Niral, IMO the bitness is not the reason here. You are striving to optimize the running time for a single image but using different types of processors.
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, memory and FSB speed, cache etc. Unless you make your own efforts to write a multi-threaded Tesseract API based app, chopping an input image to pieces and processing them in parallel. However special care and manual changes to Tesseract code are required to make it thread-safe. On the other hand, if you plan to use Tesseract in a high load production environment, another approach is to rely on the host OS task scheduler and run multiple instances of Tesseract (or your Tesseract-enabled app) in parallel. Then the benefits of a multi-core environment may become more evident. The task scheduler would balance the load between the cores and overall system's processing speed would be better. If the CPU speeds of your boxes are too close, then the reason might be in a suboptimal hardware configuration, or maybe a cluttered software environment. To configure your system's hardware, you'll need a clean machine (or many of diverse types) and quite a few experiments to understand CPU and memory consumption for your types of images. Warm regards, Dmitri Silaev www.CustomOCR.com On Thu, Oct 31, 2013 at 10:36 AM, Niral Prajapati <[email protected]> wrote: > Hello All, > > I am using Tesseract3.0 for searchable pdf after creating hocr format files > , it takes 2-3 seconds for single image ( System configuration : Windows > 64bit Os, Intel i5-2500 CPU @3.30 GHZ , 8GB RAM ). > > This is quite acceptable time for me, > > but it takes 20-23 seconds for single image (System configuration: Windows > Server 2003 -32bit, Intel Quad CPU , 8GB RAM ) > > which is totaly unacceptable , > > can anyone advise me to reduce this time ??... > Thanks in advance > > -- > -- > You received this message because you are subscribed to the Google > Groups "tesseract-ocr" group. > To post to this group, send email to [email protected] > To unsubscribe from this group, send email to > [email protected] > For more options, visit this group at > http://groups.google.com/group/tesseract-ocr?hl=en > > --- > You received this message because you are subscribed to the Google Groups > "tesseract-ocr" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to [email protected]. > For more options, visit https://groups.google.com/groups/opt_out. -- -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en --- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. For more options, visit https://groups.google.com/groups/opt_out.
