Image processing method and device

An image processing and image technology, applied in the field of image processing, can solve problems such as inaccurate comparison results

Active Publication Date: 2015-11-25
HUAWEI TECH CO LTD
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Embodiments of the present invention provide an image processing method and device to

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 processing method and device
  • Image processing method and device
  • Image processing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] In order to solve the problem of inaccurate comparison results when comparing objects in different images. In the embodiment of the present invention, the obtained first image matrix corresponding to the first target object and the second image matrix corresponding to the second target object are respectively subjected to convolution operation and block aggregation processing to generate the underlying feature matrix of the first image , and the underlying feature matrix of the second image; the underlying feature matrix of the first image is compared with the underlying feature matrix of the second image to generate a contrast matrix; The result after block aggregation processing is compared whether the first target object and the second target object are the same object. By adopting the technical solution of the present invention, the image matrix corresponding to the target object is input into the filter pair neural network of deep learning, and the comparison resul...

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 processing method and device. The method comprises respectively performing convolution operation and block aggregation processing on an obtained first image matrix corresponding to a first target object and an obtained second image matrix corresponding to a second target object, obtaining a first image bottom layer characteristic matrix and a second image bottom layer characteristic matrix, comparing the first image bottom layer characteristic matrix with the second image bottom layer characteristic matrix to generate a comparison matrix, and, after packet aggregation processing, convolution operation and block aggregation processing are successively performed on the comparison matrix, comparing whether the first target object and the second target object is the same object according to a result after the block aggregation processing. Through adoption of the technical scheme of the invention, the image matrixes corresponding to the target objects are input to deep-learning filter pair neural network, a compared result is obtained based on image characteristics corresponding to the target objects and a deep leaning strategy, and accuracy of the compared result is effectively improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image processing method and device. Background technique [0002] With the rapid development of science and technology, cameras are widely used in various fields for monitoring specific scenes and retrieving target persons. [0003] Comparing the images collected by multiple cameras can obtain the information of the target object at a certain place at a certain time, which is helpful for tracking the target object. Because the imaging of the same object in different cameras will be very different, these differences include differences caused by shooting angles, target object poses, light intensity and background objects, etc., see figure 1 As shown in , it shows the imaging difference of a target object under different cameras. Therefore, how to use a machine to recognize whether multiple target objects in images collected by different cameras are the same t...

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): G06K9/66G06T5/00G06N3/02
Inventor 王晓刚赵瑞肖桐黎伟许春景
Owner HUAWEI 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
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