Method: PMTD + CNN based method - Samples list - Task 3 - Joint text detection and script identification - ICDAR2017 Competition on Multi-lingual scene text detection and script identification - Robust Reading Competition

Page of 450

next >

View

Thumbnails
Table

Sample	Results
	Global
	Average Precision	Hmean	Precision	Recall
1	83.33%	71.43%	62.50%	83.33%
2	43.12%	56.41%	73.33%	45.83%
3	0.00%	0.00%	0.00%	0.00%
4	75.00%	85.71%	100.00%	75.00%
5	66.67%	72.73%	80.00%	66.67%
6	66.67%	57.14%	50.00%	66.67%
7	50.00%	44.44%	40.00%	50.00%
8	89.17%	90.91%	90.91%	90.91%
9	76.88%	80.00%	81.82%	78.26%
10	50.00%	66.67%	100.00%	50.00%
11	27.78%	40.00%	50.00%	33.33%
12	52.33%	57.14%	54.55%	60.00%
13	35.42%	50.00%	53.85%	46.67%
14	22.81%	38.46%	55.56%	29.41%
15	100.00%	100.00%	100.00%	100.00%
16	85.71%	85.71%	85.71%	85.71%
17	37.50%	50.00%	50.00%	50.00%
18	0.00%	0.00%	0.00%	0.00%
19	100.00%	100.00%	100.00%	100.00%
20	71.43%	76.92%	83.33%	71.43%

Download full table (.csv)

Results