Skip to content

LiaoLIDIP/NewROC

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

NewROC

本函数由于图像中目标检测算法的评价,依据的是ROC曲线
本函数可以绘制ROC曲线,并计算相应的评价指标,如auc, sensitivity, specificity


example:

threshold=0:0.01:1;
groundtruth = imread('manual.tif');
groundtruth = double(groundtruth)/255;
detecResoult = imread('detec.png');
detecResoult = double(detecResoult)/255;
[auc, IoU, acc, se, sp, pr, MedNR] = newroc(groundtruth, detecResoult, threshold);

Note:

   1.本函数用到gpu进行加速
   2.目标检测的评价参数不局限于当前这几种,你可根据需要自行增减

Reference:

Kumar R, Indrayan A. Receiver operating characteristic (ROC) curve for medical researchers[J]. Indian pediatrics, 2011, 48(4): 277-287.


Auther: LIAO.L
IDIPLAB·UESCT


About

绘制图像目标检测ROC曲线并计算相应评价指标

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages