The Hong Kong Polytechnic University Contact-free 3D/2D Hand Images Database (Ver 1.0)

The hand biometric research has attracted a lot of attention from the researchers and generated tons of papers and technical reports. In order to promote the development of more user-friendly and reliable hand identification, The Hong Kong Polytechnic University has been collecting contact-free 3D hand scans with the objective to establish large scale hand image database acquired using completely contact-free imaging setup and make it freely available to the researchers. Currently, there is no database of contact-free 3D hand scans in the public domain. This database includes textured  3D scans of the inner surface (palm-side) of the hand, which can be utilized to advance research efforts in the area of hand geometry, 2D palmprint recognition, as well as 3D palmprint recognition.

Brief Description

The 3D hand images in the database were acquired using a commercially available 3D digitizer— Minolta VIVID 910. The data collection process spanned over 4 months and 177 subjects volunteered for the database. The participants were mainly the students and staff from our institute and were in the age range of 18 – 50 years, with multiple ethnic backgrounds. Each subject contributed 5 hand images (range and a registered intensity image acquired simultaneously) in the first session, followed by another 5 in the second session. Therefore our database currently has 3,540 hand images (of 3D and corresponding 2D). Time lapse between two data collection sessions was not fixed for all subjects; instead it ranged from a minimum of one week (only for 27 subjects) to three months. All the hand images were collected in indoor environment, with no restrictions on the surrounding illumination. In fact, our data collection process was carried out at three different locations which had notable variations in surrounding illuminations. During the image acquisition, every user is expected to hold his/her right hand in front of the scanner at a distance of about 0.7 m, empirically chosen to maximize the relative size of the hand in the acquired image frame.  No constraints were employed to confine the position of the hand nor were the users instructed to remove any hand jewelry that they were wearing. However, in order to simplify the hand segmentation task, the background behind the user’s hand was ensured to be of black color. Users were only requested to hold their hand with their palm approximately parallel to the image plane of the scanner and inside the imaging area. This task was facilitated by providing the users a live visual feedback for positioning of the hand. In order to introduce variations in the database, users were asked to change their hand position after the acquisition of every image. The acquired images have been sequentially numbered for every user with an integer identification/number. The resolution of these images (3D as well as 2D) is 640 ´ 480 pixels.

Sample Images

The entire database is being made available as it was acquired. The sample images from this database are reproduced in the following image set.

Range Images (3D)

 

 

 

 

 

 

 

 

 

 

2D Images

 

 

 

 

 

 

 

 

 

Download and Copyright

The database is being made available freely for the researchers from academia and industry. Interested researchers should follow following steps to acquire the 'The Hong Kong Polytechnic University  Contact-free 3D/2D Hand Images Database version 1.0'

    1. Visit the online application link and provide all the details in this application form;

    2. The request confirmation will be sent by email and the applicants can download the database using instructions in the email.

 

All the rights of the 'The Hong Kong Polytechnic University  Contact-free 3D/2D Hand Images Database version 1.0' are reserved and commercial use/distribution of this database is strictly prohibited. All the technical reports and papers that report experimental results from this database should provide due acknowledgement/reference. The reference should appear as 'The Hong Kong Polytechnic University  Contact-free 3D/2D Hand Images Database version 1.0' http://www.comp.polyu.edu.hk/~csajaykr/myhome/database_request/3dhand/Hand3D.htm. Questions regarding this database can be directed to Ajay.Kumar@polyu.edu.hk.

References

[1] V. Kanhangad, A. Kumar, D. Zhang, “A unified framework for contactless hand identification,” IEEE Trans. Information Forensics & Security, vol. 20, no. 5, pp. 1415-1424, May 2011.

Back to Databases Page