The Biometric Research Centre (UGC/CRC) at The Hong Kong Polytechnic University has developed a real time NIR face capture device (show in Figure 1), and has used it to construct a large-scale NIR face database. To advance research and to provide researchers working in the area of face recognition with an opportunity to compare the effectiveness of face recognition algorithms, we intend to publish our NIR face database, making it freely available for academic, noncommercial uses.
The hardware of our NIR face image
acquisition system consists of a camera, an LED (light emitting diode) light
source, a filter, a frame grabber card and a computer. A snapshot of the
constructed imaging system is shown in Fig. 1. The camera used is a JAI camera,
which is sensitive to NIR band. The active light source is in the NIR spectrum
between 780nm - 1,100 nm and it is mounted on the camera. The peak wavelength
is 850nm, and it lies in the invisible and reflective light range of the
electromagnetic spectrum. An NIR LED array is used as the active radiation
sources, and it is strong enough for indoor use. The LEDs are arranged in a
circle and they are mounted on the camera to make the illumination on the face
is as homogeneous as possible. The strength of the total LED lighting is
adjusted to ensure a good quality of the NIR face images when the camera face
distance is between
Fig. 1: The NIR face image acquisition device. ‘A’ is the NIR LED light source, and ‘B’ is the NIR sensitive camera with an NIR filter.
By using the self-designed data
acquisition device described above, we collected NIR face images from 335
subjects (Due to some missing data, here we only release 335 subjects instead
of 350 referred in our paper). During the recording, the subject was first
asked to sit in front of the camera, and the normal frontal face images of
him/her were collected. Then the subject was asked to make expression and pose
changes and the corresponding images were collected. To collect face images
with scale variations, we asked the subjects to move near to or away from the
camera in a certain range. At last, to collect face images with time
variations, samples from 15 subjects were collected at two different times with
an interval of more than two months. In each recording, we collected about 100
images from each subject, and in total about 34,000 images were collected in
the PolyU-NIRFD database. The sample images in the PolyU-NIRFD are labeled as
‘NN_xxxxxx_S_D_****’, where “NN” represents the prefix of the label string, ‘S’
represents the Gender information, ‘xxxxxx’ indicates the ID serial number of
the subject, ‘D’ denotes the place where the image was captured, and ‘****’ is
the index of the face image. For example, “NN_200001_F_B_
Fig. 2: Sample NIR face images of a subject. (a) Normal face image; and images with (b) expression variation; (c) pose variation and (d) scaling variation.
Fig. 3: Sample NIR face images captured in more than two months.
1. Baochang Zhang, Lei Zhang, David Zhang, and Linlin Shen, “Directional Binary Code with Application to PolyU Near-Infrared Face Database”, Pattern Recognition Letters, vol. 31, issue 14, pp. 2337-2344, Oct. 2010.
The Announcement of the Copyright
All rights of the PolyU-NIRFD are reserved. The database is only available for research and noncommercial purposes. Commercial distribution or any act related to commercial use of this database is strictly prohibited. A clear acknowledgement should be made for any public work based on the PolyU-NIRFD. A citation to “PolyU-NIRFD, http://www.comp.polyu.edu.hk/~biometrics/polyudb_face.htm” and our related works must be added in the references. A soft copy of any released or public documents that use the PolyU-NIRFD must be forwarded to: firstname.lastname@example.org
Download ZIP to your local disk (Due to the large size of data, we have divided it into 6 parts). Then, fill in the application forms. Send the application form to email@example.com. The successful applicants will receive the passwords for unzipping the files downloaded.
Here we also provide the training, gallery, probe subsets which were used in our paper “Directional Binary Code with Application to PolyU Near-Infrared Face Database” (including the Experiments 1,2,3) for your reference and comparison.
Experiment Subset (64M)
Copyright © 2010
Biometric Research Centre, The