Image searching method and device

An image search and image technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problems of large amount of data calculation, inability to satisfy local search, and affect search speed, so as to improve search speed and meet search requirements. The demand for local areas of the image, the effect of reducing the range

Inactive Publication Date: 2017-09-08
SHENZHEN ZTE NETVIEW TECH
View PDF4 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since it is necessary to compare the image features of the entire input image with the image features of each image in the image database, the amount of data calculation is very large, which affects the search speed
A

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 searching method and device
  • Image searching method and device
  • Image searching method and device

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0042] see figure 1 , propose the first embodiment of the image search method of the present invention, the method includes the following steps:

[0043] S11. Extract and store the features of each image in the image database.

[0044] In this embodiment, the terminal device preprocesses the images in the image database in advance, extracts and stores the features of each image in the image database, and can directly read the features and features stored in the image database when performing subsequent image searches. The features of the input images are compared, which saves the step of extracting the features of each image in the image database in real time, thereby improving the search speed.

[0045] The extracted features can only include the image features of the image, and can also include the color features and image features of the image, wherein the image features include gradient direction histogram (Histogram of Oriented Gradients, referred to as HOG) features, lo...

no. 2 example

[0120] see Figure 5 , propose the second embodiment of the image search method of the present invention, the method includes the following steps:

[0121] S21. Extract and store the features of each image in the image database.

[0122] The features of the image extracted in this embodiment only include image features, including HOG features, LBP features and hash features. The method for extracting image features is the same as step S11 in the first embodiment, and will not be repeated here.

[0123] S22. Acquire at least one target area selected by the user on the input image.

[0124] Specifically, the user inputs an image to the terminal device, and selects a local area on the input image as a target area, and the terminal device acquires the target area selected by the user on the input image. According to needs, the user can select one target area on the input image, or select two or more target areas. The target area is usually an area that can represent the main f...

no. 3 example

[0134] see Figure 6 , propose the third embodiment of the image search method of the present invention, the method includes the following steps:

[0135] S31. Acquire at least one target area selected by a user on an input image.

[0136] Specifically, the user inputs an image to the terminal device, and selects a local area on the input image as a target area, and the terminal device acquires the target area selected by the user on the input image. According to needs, the user can select one target area on the input image, or select two or more target areas. The target area is usually an area that can represent the main features of the image, or an area that needs to be searched locally.

[0137] Taking the vehicle image as an example, the user can select the license plate area, vehicle logo area, annual inspection sign area, etc. of the vehicle image as the target area.

[0138] S32. Extracting image features of the target area.

[0139] The image features of the target...

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 discloses an image searching method and device. The method comprises steps of acquiring at least one target area selected from an input image by the user, extracting image features of the target area, searching an image database according to the image features of the target area, acquiring an image of an area matched with the image features of the target area and designating the image as a search result. The image searching method provided allows a user to select a local area on the image during image searching, and retrieve an image database according to features of the local area to acquire a searching result, so comparison is only required between the features of the local area and image features of the image database; data computation amount can be improved; besides, an image local search function can be achieved; and a demand for user searching image local areas can be met.

Description

technical field [0001] The invention relates to the technical field of video surveillance, in particular to an image search method and device. Background technique [0002] With the development of society and the advancement of science and technology, the construction scope of image monitoring (including highway image monitoring) system is expanding day by day, and the density of control points is increasing day by day. Numerous monitoring devices have recorded massive pictures and video data in real time. These massive data are both It provides clues for the detection of the case, but it also increases the difficulty for the investigators to obtain useful information from it. If images can be quickly and accurately searched in massive data, the efficiency of case handling will undoubtedly be greatly improved. [0003] The image search scheme in the prior art mainly includes the following steps: first input an image, then extract the image features of the entire input image,...

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): G06F17/30
CPCG06F16/7837
Inventor 李平生山黎余登超张占华常爱平
Owner SHENZHEN ZTE NETVIEW TECH
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