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

A Method for Optimizing Control Parameters in Image Processing and Vision Algorithms

A technology for controlling parameters and image processing, applied in the direction of genetic models, etc., can solve problems such as good parameter values ​​and satisfactory results, adjustment methods are not guaranteed, waste of time and energy, etc., to save time, labor and cost, save costs, and be applicable broad effect

Active Publication Date: 2016-02-24
深圳市康鸿泰科技有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The adjustment method in the prior art has no guarantee mechanism, and there are blindness and result uncertainty, so many attempts are wasted time and energy, and cannot guarantee to obtain good parameter values ​​and satisfactory results

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 for Optimizing Control Parameters in Image Processing and Vision Algorithms
  • A Method for Optimizing Control Parameters in Image Processing and Vision Algorithms
  • A Method for Optimizing Control Parameters in Image Processing and Vision Algorithms

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In order to make the object, technical solution and advantages of the present invention clearer, the implementation manner of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0031] In this method, an example that needs to adjust the value of the control parameter --- StorySegmentation is taken as an example to illustrate. The news story segmentation technology has three important control parameters, namely SentenceLength, Cutoff and Scale. The quality of these control parameter values ​​has a great influence on the news story segmentation results (the quality of the segmentation effect is represented by the commonly used standard F-measure value in the field of information retrieval). The purpose of news story segmentation is to divide text, audio or video streams into a series of blocks with consistent themes. These blocks are called stories (Stories), which mainly focus on the establishment of topic model...

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 a method for optimizing a control parameter in an image processing and vision algorithm. The method comprises the following steps that: an outer-layer control process intelligently adjusts an inner-layer optimization process; the inner-layer optimization process searches for an optimal value of a general control parameter, and a control coefficient thereof is used as an individual of an outer-layer control process population; the proposed innovation mechanism solves the problem in the algorithm control parameter setting in the field of visual media calculation, intelligently adjusts a general parameter setting process, does not need artificial interaction and saves time and labor; a user is allowed to input a group of control parameter values for manual adjustment, intelligent optimization search is performed on the basis, and a group of preferable control parameter values is obtained; and the method has wide applicability and can solve many similar problems. The parameter setting of a news story division technology indicates that the method obtains more accurate control parameter values than manual adjustment, successfully solves the problem in algorithm control parameter setting, saves time and labor and realizes high precision.

Description

technical field [0001] The invention relates to the field of visual media computing, in particular to a method for optimizing control parameters in image processing and visual algorithms. Background technique [0002] In the field of image processing and vision in the field of visual media computing (for example: news story segmentation, image and video segmentation, target recognition, target detection and extraction, etc.), many technologies will have several control parameters that determine the quality of the results. These Control parameters need to be given an initial value before the program runs or give control parameter values ​​interactively. The values ​​of these control parameters mentioned above greatly affect the results; that is, inappropriate control parameter values ​​will lead to poor results; conversely, better control parameter values ​​will produce good results. [0003] In the prior art, these control parameters are usually adjusted by manual experienc...

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): G06N3/12
Inventor 冯伟万亮尹雪飞
Owner 深圳市康鸿泰科技有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com