DCTmod2 features computed from 64x80 faces extracted using: manually annotated eye coordinates download here (67 Mb), automatically localized using IDIAP frontal face detector (download here (67 Mb)), automatically localized using Tim Cootes AAM (download here (67 Mb)).
![]() The 3D Face Database ![]() Currently, little three-dimensional face data is publicly available and nothing towards the magnitude of data that we require for development and testing of our recognition systems.Therefore, we began populating our own 3D face database.Ten facial surfaces of 97 different people were captured, under the conditions shown below.
During capture, no effort was made to control the lighting conditions.In order to capture facial surfaces at various head orientations, the subjects are asked to face towards reference points positioned roughly at 45 degrees to the left, right, above and below the camera, but no effort was made to enforce a precise angle of orientation.Examples of the 10 models captured for each person are shown below. The 3D Face Database - Stage 2 CompleteThe second stage in our research required the expansion of our current 3D face data to include a much larger test set. This has now been completed with the help of several departments at the University of York, together with external collaboration of Cybula Ltd. The database has now been populated with facial models captured under a much wider variety of conditions. This new database is intended to provided a platform for testing 3D face recognition systems on a scale to match those carried out on the 2D FERET (Face Recognition Technology) database in the FRVT (Face Recognition Vendor Tests). The table below shows the capture conditions for each subject in the database.
The database currently consists of over 5000 3D face models of approximately 350 people (15 models each). Some snap-shot examples of these 3D models are shown below.
Acquiring the UOY 3D Face DatabaseTo enquire about use of the UOY 3D Face Database click: UoY 3D Face Database enquiry . This directs your email to the appropriate staff at Cybula Ltd.
3D Face Recognition - Graph Matcher (login required)
Database description:
The very first step in many facial analysis systems is face detection. Though face detection has been studied for many years, there is not still a benchmark public database to be widely accepted among researchers for which both color and depth information are obtained by the same sensor. Most of the available 3d databases have already automatically or manually detected the face images and they are therefore mostly used for face recognition not detection. This paper purposes an RGB-D database containing 1581 images (and their depth counterparts) taken from 31 persons in 17 different poses and facial expressions using a Kinect device. The faces in the images are not extracted neither in the RGB images nor in the depth hereof, therefore they can be used for both detection and recognition. The proposed database has been used in a face detection algorithm which is based on the depth information of the images. The challenges and merits of the database have been highlighted through experimental results.
Citation:
If you use this database, please cite the following paper: R.I. Høg, P. Jasek, C. Rofidal, K. Nasrollahi, and T.B. Moeslund, “An RGB-D Database Using Microsoft’s Kinect for Windows for Face Detection,” The IEEE 8th International Conference on Signal Image Technology & Internet Based Systems, Italy, 2012.
Data set:
A readme file describing the data set can be found here.
Images can be downloaded from the following links:
(2012-05-16)(151751).zip (2012-05-16)(153054).zip (2012-05-16)(154211).zip (2012-05-16)(160440).zip (2012-05-16)(160931).zip (2012-05-16)(161342).zip (2012-05-16)(163349).zip (2012-05-16)(164248).zip (2012-05-17)(141550).zip (2012-05-17)(142154).zip (2012-05-17)(142457).zip (2012-05-17)(143016).zip (2012-05-18)(132824).zip (2012-05-18)(133201).zip (2012-05-18)(133846).zip (2012-05-18)(134239).zip (2012-05-18)(134757).zip (2012-05-18)(140516).zip (2012-05-18)(143345).zip (2012-05-18)(144316).zip (2012-05-18)(145150).zip (2012-05-18)(145623).zip (2012-05-18)(150303).zip (2012-05-18)(150650).zip (2012-05-18)(151337).zip (2012-05-18)(151650).zip (2012-05-18)(152717).zip (2012-05-18)(153532).zip (2012-05-18)(154129).zip (2012-05-18)(154728).zip (2012-05-18)(155357).zip ![]() Comments are closed.
|
AuthorWrite something about yourself. No need to be fancy, just an overview. Archives
March 2023
Categories |