RAP3DF V2
Description
This database contains facial images of volunteers in frontal and random poses. Each facial image collection has a visible light image, an infrared image and a depth image. Version 02 The images in this database version were collected by a single person during the period of December 17 2018 to 01 July of the year 2019 at Univali University. This dataset was created with the approval of CEP (Research Ethics Committee) from University of Itajaí Valley - Brazil with CAAE (Certificate of Presentation of Ethical Appreciation) number: 97615018.9.0000.012. The V2 database contains: 80 volunteers 1600 facial image samples (approximately) a frontal image (VIS, IR, DEPTH) by volunteer an image (VIS, IR, DEPTH) with a face turned to the right by a volunteer an image (VIS, IR, DEPTH) with a face turned to the left by a volunteer an image (VIS, IR, DEPTH) with a face turned up by a volunteer an image (VIS, IR, DEPTH) with a face turned down by a volunteer an image (VIS, IR, DEPTH) with random pose by volunteer Version 01 The images in this database version were collected by a single person during the period of October 10 to 27 of the year 2017. 8 classes in the computer science course at UNIVALI University were invited to participate in this paper, where 64 accepted to participate in this work. The V1 database contains: 64 volunteers 267 facial image samples 267 facial images of the visible light spectrum 267 facial images of the infrared spectrum (corrupted) 267 depth images (3D)
Files
Steps to reproduce
Each folder identifies a database user. Version 02 Open the folder and file rgb_.bmp to view the visible light image. Open the folder and file ir_.bmp to view the image with the infrared image. Open the folder and the depth_.bmp file to view the depth image. Open the folder and the depth_.data file with Kinect One raw data. The database.json file contains the description of the all faces directions. Version 01 Open the folder and file k1_box_xy.bmp to view the visible light image. Open the folder and file k1_box_xy_ir_view.bmp to view the image with the infrared image. Open the folder and the k1_box_xyz_depth_view.bmp file to view the depth image. These 3 images represent the frontal image of the volunteer. Open the tests subfolder to view the images in random positions. The database.csv file contains the description of the facial expression of the random sample.