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

Image retrieval method and device

An image retrieval and image technology, applied in the field of information retrieval, can solve problems such as inaccurate image features, difficulty reflecting input image features, low image retrieval accuracy, etc., and achieve the effect of improving accuracy

Inactive Publication Date: 2020-12-04
BEIJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the manually acquired image features may be inaccurate, and it is difficult to reflect the features of the input image, making the accuracy of image retrieval 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
  • Image retrieval method and device
  • Image retrieval method and device
  • Image retrieval method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The invention provides an image retrieval method. figure 1 Flowchart of an image retrieval method provided by the present invention Figure 1 . The image retrieval method can be executed by an image retrieval device, and the image retrieval device can be integrated in any device with processing functions, such as a tablet computer, a notebook computer, a desktop computer, a server, etc., through software and / or hardware. Such as figure 1 As shown, the image retrieval method may include:

[0032] S101. Process the input image by using a deep convolutional neural network to obtain image features of the input image.

[0033] Specifically, in S101, the processing function of the deep convolutional neural network may be used to process the pixel data of the input image to obtain image features of the input image. The processing function of the deep convolutional neural network can also be called the model function of the deep convolutional neural network.

[0034] For e...

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 provides an image search method and device. The image search method includes the steps: processing inputted images by the aid of a deep convolutional neural network to obtain image characteristics of the inputted images; processing the image characteristics by the aid of a nonlinear mapping function to obtain hash codes of the inputted images; determining Hamming distances among the inputted images and each image according to the hash codes of the inputted images and a hash code of each image in at least one image; performing sequencing on the images according to the Hamming distances among the inputted images and the image, and taking the sequenced images as image search results. According to the method, image search accuracy can be improved.

Description

technical field [0001] The invention relates to the technical field of information retrieval, in particular to an image retrieval method and device. Background technique [0002] With the explosive growth of image data in the network and users' demand for image-based retrieval, the application of image retrieval technology is becoming more and more extensive. [0003] Image retrieval technology, generally according to the hash code of the input image and the hash code of each image in the at least one image, determine the target image from the at least one image as the image retrieval result. Wherein, the hash code of the input image may be determined according to image features of the input image obtained manually. [0004] However, the manually acquired image features may be inaccurate, and it is difficult to reflect the features of the input image, making the accuracy of image retrieval low. Contents of the invention [0005] The invention provides an image retrieval ...

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): G06F16/532G06F16/58G06N3/04G06N3/02
CPCG06N3/02G06F16/583
Inventor 程祥苏森陈刚
Owner BEIJING UNIV OF POSTS & TELECOMM