Consider an example as shown below:
I ran imageProcess and I fail to get C (I also get a false positive "J", but this is okay). In some other images there are more true negatives. In general, is there any easy way to deal with this kind of image? If not, can I make the OCR more lenient so that I increase recall rate (sacrificing precision)?
asked 14 Dec '14, 05:04
Hi! This issue was fixed by our developers and now the fix is finally available in Cloud OCR SDK. We also recommend you to increase the scanning resolution to improve the recognition result.
answered 09 Feb '15, 19:09
Anna Falevskaya ♦♦