A method and apparatus for image processing

An image processing device and an image processing technology, applied in the field of image processing, can solve the problem that the detection efficiency and detection accuracy cannot be guaranteed at the same time.

Inactive Publication Date: 2019-02-05
HUAWEI TECH CO LTD
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] This application provides an image processing method and equipment to solve the problem in the prior art that the number of target candidate frames screened out in the target detection process is fixed so that the detection efficiency and detection accuracy cannot be guaranteed at the same time during target detection

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
  • A method and apparatus for image processing
  • A method and apparatus for image processing
  • A method and apparatus for image processing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0072]The present application provides an image processing method and device, which is used for the image processing device to select a number from a plurality of target candidate frames in the image to be detected based on the number of targets in the image to be detected, which is related to the number of targets The target candidate frame, so that the number of target candidate frames selected for different images is more suitable, so that in the process of target image detection, the problem of low detection efficiency caused by too much calculation can be avoided, and the detection result can be improved. More accurate.

[0073] First of all, some terms used in this application are explained in order to make those skilled in the art understand.

[0074] 1. The basic feature image, the image to be detected is processed to obtain the basic features of each pixel in the image, the image composed of the basic features of all pixels is the basic feature image, and the value of...

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 an image processing method and a device, which are used for solving the problem that the number of target candidate frames selected in the target detection process in the prior art is fixed so that the detection efficiency and the detection accuracy can not be guaranteed at the same time when the target is detected. In accordance with an embodiment of that present invention, A device determines a target number of images to be detected based on the images to be detected, and selecting target candidate frames related to the number of targets from a plurality of target candidate frames of the image to be detected, So that the number of target candidate frames selected for different images is more suitable, so that the problem of low detection efficiency caused by toomuch computation can be avoided in the target image detection process, and the detection result can be more accurate.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular to an image processing method and device. Background technique [0002] For a given image, it is often necessary to mark or extract the target that the user cares about in the image. This process is called target detection, which can also be called target extraction; target detection is an image segmentation technology based on the geometric and statistical characteristics of the target. , object detection involves the recognition of objects in images and image segmentation, and the accuracy and efficiency of object detection are two important indicators for evaluating object detection. [0003] In recent years, object detection has mostly used some object detection algorithms based on deep learning. Most of these deep learning-based target detection algorithms use a cascade architecture, such as Fast-RCNN (fast convolution neural network, fast regional convo...

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): G06N3/04
CPCG06T7/10G06N3/045
Inventor 沈鹏程
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