Publication Date: 2012-09-26
THE PLA INFORMATION ENG UNIV
View PDF2 Cites 38 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Aiming at the deficiencies of the existing technologies, the present invention proposes a target retrieval method based on randomized visual dictionary groups and contextual semantic information, which effectively solves the high computational complexi

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
  • Target retrieval method based on group of randomized visual vocabularies and context semantic information
  • Target retrieval method based on group of randomized visual vocabularies and context semantic information
  • Target retrieval method based on group of randomized visual vocabularies and context semantic information

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0071] Embodiment 1: This embodiment is a target retrieval method based on randomized visual dictionary sets and contextual semantic information. First of all, for the low efficiency of traditional clustering algorithms and the problem of visual word synonymy and ambiguity, E 2 LSH clusters the local feature points of the training image database to generate a set of randomized visual dictionary groups that support dynamic expansion; secondly, select the query image and define the target area with a rectangular frame, and then extract the query image and image database according to Lowe's method SIFT features and E 2 LSH mapping realizes the matching of feature points and visual words; then, based on the language model, use the rectangular frame area and image saliency detection to calculate the retrieval score of each visual word in the query image and obtain the target model containing the semantic information of the target context ; Finally, for the problem of large memory cons...

Example Embodiment

[0073] Example 2: see figure 2 , image 3 , Figure 4 , The target retrieval method based on randomized visual dictionary group and contextual semantic information of this embodiment adopts the following steps to generate E 2 LSH's randomized visual dictionary group:

[0074] For each hash function g i (i=1,...,L), using it to hash the SIFT points of the training image library, the points that are very close in the space will be stored in the same bucket of the hash table, with the center of each bucket Represents a visual word, then each function g i Can generate a hash table, that is, a visual dictionary. Then, L functions g 1 ,...,G L Can generate a visual dictionary group, the process is like figure 2 Shown.

[0075] Among them, the detailed process of generating a single visual dictionary can be described as follows:

[0076] (1) SIFT feature extraction of training image library. This paper uses Oxford5K, a commonly used database for target retrieval, as the training image l...

Example Embodiment

[0103] Embodiment 3: The difference between this embodiment and the second embodiment is that the following steps are used to measure the similarity:

[0104] The similarity between the query image q and any image d in the image library can be measured by the query likelihood p(q|d), then:

[0105] p ( q | d ) = Π i = 1 M q p ( q i | d ) - - - ( 14 )

[0106] Turn it into a risk minimization problem, that is, given the query image q, the risk function of the returned image d is defined as follows:

[0107]

[0108]

[0109] p(θ D |d)p(r|θ Q ,θ D )dθ Q dθ D

[0110] Where a=d means that the returned image is d, The set of images returned from the search results in the database, r represents the similarity between the query image q and the image d, θ D Represents the language model of d, L is the loss function, which can be determined by θ Q ,θ D K-L divergence calculation between, then the risk function R can be trans...

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 a target retrieval method based on a group of randomized visual vocabularies and context semantic information. The target retrieval method includes the following steps of clustering local features of a training image library by an exact Euclidean locality sensitive hash function to obtain a group of dynamically scalable randomized visual vocabularies; selecting an inquired image, bordering an target area with a rectangular frame, extracting SIFT (scale invariant feature transform) features of the inquired image and an image database, and subjecting the SIFT features to S<2>LSH (exact Euclidean locality sensitive hashing) mapping to realize the matching between feature points and the visual vocabularies; utilizing the inquired target area and definition of peripheral vision units to calculate a retrieval score of each visual vocabulary in the inquired image and construct an target model with target context semantic information on the basis of a linguistic model; storing a feature vector of the image library to be an index document, and measuring similarity of a linguistic model of the target and a linguistic model of any image in the image library by introducing a K-L divergence to the index document and obtaining a retrieval result.

Description

technical field [0001] The invention relates to a target retrieval method based on a randomized visual dictionary group and contextual semantic information. Background technique [0002] In recent years, with the rapid development and application of computer vision, especially image local features (such as SIFT) and visual dictionary method (BoVW, Bag of Visual Words), the target retrieval technology has become more and more practical, and has been obtained in real-life products. widely used. For example, Tineye is a network-oriented near-duplicate image retrieval system, and Google Goggles allows users to use mobile phones to take pictures and retrieve information related to the objects contained in the pictures. The BoVW method is inspired by the word set method in the field of text retrieval. Due to its outstanding performance, the BoVW method has become the mainstream method in the field of target retrieval, but it also has some open problems. One is the low time effic...

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): G06F17/30G06K9/62
CPCH04L9/3236
Inventor 赵永威李弼程高毫林蔺博宇
Owner THE PLA INFORMATION ENG UNIV
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap