TASK-4 Results

Description:Identifying the combination of all the ten scripts.

Participation Systems

1. C-DAC, India: Swapnil Belhe from Centre for Development of Advanced Computing (C-DAC), has participated in all of the four competition tasks.
2. HUST, China Baoguang Shi, and his team members Cong Yao, Chengquan Zhang, Wei Shen, Zheng Zhang, and Xiang Bai from Huazhong University of Science and Technology (HUST) have submitted systems by participating in all of the four competition tasks.
3. CVC-1 and CVC-2, Spain: Lluis Gomez from the Computer Vision Center at UAB have participated in all of the four competition tasks and submitted two sets of systems for video script identification.
4. Google, Inc.: Yuanpeng Li from Google has participated in all four of the competition tasks.
5. CUK, India: Manjunath Shantharamu from Central University of Kerala (CUK) has participated in three tasks namely Task-2, Task-3 and Task-4.

Accuracy (%)
Scripts	C-DAC	HUST	CVC-1	CVC-2	Google	CUK
Arabic	97.69	100.00	99.34	99.67	100	89.44
Bengali	91.61	95.81	94.19	92.58	99.35	68.71
English	68.33	93.55	87.68	88.86	97.95	65.69
Gujrathi	88.99	97.55	97.55	98.17	98.17	73.39
Hindi	71.47	96.31	90.49	96.01	99.08	61.66
Kannada	68.47	92.68	97.13	97.13	97.77	71.66
Oriya	88.04	98.47	99.39	98.16	98.47	79.14
Punjabi	90.51	97.15	97.47	96.52	99.38	92.09
Tamil	91.9	97.82	100.00	99.69	99.38	82.55
Telugu	91.33	97.83	96.28	93.8	99.69	57.89
Overall	84.66	96.69	95.88	96	98.91	74.06