Method: TextBPN++(ResNet-50) - Samples list - Task 1 - Text Localization - ICDAR2017 Competition on Multi-lingual scene text detection and script identification - Robust Reading Competition

Page of 450

next >

View

Thumbnails
Table

Sample	Results
	IoU - Global
	Average Precision	Recall	Precision	Hmean
1	80.56%	83.33%	83.33%	83.33%
2	31.98%	33.33%	80.00%	47.06%
3	0.00%	0.00%	0.00%	0.00%
4	40.00%	75.00%	60.00%	66.67%
5	66.67%	66.67%	100.00%	80.00%
6	66.67%	66.67%	28.57%	40.00%
7	20.83%	50.00%	33.33%	40.00%
8	24.44%	45.45%	41.67%	43.48%
9	60.67%	65.22%	93.75%	76.92%
10	0.00%	0.00%	0.00%	0.00%
11	50.00%	50.00%	75.00%	60.00%
12	45.09%	70.00%	77.78%	73.68%
13	93.33%	93.33%	100.00%	96.55%
14	21.57%	23.53%	66.67%	34.78%
15	100.00%	100.00%	100.00%	100.00%
16	85.71%	85.71%	100.00%	92.31%
17	35.83%	75.00%	60.00%	66.67%
18	50.00%	50.00%	33.33%	40.00%
19	100.00%	100.00%	100.00%	100.00%
20	100.00%	100.00%	100.00%	100.00%

Download full table (.csv)

Results