Re: Tesseract gurus please help me to get better results

2013-11-06 Thread valent.turko...@gmail.com
On Mon, Nov 4, 2013 at 8:34 AM, zdenko podobny wrote: > Tesseract is "noise sensitive" - you need to pre-process image before OCR. Can I learn tesseract to ignore some noise by using images that aren't 100% cleaned of all noise? Will that produce better or worst results? -- -- You received thi

Re: Tesseract gurus please help me to get better results

2013-11-06 Thread zdenko podobny
I did not play with it, but try to adjust some tesseract parameters[1] that have in description or name "noise". List of 3.02 parameters with description can be find online[2]. If you use tesseract from svn, than you can use ''tesseract --print-parameters", but there is no description (e.g. for new

Re: Tesseract 3.0 Performance down at 32bit Os

2013-11-06 Thread Andreas Romeyke
Hello Dmitri, Am Donnerstag, 31. Oktober 2013 09:01:44 UTC+1 schrieb Dmitri Silaev: > Tesseract at this time does not take advantage of multi-processor or > multi-core architecture. A single instance of Tesseract-enabled app > would run on a single core, hence all that matters is the clock,

How to create html using Tesseract hocr in iOS?

2013-11-06 Thread Arnold Bailey
I have a working iOS code using tesseract. I would like to create html using the hocr config option. I cannot find an example of how to generate html programmatically. Is there any sample code/tutorial around? I'm using Xcode 5 and the latest Tesseract-ios. - (NSString *)OCRPage:(NSString *)i

Re: Different Results on Linux vs Windows

2013-11-06 Thread Tom Morris
On Tuesday, November 5, 2013 12:38:57 PM UTC-5, rkomar wrote: > So, I would say that totally different results with code > compiled with different options or different compilers > is a sign of bad code. I don't think it should just be > shrugged off as unavoidable. > I agree with Rob here.

Re: Different Results on Linux vs Windows

2013-11-06 Thread zdenko podobny
On Wed, Nov 6, 2013 at 6:02 PM, Tom Morris wrote: > On Tuesday, November 5, 2013 12:38:57 PM UTC-5, rkomar wrote: > >> So, I would say that totally different results with code >> compiled with different options or different compilers >> is a sign of bad code. I don't think it should just be >> s

Re: Tesseract 3.0 Performance down at 32bit Os

2013-11-06 Thread Dmitri Silaev
Andreas, You are talking about vectorization which has nothing to do with what I am talking about, because this optimization technique still works within a single core (see articles on vector instructions on the internet). But even if you were talking about the right topic, automatic parallelizat