Method: A modified CTPN model 1.0 - Samples list - Task 1 - Text Localization - ICDAR 2019 Robust Reading Challenge on Scanned Receipts OCR and Information Extraction - Robust Reading Competition

< previous

Page of 19

next >

View

Thumbnails
Table

Sample	Results
	Deteval
	Recall	Precision	Hmean
21	97.87%	97.73%	97.80%
22	97.56%	97.37%	97.46%
23	76.54%	69.66%	72.94%
24	65.00%	65.65%	65.32%
25	89.13%	85.42%	87.23%
26	98.15%	96.36%	97.25%
27	93.33%	97.44%	95.34%
28	98.25%	97.96%	98.10%
29	100.00%	100.00%	100.00%
30	85.17%	83.47%	84.31%
31	100.00%	100.00%	100.00%
32	98.82%	97.78%	98.30%
33	89.44%	87.14%	88.28%
34	98.03%	96.00%	97.01%
35	100.00%	100.00%	100.00%
36	82.72%	89.23%	85.85%
37	96.39%	97.70%	97.04%
38	90.32%	96.55%	93.33%
39	100.00%	100.00%	100.00%
40	100.00%	100.00%	100.00%

Download full table (.csv)

Results