Method: Sun Asterisk - AI Research - Samples list - Task 2 - Scanned Receipt OCR - ICDAR 2019 Robust Reading Challenge on Scanned Receipts OCR and Information Extraction - Robust Reading Competition

Page of 19

next >

View

Thumbnails
Table

Sample	Results
	OCR
	Recall	Precision	Hmean
1	88.29%	89.91%	89.09%
2	87.23%	87.23%	87.23%
3	82.00%	76.40%	79.10%
4	91.11%	90.11%	90.61%
5	96.97%	96.97%	96.97%
6	82.73%	76.47%	79.48%
7	89.81%	89.81%	89.81%
8	86.86%	90.84%	88.81%
9	91.36%	84.09%	87.57%
10	90.52%	93.63%	92.05%
11	90.20%	90.20%	90.20%
12	94.83%	90.16%	92.44%
13	93.81%	95.63%	94.71%
14	88.24%	88.98%	88.61%
15	95.15%	96.08%	95.61%
16	95.54%	96.77%	96.15%
17	94.87%	97.37%	96.10%
18	97.46%	97.46%	97.46%
19	86.67%	83.33%	84.97%
20	93.41%	92.86%	93.13%

Download full table (.csv)

Results