Welcome to
RPI Intelligent Systems Lab (ISL) Image Databases
Overview of RPI
ISL Image Databases
The
goal of the ISL Image Databases is to share image data sets with researchers
around the world. The ISL image databases consist of four major parts: medical
image databases, fatigue image databases, face and eye databases, and facial
expression databases.
The RPI ISL Image
Databases
A.
Face and Eye Databases
1.
Unprocessed
images
This database contains the
unprocessed images from different sources.
o ISL WebImage Database
(442M)
This database is collected
from website by our own research group. It can be used in many applications such
as face detection, eye detection, and face pose
estimation.
o
ISL Face Database
This database is created by
our own research group. It consists of video sequences and static images. It can
be used in many applications such as face and eye detection, face tracking, face
pose estimation, and face recognition.
o
ISL Eye Image
Database
This database is
constructed by our own research group. It consists of image sequences taken
under IR cameras. Each image sequence is decomposed into dark pupil image
sequence and its corresponding bright pupil image sequence. This database is
primarily used in eye detection and tracking.
o
Face
Databases from Other Research Groups
o
Eye
Databases from Other Research Groups
2. Training Image
Databases
The training image
databases contain the cropped image region of interest (ROI) for training
various classifiers including eye, eye corner, and face.
B.
Facial Expression databases
o
ISL
Facial Expression Databases
This database is collected
by our own research group. It is primarily used for facial action unit
recognition. It consists of two subsets: frontal-view facial expression database
and multi-view facial expression database.
o
ISL
Enhanced Cohn-Kanade AU-coded Facial Expression Database
Our research group has
manually created more groundtruth data for Cohn-Kanade AU-coded facial
expression database including the frame-by-frame AU labeling and coordinates of
34 facial feature points.
C. Human Fatigue Database
This database consists of
face and eye images for human subjects under different fatigue
states
D. Medical Image
Databases
(Partially available)
This database consists of
medical images for microtubule segmentation, membrane segmentation, and
C-elegans (nematode worms) segmentation.
Others' Image
Databases
o
Face
Databases from Other Research Groups
o
Eye
Databases from Other Research Groups
o Facial Expression Databases from Other Research Groups
How to get a copy of ISL Database.
The RPI ISL databases are publicly available for non-commercial use. Any commercial distribution or any act related to commercial use of this database is strictly prohibited. Follow the following steps to get access to RPI ISL databases:
Step 1. Select Database.
Each
database includes several sub-databases for different use. Please read the
descriptions carefully and select the databases you may be interested.
(Note:Only databases with
are available now. )
Step 2. Download and sign the license.
If you are working on a research project, please ask the Principal Investigator of the project to sign the license agreement form.
Step 3. Contact us.
The contact information is as follows. Please send us an email and also fax the signed license agreement to us.
Step 4. Upload Data.
Currently, our department restricts the network connection so that we cannot set up a server for you to download the database. You need to set up a server for us to upload the databases. Sorry for any inconvenience.
Contact Information
Please contact Professor
Qiang Ji (qji@ecse.rpi.edu), if you are
interested in getting a copy of the databases.
 Image Databases_files/meter.gif)