CISLR1:Competition on Indian Sign Language Recognition
 |
Sign language is the only means of communication for speech and hearing impaired people. Using machine translation, Sign Language Recognition (SLR) systems provide medium of communication between speech and hearing impaired and others who have difficulty in understanding such languages. |
|---|---|
|
Dataset: 10 User, per user 9 samples (3 sample per direction) for all 30 activities.
Thus, total 10* 9* 30= 2700 samples are given in the dataset.
Each data file is named as X_Y_Z.txt, where X is sign gesture, Y is subject performed sign X. Z={1,2,3}(Front View), {4,5,6}(Side View 1), {7,8,9}(Side View 2).
Test Protocol 1 (User Independent): Training: 6 Users i.e. 6*9*30=1620 samples (Users other than in validation and in testing to be used in training). Validation: 2 Users (apurve,shewta) Testing: 2 Users (prateek, rajkumar) Test Protocol 2 (User Dependent): Training: Front View Validation: Side View 1 Testing: Side View 2 Dataset can be downloaded here. More information could be found here. | |
Note: Please send your codes with proper documentations and operating procedures to wcvip2018[at]iitr[dot]ac[dot]in. Submission will be closed on Feb 28, 2018, 5:00 PM. Only one submission is allowed per team, in case of multiple submissions only first will be evaluated. Top scorer shall be awarded if they register for WCVIP 2018 which will be organized during March 9-11, 2018 at IIT Roorkee, Uttarakhand, India.