Performance Evaluation Method of Scene Matching Algorithm Based on Decision Tree
ZOU Hui
WU Qifeng
ZHANG Yifei
MING Delie
Abstract：Inspired by the research on the analysis of SAR images matching property and infrared image recognition property,it is found that image category has a great effect on image matching,also the image category measured by image feature,the image features including Intensity edge and correlation analysis.Based on the analysis of these characteristics of images,a method of performance evaluation of scene matching algorithm based on CART decision tree is proposed.Finally, decision tree is used to evaluate the performance on two image matching.The results show that the method is effective.
Keywords：scene matchingalgorithm evaluationdecision treeadaptation propertyrecognition ability
Publication Date：2016-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：8( 2103-2109,2117 )