|
|
|
|
The DeitY-TU Face Database contains 49,780 images of 524 subjects collected from five different states of northeastern India (Mizoram, Assam, Tripura, Nagaland, Manipur) i.e. Mongoloid Race with different ethnic background (Meghalayan, Nagamese, Mizo, Arunachali and Manipuri).
Database images are captured with the combined challenges of illumination (4), expression (8), and pose (5). Five different poses are available for each combination of illumination and expression in the database.
Soft biometric features such as moles, scars, and freckles are also present in 126, 39, and 17 individuals’ faces, respectively along with ground truth information.
|
|
| Importance/Utilities of the Dataset: |
The key features of the designed dataset are as follows:
i. Database images are captured with the combined challenges of illumination (4), expression (8), and pose (5). Five different poses are available for each combination of illumination and expression in the database.
ii. Soft biometric features such as moles, scars, and freckles are also present in 126, 39, and 17 individuals’ faces, respectively along with ground truth information.
|
|
Dataset Statistic:
| State |
Total Images |
No. of image per person |
Total Persons |
Male |
Female |
Tribe |
Non-Tribe |
|
| Mizoram |
10,640 |
95 |
112 |
62 |
50 |
112 |
00 |
| Assam |
10,165 |
|
107 |
46 |
61 |
14 |
93 |
| Tripura |
9500 |
|
100 |
49 |
51 |
34 |
66 |
| Nagaland |
9595 |
|
101 |
57 |
44 |
101 |
00 |
| Manipur |
9890 |
|
104 |
80 |
24 |
29 |
75 |
|
| Total |
49,780 |
95 |
524 |
294 |
230 |
290 |
234 |
|
|
| Year of Developed of Dataset: |
2014 |
|
| Dataset Releasing Year: |
Permission pending from funding agency
|
|
| Size of Dataset: |
N/A
|
|
| Publications: |
[1] Priya Saha, Mrinal Kanti Bhowmik, Debotosh Bhattacharjee, Barin Kumar De, “Expression Recognition of North-East Indian (NEI) Faces”, Multimedia Tools and Applications, Vol.74, No. 24, pp. 16781-16807, published by Springer US, Indexed by Science Citation Index Expanded (SCIE), Impact Factor: 2.313, 2016, ISSN: 1380-7501 (Print) and 1573-7721 (Online), https://doi.org/10.1007/s11042-015-2945-2
 Download
[2] Mrinal Kanti Bhowmik,Kankan Saha, Priya Saha, Debotosh Bhattacharjee, " DeitY-TU face database: its design, multiple camera capturing, characteristics, and evaluation", Journal of Optical Engineering, Vol. 53, No. 10, pp: 102106-1 to 24, Published by SPIE Digital Library, Indexed by Science Citation Index Expanded (SCIE), 2014, ISSN: 0091-3286 (Print) and 1560-2303 (Online), Impact Factor: 1.113, DOI: 10.1117/1.OE.53.10.102106. Download
|
|
| Copyright: |
The DeitY-TU Face Dataset is the property of Tripura University. This data can only be used for research or academic purposes. Any commercial use of the data whatsoever or incorporation of the data into a larger database intended for public distribution must be done with the explicit written consent of the administrators.
|
|
| Sponsored/Funded By: |
Department of Electronics and Information Technology(DIT),Now MeitY (Ministry of Electronics & Information Technology), New Delhi, Government of India.
|