Re: [tesseract-ocr] Training for plotter file
The basic image processing is only available for individual images loaded in the UI. The bulk or batch OCR does not have this support. Therefore, it's suggested that you perform the bulk image processing outside of VietOCR, using ImageMagick, GIMP, etc. Both VietOCR Java .NET support command-line execution. The command syntax is similar to that of Tesseract: vietocr vietsample.tif out -l vie On Sunday, March 22, 2015 at 3:55:50 PM UTC-5, Dennis wrote: I just tried the bulk option, and I see that it also outputs the location of the text it OCRed, which is what I wanted, but it does not have an option to do a smooth or textbox around the text I want to OCR. There is no way to automate these things? Also, how do I run vietocr with commandline? preferably through .NET rather than Java. Thank you for the help, Dennis On Sunday, March 22, 2015 at 11:20:18 AM UTC-7, shree wrote: vietocr has bulkocr and batch options. ShreeDevi भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com On Sun, Mar 22, 2015 at 6:39 AM, Dennis denni...@gmail.com wrote: I'm using the latest version of tesseract: 3.02. I successfully OCRed with vietocr gui. If I set it as screenshot mode, apply a smooth filter, and use the textbox to select each line one by one, I get a 100% correct OCR. Now I am wondering, how can I automate this process? I want to be able to create a program or execute a command so that I give it the image and it does the above things automatically and outputs the OCR and the location of the OCRed text in the image file. Thank you, Dennis Gahm On Sunday, October 19, 2014 at 7:02:05 PM UTC-7, shree wrote: Which version of tesseract are you using? Try changing to 300/600 dpi, apply a blur/soften filter, decrease brighness, convert to greyscale. I tried with vietocr gui, zero with the line across gets recognized as @, rest comes out ok. If you will not have @ in your plots, you could just substitute @ by zero in post-processing. ShreeDevi भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com On Sun, Oct 19, 2014 at 3:21 AM, Dennis denni...@gmail.com wrote: Hello, I am trying to recognize the characters from a plot file (attached). The characters are composed of lines and are not fonts. I've tried training, but I was unsuccessful (I probably did something wrong). Can anyone help? Thank you, Dennis -- 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 tesseract-oc...@googlegroups.com. To post to this group, send email to tesser...@googlegroups.com. Visit this group at http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/ msgid/tesseract-ocr/7b3aa12c-0927-4f27-9b31-178b0c234d5e% 40googlegroups.com https://groups.google.com/d/msgid/tesseract-ocr/7b3aa12c-0927-4f27-9b31-178b0c234d5e%40googlegroups.com?utm_medium=emailutm_source=footer . For more options, visit https://groups.google.com/d/optout. -- 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 tesseract-oc...@googlegroups.com. To post to this group, send email to tesser...@googlegroups.com. Visit this group at http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/b6433fbd-0159-42ba-84b7-52ea0e563bd9%40googlegroups.com https://groups.google.com/d/msgid/tesseract-ocr/b6433fbd-0159-42ba-84b7-52ea0e563bd9%40googlegroups.com?utm_medium=emailutm_source=footer . For more options, visit https://groups.google.com/d/optout. -- 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 tesseract-ocr+unsubscr...@googlegroups.com. To post to this group, send email to tesseract-ocr@googlegroups.com. Visit this group at http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/2517da0d-3c4c-463f-9bcc-60e94dfb4016%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
Re: [tesseract-ocr] Training for plotter file
I'm using the latest version of tesseract: 3.02. I successfully OCRed with vietocr gui. If I set it as screenshot mode, apply a smooth filter, and use the textbox to select each line one by one, I get a 100% correct OCR. Now I am wondering, how can I automate this process? I want to be able to create a program or execute a command so that I give it the image and it does the above things automatically and outputs the OCR and the location of the OCRed text in the image file. Thank you, Dennis Gahm On Sunday, October 19, 2014 at 7:02:05 PM UTC-7, shree wrote: Which version of tesseract are you using? Try changing to 300/600 dpi, apply a blur/soften filter, decrease brighness, convert to greyscale. I tried with vietocr gui, zero with the line across gets recognized as @, rest comes out ok. If you will not have @ in your plots, you could just substitute @ by zero in post-processing. ShreeDevi भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com On Sun, Oct 19, 2014 at 3:21 AM, Dennis denni...@gmail.com javascript: wrote: Hello, I am trying to recognize the characters from a plot file (attached). The characters are composed of lines and are not fonts. I've tried training, but I was unsuccessful (I probably did something wrong). Can anyone help? Thank you, Dennis -- 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 tesseract-oc...@googlegroups.com javascript:. To post to this group, send email to tesser...@googlegroups.com javascript:. Visit this group at http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/7b3aa12c-0927-4f27-9b31-178b0c234d5e%40googlegroups.com https://groups.google.com/d/msgid/tesseract-ocr/7b3aa12c-0927-4f27-9b31-178b0c234d5e%40googlegroups.com?utm_medium=emailutm_source=footer . For more options, visit https://groups.google.com/d/optout. -- 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 tesseract-ocr+unsubscr...@googlegroups.com. To post to this group, send email to tesseract-ocr@googlegroups.com. Visit this group at http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/b6433fbd-0159-42ba-84b7-52ea0e563bd9%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
Re: [tesseract-ocr] Training for plotter file
vietocr has bulkocr and batch options. ShreeDevi भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com On Sun, Mar 22, 2015 at 6:39 AM, Dennis dennisg...@gmail.com wrote: I'm using the latest version of tesseract: 3.02. I successfully OCRed with vietocr gui. If I set it as screenshot mode, apply a smooth filter, and use the textbox to select each line one by one, I get a 100% correct OCR. Now I am wondering, how can I automate this process? I want to be able to create a program or execute a command so that I give it the image and it does the above things automatically and outputs the OCR and the location of the OCRed text in the image file. Thank you, Dennis Gahm On Sunday, October 19, 2014 at 7:02:05 PM UTC-7, shree wrote: Which version of tesseract are you using? Try changing to 300/600 dpi, apply a blur/soften filter, decrease brighness, convert to greyscale. I tried with vietocr gui, zero with the line across gets recognized as @, rest comes out ok. If you will not have @ in your plots, you could just substitute @ by zero in post-processing. ShreeDevi भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com On Sun, Oct 19, 2014 at 3:21 AM, Dennis denni...@gmail.com wrote: Hello, I am trying to recognize the characters from a plot file (attached). The characters are composed of lines and are not fonts. I've tried training, but I was unsuccessful (I probably did something wrong). Can anyone help? Thank you, Dennis -- 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 tesseract-oc...@googlegroups.com. To post to this group, send email to tesser...@googlegroups.com. Visit this group at http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/ msgid/tesseract-ocr/7b3aa12c-0927-4f27-9b31-178b0c234d5e% 40googlegroups.com https://groups.google.com/d/msgid/tesseract-ocr/7b3aa12c-0927-4f27-9b31-178b0c234d5e%40googlegroups.com?utm_medium=emailutm_source=footer . For more options, visit https://groups.google.com/d/optout. -- 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 tesseract-ocr+unsubscr...@googlegroups.com. To post to this group, send email to tesseract-ocr@googlegroups.com. Visit this group at http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/b6433fbd-0159-42ba-84b7-52ea0e563bd9%40googlegroups.com https://groups.google.com/d/msgid/tesseract-ocr/b6433fbd-0159-42ba-84b7-52ea0e563bd9%40googlegroups.com?utm_medium=emailutm_source=footer . For more options, visit https://groups.google.com/d/optout. -- 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 tesseract-ocr+unsubscr...@googlegroups.com. To post to this group, send email to tesseract-ocr@googlegroups.com. Visit this group at http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/CAG2NduVm06%3D1JtSoEhmvv13gBe62vg_xSXg5na4My5k8ozqLfQ%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
Re: [tesseract-ocr] Training for plotter file
I just tried the bulk option, and I see that it also outputs the location of the text it OCRed, which is what I wanted, but it does not have an option to do a smooth or textbox around the text I want to OCR. There is no way to automate these things? Also, how do I run vietocr with commandline? preferably through .NET rather than Java. Thank you for the help, Dennis On Sunday, March 22, 2015 at 11:20:18 AM UTC-7, shree wrote: vietocr has bulkocr and batch options. ShreeDevi भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com On Sun, Mar 22, 2015 at 6:39 AM, Dennis denni...@gmail.com javascript: wrote: I'm using the latest version of tesseract: 3.02. I successfully OCRed with vietocr gui. If I set it as screenshot mode, apply a smooth filter, and use the textbox to select each line one by one, I get a 100% correct OCR. Now I am wondering, how can I automate this process? I want to be able to create a program or execute a command so that I give it the image and it does the above things automatically and outputs the OCR and the location of the OCRed text in the image file. Thank you, Dennis Gahm On Sunday, October 19, 2014 at 7:02:05 PM UTC-7, shree wrote: Which version of tesseract are you using? Try changing to 300/600 dpi, apply a blur/soften filter, decrease brighness, convert to greyscale. I tried with vietocr gui, zero with the line across gets recognized as @, rest comes out ok. If you will not have @ in your plots, you could just substitute @ by zero in post-processing. ShreeDevi भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com On Sun, Oct 19, 2014 at 3:21 AM, Dennis denni...@gmail.com wrote: Hello, I am trying to recognize the characters from a plot file (attached). The characters are composed of lines and are not fonts. I've tried training, but I was unsuccessful (I probably did something wrong). Can anyone help? Thank you, Dennis -- 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 tesseract-oc...@googlegroups.com. To post to this group, send email to tesser...@googlegroups.com. Visit this group at http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/ msgid/tesseract-ocr/7b3aa12c-0927-4f27-9b31-178b0c234d5e% 40googlegroups.com https://groups.google.com/d/msgid/tesseract-ocr/7b3aa12c-0927-4f27-9b31-178b0c234d5e%40googlegroups.com?utm_medium=emailutm_source=footer . For more options, visit https://groups.google.com/d/optout. -- 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 tesseract-oc...@googlegroups.com javascript:. To post to this group, send email to tesser...@googlegroups.com javascript:. Visit this group at http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/b6433fbd-0159-42ba-84b7-52ea0e563bd9%40googlegroups.com https://groups.google.com/d/msgid/tesseract-ocr/b6433fbd-0159-42ba-84b7-52ea0e563bd9%40googlegroups.com?utm_medium=emailutm_source=footer . For more options, visit https://groups.google.com/d/optout. -- 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 tesseract-ocr+unsubscr...@googlegroups.com. To post to this group, send email to tesseract-ocr@googlegroups.com. Visit this group at http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/bec14bdc-b81f-44ff-bb7a-c2b494c7582e%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
