T O P I C R E V I E W |
rswyman@docuxplorer.com |
Posted - Nov 01 2012 : 04:33:06 We are trying to Zone OCR from screen shots of other application data entry fields but not having much luck on the OCR recognizing the text. Enclosed is a sample file.


What can I do to improve my results?
I’m using the OCR demo application… Also the m_OCR.getWordBoxes(); raises an exception in the demo. |
5 L A T E S T R E P L I E S (Newest First) |
fab |
Posted - Nov 08 2012 : 03:37:32 Hi, you could try to increase image size. For example, with the image you have posted, executing:
ImageEnVect1.Proc.Resample(2000, -1, rfBicubic);
will make OCR correctly (tried with OCR example, just pressing "Recognize"). |
rswyman@docuxplorer.com |
Posted - Nov 02 2012 : 18:58:17 Any sugestions as to my initial query? |
xequte |
Posted - Nov 02 2012 : 18:22:56 Hi
I'm afraid this is not possible with ImageEn.
Nigel Xequte Software www.xequte.com nigel@xequte.com
|
rswyman@docuxplorer.com |
Posted - Nov 01 2012 : 10:28:33 Here is a referance as to the effect I think needs to be created.. http://www.m.cs.osakafu-u.ac.jp/cbdar2007/proceedings/papers/O1-1.pdf
How can I produce this with ImageEn?
|
rswyman@docuxplorer.com |
Posted - Nov 01 2012 : 09:48:07 Can ImageEn support binarization filter. If so how? |