OpenCV
4.0.0
Open Source Computer Vision
|
Classes | |
class | cv::datasets::FR_adience |
struct | cv::datasets::FR_adienceObj |
class | cv::datasets::FR_lfw |
struct | cv::datasets::FR_lfwObj |
Enumerations | |
enum | cv::datasets::genderType { cv::datasets::male = 0, cv::datasets::female, cv::datasets::none } |
Implements loading dataset:
"Adience": http://www.openu.ac.il/home/hassner/Adience/data.html
Usage:
faces.tar.gz\aligned.tar.gz
and files with splits: fold_0_data.txt-fold_4_data.txt
, fold_frontal_0_data.txt-fold_frontal_4_data.txt
. (For face recognition task another splits should be created)Implements loading dataset:
"Labeled Faces in the Wild": http://vis-www.cs.umass.edu/lfw/
Usage:
lfw.tgz\lfwa.tar.gz\lfw-deepfunneled.tgz\lfw-funneled.tgz
and files with pairs: 10 test splits: pairs.txt
and developer train split: pairsDevTrain.txt
.pairs.txt
and pairsDevTrain.txt
in created folder.For this dataset was implemented benchmark with accuracy: 0.623833 +- 0.005223 (train split: pairsDevTrain.txt
, dataset: lfwa)
To run this benchmark execute: