Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Object-level depth feature aggregation method for image retrieval

A deep feature, image retrieval technology, applied in special data processing applications, instruments, electrical digital data processing and other directions, can solve the problems of redundancy, lost information, noise and other problems in the aggregation process, to reduce complexity, improve accuracy, high The effect of robustness

Inactive Publication Date: 2017-05-10
DALIAN UNIV OF TECH
View PDF3 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although these methods take into account the local information of the image, making the feature more robust to various changes than the global method, there are still some defects in these methods.
For example, use the sliding window method to obtain the image area (refer to the article "Multi-scale orderless pooling of deep convolutional activation features" published by Yunchao Gong, Liwei Wang, Ruiqi Guo, and Svetlana Lazebnik on pages 392-407 of the European Conference on Computer Vision 2014 ), because the color, texture, edge and other visual content of the image are not considered, a large number of regions with no semantic meaning are generated, which brings redundancy and noise information to the subsequent aggregation process
In addition, the maximum pooling algorithm commonly used in regional feature fusion (refer to the article "Objectlevel deep feature pooling for compact image representation"), because only the maximum response of the feature is retained without considering the correlation between features, a large amount of information is lost, and the discrimination of the final image features obtained is reduced

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
  • Object-level depth feature aggregation method for image retrieval
  • Object-level depth feature aggregation method for image retrieval
  • Object-level depth feature aggregation method for image retrieval

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0023] Example 1: Retrieval of similar images

[0024] 1. figure 1 It is a flow chart of the present invention. Firstly, all images in the library image are extracted using the fast mode of the Selective Search algorithm to extract candidate areas. On average, about 2000 candidate areas of different sizes can be obtained for each image.

[0025] 2. The present invention adopts the convolutional neural network structure Alex network of Krizhevsky et al. The input is an RGB image of 224*224, including five layers of convolution layers, three layers of maximum pooling layers and three layers of fully connected layers. The network is trained using the Caffe framework, and the training data is the 1000-class classification data set in the ILSVRC12 competition.

[0026] 3. After the network training is completed, the candidate area obtained in step 1 is filled and scaled to a fixed size of 224*224 as the input of the network, and the output of the fully connected layer fc7 is extra...

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 field of digit media and provides an object-level depth feature aggregation method for image retrieval. First, an unsupervised method is used to generate candidate regions that may contain objects; then corresponding convolution neural network characteristics are extracted; finally, the area features are aggregated to obtain image feature representation having high robustness for image transformation for the use of image retrieval applications. The present invention addresses the lack of geometric transformation and spatial layout invariance of existing models, and the object-based mode is adopted to solve the problems in the prior art; the image features generated by the method have high robustness on image geometric transformation and spatial arrangement transformation; the accuracy of image retrieval is increased; the obtain image is quit compact and concise so that complexity of similarity calculation among images is reduced and retrieval efficiency is increased.

Description

technical field [0001] The invention belongs to the field of digital media, and relates to an image retrieval-oriented object-level deep feature aggregation method. Background technique [0002] Content-based image retrieval, as an important research problem in the field of computer vision, has received extensive attention from domestic and foreign scholars in the past decade. Content-based image retrieval refers to finding images similar to the query image from the image database. Due to different factors such as angles, distances, and environments when shooting, similar or identical subjects will have great changes in different images, such as changes in scale, perspective, and layout. Therefore, generating an image feature that is highly robust to various image variations is the key to solving image retrieval problems. [0003] Compared with traditional image features based on artificial design, learning-based methods, especially convolutional neural networks, have show...

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): G06F17/30G06K9/62
CPCG06F16/583G06F18/23213G06F18/24
Inventor 李豪杰暴雨樊鑫罗钟铉
Owner DALIAN UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products