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

A method for measuring characterization methods

A feature description, feature vector technology, applied in the direction of instruments, character and pattern recognition, computer parts, etc., can solve the problem of deviation and influence of calculation results

Active Publication Date: 2017-12-08
THE SECOND RES INST OF CIVIL AVIATION ADMINISTRATION OF CHINA
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, such a measurement method will be affected by the upper-level recognition model, and its calculation results are biased.

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 measuring characterization methods
  • A method for measuring characterization methods
  • A method for measuring characterization methods

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] Step 1: Sampling is uniformly distributed through the sampling window for all marked areas of the positive sample image; uniformly distributed sampling is performed for the image of the negative sample through the sampling window;

[0032] Step 2: Using the feature description method to be measured, convert all sampling windows of all identified regions of the positive sample image and all sampling windows of the negative sample image into positive feature vectors F P ={α 1 ,α 2 ...α A} and the negative eigenvector F N ={β1 ,β 2 ...β B}, the numbers of which are denoted as A and B respectively;

[0033] Step 3: Use a cluster analysis method to divide the positive eigenvectors into K clusters {w 1 ,w 2 ...w K}, w in each cluster k Call it a common descriptor, 1≤k≤K, each common descriptor w k are n positive eigenvectors α i set of w k is F P A subset of n≤A, 10≤K≤1000; if the number of feature vectors contained in a common descriptor is n≤X, delete the commo...

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 the field of object detection and recognition in the field of image recognition, in particular to a method for measuring a feature description method. Aiming at the problems existing in the prior art, the present invention provides a method for measuring feature description methods, quantitatively compares multiple feature description methods, and selects the best feature description method. The present invention samples the positive and negative samples of the object to be identified, and uses the feature description method to be measured to convert the positive and negative samples into a positive and negative feature description vector, and then uses a cluster analysis method to describe the repeatability of the positive-positive feature vector, and the positive-positive feature description vector. The discriminability of negative feature vectors is quantitatively calculated, so as to quantitatively evaluate the performance of the feature description method to be measured for detection and recognition of the object to be recognized.

Description

technical field [0001] The invention relates to the field of object detection and recognition in the field of image recognition, in particular to a method for measuring a feature description method. Background technique [0002] In the field of object image detection and recognition, the current research hotspot is generic object (Generic ObjectCategory) detection and recognition. Generic objects refer to a class of objects, and there are commonality and individuality between individuals in the same object, such as airplanes, apples, and people. Generic objects are for specific objects. A specific object refers to a particular individual, or a group of people with exactly the same appearance, such as the Eiffel Tower, my bicycle, and a brand new iphone6. compared to specific object detection. [0003] The difficulty of detecting and identifying generic objects is significantly greater than that of specific objects. First of all, the number of individuals contained in a c...

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): G06K9/46G06K9/62
CPCG06V10/48G06F18/23
Inventor 隋运峰钟琦李华琼鄢丹青张中仅
Owner THE SECOND RES INST OF CIVIL AVIATION ADMINISTRATION OF CHINA
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