Re: [tesseract-ocr] Re: How to improve ocr reader?
Ok thanks, I'll keep this. Il giorno sabato 28 marzo 2020 19:24:12 UTC+1, Lorenzo Blz ha scritto: > > If you'd like to improve the OCR accuracy too a simple contrast > enhancement (with a simple S shaped curve) and a little sharpening helps > with the left border. See the attached file. > > > > Lorenzo > > Il giorno sab 28 mar 2020 alle ore 19:04 Essam Zaky > ha scritto: > >> Yes with the same command the result attached >> >> >> بتاريخ السبت، 28 مارس، 2020 7:55:05 م UTC+2، كتب Teo: >>> >>> With the same coomand? >>> tesseract pho.png pho-eng -l eng pdf >>> >>> >>> >>> Il giorno sabato 28 marzo 2020 18:48:17 UTC+1, Essam Zaky ha scritto: It works fine in my machine It seems it's problem in your pdf viewer i used Adobe PDF reader V9.0 there are some pdf readers fail to read serachable pdf , try to check another reader Best Regards Essam بتاريخ السبت، 28 مارس، 2020 7:34:59 م UTC+2، كتب Teo: > > > Ok > Il giorno sabato 28 marzo 2020 18:32:26 UTC+1, Essam Zaky ha scritto: >> >> PLease attach the original image to check on my machine >> >> بتاريخ السبت، 28 مارس، 2020 7:24:07 م UTC+2، كتب Teo: >>> >>> Thanks for the reply. >>> I just opened an issue on github/Tesseract. Then I tried to create >>> an pdf only with tesseract and without gimagereader with: >>> tesseract pho.png pho-eng -l eng pdf >>> but this is the result... >>> >>> >>> Il giorno venerdì 27 marzo 2020 03:13:40 UTC+1, Essam Zaky ha >>> scritto: So I guess the error in PDF generation module you have one of the following option -try to enhance the bug by your self -raise an issue in Tesseract issues , but check first that the issue is not exist in list of issues -Use other extrenal library to create searchable pdf depending on hocr before tesseract add feature of generating pdf i used library called itextsharp to generate the pdf and the result was very good for me بتاريخ الخميس، 26 مارس، 2020 10:54:50 م UTC+2، كتب Teo: > > Ok coordinates seem correct. > > Il giorno giovedì 26 marzo 2020 19:13:52 UTC+1, Essam Zaky ha > scritto: >> >> read this document >> https://tesseract-ocr.github.io/tessdoc/Command-Line-Usage >> >> the following command can return the coordinates >> >> tesseract testing/eurotext.png testing/eurotext-eng -l eng hocr >> >> >> hocr contain the word as a text and coordinate >> you can open the image in any image editor such as MSpaint and >> check the returned coordinates represent the word in images >> >> Best Regards >> >> بتاريخ الخميس، 26 مارس، 2020 1:10:22 م UTC+2، كتب Teo: >>> >>> Thanks for your help. how can i get the coordinates, and how do >>> i check if they are correct? >>> >>> Il giorno mercoledì 25 marzo 2020 10:41:07 UTC+1, Essam Zaky ha >>> scritto: You need now to check the coordinates returned from tesseract ,use hocr output and check if words coordinates are returned correctly if yes so it is a bug in pdf generation if the coordinates are wrong it's bug in tesseract for me i used before library called itextsharp to generate searchable pdf , the library ported from itext java library , it gives good pdf output بتاريخ الأربعاء، 25 مارس، 2020 11:25:46 ص UTC+2، كتب Teo: > > Ok I think that it's a pdf generation module, because the txt > is almost the same with the exception of some "the" which > tesseract sees as > "thè". > > Il giorno mercoledì 25 marzo 2020 07:25:11 UTC+1, Essam Zaky > ha scritto: >> >> You need to know which to improve tesserct engine or PDF >> generation >> >> so compare text file from abby and tesserct >> if the result is highly different you need to improve image >> quality or improve LSTM >> >> if the result of tesseract is good so you need to enhance the >> PDF generation module >> >> بتاريخ الأربعاء، 25 مارس، 2020 7:04:14 ص UTC+2، كتب Teo: >>> >>> The quality is already very good, but is lower than abby >>> finereader. In attachment there is a comparison between abby >>> and >>> gimagereader ocr, and you can see the difference. How we >>> can improve it? >>> >>>
[tesseract-ocr] Re: How to improve ocr reader?
Ok thanks a lot. Il giorno sabato 28 marzo 2020 19:04:25 UTC+1, Essam Zaky ha scritto: > > Yes with the same command the result attached > > > بتاريخ السبت، 28 مارس، 2020 7:55:05 م UTC+2، كتب Teo: >> >> With the same coomand? >> tesseract pho.png pho-eng -l eng pdf >> >> >> >> Il giorno sabato 28 marzo 2020 18:48:17 UTC+1, Essam Zaky ha scritto: >>> >>> It works fine in my machine >>> It seems it's problem in your pdf viewer >>> i used Adobe PDF reader V9.0 >>> >>> there are some pdf readers fail to read serachable pdf , try to check >>> another reader >>> >>> Best Regards >>> Essam >>> >>> بتاريخ السبت، 28 مارس، 2020 7:34:59 م UTC+2، كتب Teo: Ok Il giorno sabato 28 marzo 2020 18:32:26 UTC+1, Essam Zaky ha scritto: > > PLease attach the original image to check on my machine > > بتاريخ السبت، 28 مارس، 2020 7:24:07 م UTC+2، كتب Teo: >> >> Thanks for the reply. >> I just opened an issue on github/Tesseract. Then I tried to create an >> pdf only with tesseract and without gimagereader with: >> tesseract pho.png pho-eng -l eng pdf >> but this is the result... >> >> >> Il giorno venerdì 27 marzo 2020 03:13:40 UTC+1, Essam Zaky ha scritto: >>> >>> So I guess the error in PDF generation module >>> you have one of the following option >>> -try to enhance the bug by your self >>> -raise an issue in Tesseract issues , but check first that the issue >>> is not exist in list of issues >>> -Use other extrenal library to create searchable pdf depending on >>> hocr >>> >>> before tesseract add feature of generating pdf i used library called >>> itextsharp to generate the pdf and the result was very good for me >>> >>> بتاريخ الخميس، 26 مارس، 2020 10:54:50 م UTC+2، كتب Teo: Ok coordinates seem correct. Il giorno giovedì 26 marzo 2020 19:13:52 UTC+1, Essam Zaky ha scritto: > > read this document > https://tesseract-ocr.github.io/tessdoc/Command-Line-Usage > > the following command can return the coordinates > > tesseract testing/eurotext.png testing/eurotext-eng -l eng hocr > > > hocr contain the word as a text and coordinate > you can open the image in any image editor such as MSpaint and > check the returned coordinates represent the word in images > > Best Regards > > بتاريخ الخميس، 26 مارس، 2020 1:10:22 م UTC+2، كتب Teo: >> >> Thanks for your help. how can i get the coordinates, and how do i >> check if they are correct? >> >> Il giorno mercoledì 25 marzo 2020 10:41:07 UTC+1, Essam Zaky ha >> scritto: >>> >>> You need now to check the coordinates returned from tesseract >>> ,use hocr output and check if words coordinates are returned >>> correctly if >>> yes so it is a bug in pdf generation >>> >>> if the coordinates are wrong it's bug in tesseract >>> >>> for me i used before library called itextsharp to generate >>> searchable pdf , the library ported from itext java library , it >>> gives >>> good pdf output >>> >>> >>> بتاريخ الأربعاء، 25 مارس، 2020 11:25:46 ص UTC+2، كتب Teo: Ok I think that it's a pdf generation module, because the txt is almost the same with the exception of some "the" which tesseract sees as "thè". Il giorno mercoledì 25 marzo 2020 07:25:11 UTC+1, Essam Zaky ha scritto: > > You need to know which to improve tesserct engine or PDF > generation > > so compare text file from abby and tesserct > if the result is highly different you need to improve image > quality or improve LSTM > > if the result of tesseract is good so you need to enhance the > PDF generation module > > بتاريخ الأربعاء، 25 مارس، 2020 7:04:14 ص UTC+2، كتب Teo: >> >> The quality is already very good, but is lower than abby >> finereader. In attachment there is a comparison between abby and >> gimagereader ocr, and you can see the difference. How we can >> improve it? >> >> >> >> -- 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 view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/5116c498-15c8-4090-b125-1c30579c54f2%40googlegroups.com.
[tesseract-ocr] Re: How to improve ocr reader?
With the same coomand? tesseract pho.png pho-eng -l eng pdf Il giorno sabato 28 marzo 2020 18:48:17 UTC+1, Essam Zaky ha scritto: > > It works fine in my machine > It seems it's problem in your pdf viewer > i used Adobe PDF reader V9.0 > > there are some pdf readers fail to read serachable pdf , try to check > another reader > > Best Regards > Essam > > بتاريخ السبت، 28 مارس، 2020 7:34:59 م UTC+2، كتب Teo: >> >> >> Ok >> Il giorno sabato 28 marzo 2020 18:32:26 UTC+1, Essam Zaky ha scritto: >>> >>> PLease attach the original image to check on my machine >>> >>> بتاريخ السبت، 28 مارس، 2020 7:24:07 م UTC+2، كتب Teo: Thanks for the reply. I just opened an issue on github/Tesseract. Then I tried to create an pdf only with tesseract and without gimagereader with: tesseract pho.png pho-eng -l eng pdf but this is the result... Il giorno venerdì 27 marzo 2020 03:13:40 UTC+1, Essam Zaky ha scritto: > > So I guess the error in PDF generation module > you have one of the following option > -try to enhance the bug by your self > -raise an issue in Tesseract issues , but check first that the issue > is not exist in list of issues > -Use other extrenal library to create searchable pdf depending on hocr > > before tesseract add feature of generating pdf i used library called > itextsharp to generate the pdf and the result was very good for me > > بتاريخ الخميس، 26 مارس، 2020 10:54:50 م UTC+2، كتب Teo: >> >> Ok coordinates seem correct. >> >> Il giorno giovedì 26 marzo 2020 19:13:52 UTC+1, Essam Zaky ha scritto: >>> >>> read this document >>> https://tesseract-ocr.github.io/tessdoc/Command-Line-Usage >>> >>> the following command can return the coordinates >>> >>> tesseract testing/eurotext.png testing/eurotext-eng -l eng hocr >>> >>> >>> hocr contain the word as a text and coordinate >>> you can open the image in any image editor such as MSpaint and check >>> the returned coordinates represent the word in images >>> >>> Best Regards >>> >>> بتاريخ الخميس، 26 مارس، 2020 1:10:22 م UTC+2، كتب Teo: Thanks for your help. how can i get the coordinates, and how do i check if they are correct? Il giorno mercoledì 25 marzo 2020 10:41:07 UTC+1, Essam Zaky ha scritto: > > You need now to check the coordinates returned from tesseract ,use > hocr output and check if words coordinates are returned correctly if > yes so > it is a bug in pdf generation > > if the coordinates are wrong it's bug in tesseract > > for me i used before library called itextsharp to generate > searchable pdf , the library ported from itext java library , it > gives > good pdf output > > > بتاريخ الأربعاء، 25 مارس، 2020 11:25:46 ص UTC+2، كتب Teo: >> >> Ok I think that it's a pdf generation module, because the txt is >> almost the same with the exception of some "the" which tesseract >> sees as >> "thè". >> >> Il giorno mercoledì 25 marzo 2020 07:25:11 UTC+1, Essam Zaky ha >> scritto: >>> >>> You need to know which to improve tesserct engine or PDF >>> generation >>> >>> so compare text file from abby and tesserct >>> if the result is highly different you need to improve image >>> quality or improve LSTM >>> >>> if the result of tesseract is good so you need to enhance the >>> PDF generation module >>> >>> بتاريخ الأربعاء، 25 مارس، 2020 7:04:14 ص UTC+2، كتب Teo: The quality is already very good, but is lower than abby finereader. In attachment there is a comparison between abby and gimagereader ocr, and you can see the difference. How we can improve it? -- 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 view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/de82d805-d1e2-44e1-aef2-4bab79eadd21%40googlegroups.com.
[tesseract-ocr] Re: How to improve ocr reader?
It works fine in my machine It seems it's problem in your pdf viewer i used Adobe PDF reader V9.0 there are some pdf readers fail to read serachable pdf , try to check another reader Best Regards Essam بتاريخ السبت، 28 مارس، 2020 7:34:59 م UTC+2، كتب Teo: > > > Ok > Il giorno sabato 28 marzo 2020 18:32:26 UTC+1, Essam Zaky ha scritto: >> >> PLease attach the original image to check on my machine >> >> بتاريخ السبت، 28 مارس، 2020 7:24:07 م UTC+2، كتب Teo: >>> >>> Thanks for the reply. >>> I just opened an issue on github/Tesseract. Then I tried to create an >>> pdf only with tesseract and without gimagereader with: >>> tesseract pho.png pho-eng -l eng pdf >>> but this is the result... >>> >>> >>> Il giorno venerdì 27 marzo 2020 03:13:40 UTC+1, Essam Zaky ha scritto: So I guess the error in PDF generation module you have one of the following option -try to enhance the bug by your self -raise an issue in Tesseract issues , but check first that the issue is not exist in list of issues -Use other extrenal library to create searchable pdf depending on hocr before tesseract add feature of generating pdf i used library called itextsharp to generate the pdf and the result was very good for me بتاريخ الخميس، 26 مارس، 2020 10:54:50 م UTC+2، كتب Teo: > > Ok coordinates seem correct. > > Il giorno giovedì 26 marzo 2020 19:13:52 UTC+1, Essam Zaky ha scritto: >> >> read this document >> https://tesseract-ocr.github.io/tessdoc/Command-Line-Usage >> >> the following command can return the coordinates >> >> tesseract testing/eurotext.png testing/eurotext-eng -l eng hocr >> >> >> hocr contain the word as a text and coordinate >> you can open the image in any image editor such as MSpaint and check >> the returned coordinates represent the word in images >> >> Best Regards >> >> بتاريخ الخميس، 26 مارس، 2020 1:10:22 م UTC+2، كتب Teo: >>> >>> Thanks for your help. how can i get the coordinates, and how do i >>> check if they are correct? >>> >>> Il giorno mercoledì 25 marzo 2020 10:41:07 UTC+1, Essam Zaky ha >>> scritto: You need now to check the coordinates returned from tesseract ,use hocr output and check if words coordinates are returned correctly if yes so it is a bug in pdf generation if the coordinates are wrong it's bug in tesseract for me i used before library called itextsharp to generate searchable pdf , the library ported from itext java library , it gives good pdf output بتاريخ الأربعاء، 25 مارس، 2020 11:25:46 ص UTC+2، كتب Teo: > > Ok I think that it's a pdf generation module, because the txt is > almost the same with the exception of some "the" which tesseract sees > as > "thè". > > Il giorno mercoledì 25 marzo 2020 07:25:11 UTC+1, Essam Zaky ha > scritto: >> >> You need to know which to improve tesserct engine or PDF >> generation >> >> so compare text file from abby and tesserct >> if the result is highly different you need to improve image >> quality or improve LSTM >> >> if the result of tesseract is good so you need to enhance the PDF >> generation module >> >> بتاريخ الأربعاء، 25 مارس، 2020 7:04:14 ص UTC+2، كتب Teo: >>> >>> The quality is already very good, but is lower than abby >>> finereader. In attachment there is a comparison between abby and >>> gimagereader ocr, and you can see the difference. How we can >>> improve it? >>> >>> >>> >>> -- 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 view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/28825e73-ab2c-4941-8a0c-cd10c4bc8e95%40googlegroups.com.
[tesseract-ocr] Re: How to improve ocr reader?
PLease attach the original image to check on my machine بتاريخ السبت، 28 مارس، 2020 7:24:07 م UTC+2، كتب Teo: > > Thanks for the reply. > I just opened an issue on github/Tesseract. Then I tried to create an pdf > only with tesseract and without gimagereader with: > tesseract pho.png pho-eng -l eng pdf > but this is the result... > > > Il giorno venerdì 27 marzo 2020 03:13:40 UTC+1, Essam Zaky ha scritto: >> >> So I guess the error in PDF generation module >> you have one of the following option >> -try to enhance the bug by your self >> -raise an issue in Tesseract issues , but check first that the issue is >> not exist in list of issues >> -Use other extrenal library to create searchable pdf depending on hocr >> >> before tesseract add feature of generating pdf i used library called >> itextsharp to generate the pdf and the result was very good for me >> >> بتاريخ الخميس، 26 مارس، 2020 10:54:50 م UTC+2، كتب Teo: >>> >>> Ok coordinates seem correct. >>> >>> Il giorno giovedì 26 marzo 2020 19:13:52 UTC+1, Essam Zaky ha scritto: read this document https://tesseract-ocr.github.io/tessdoc/Command-Line-Usage the following command can return the coordinates tesseract testing/eurotext.png testing/eurotext-eng -l eng hocr hocr contain the word as a text and coordinate you can open the image in any image editor such as MSpaint and check the returned coordinates represent the word in images Best Regards بتاريخ الخميس، 26 مارس، 2020 1:10:22 م UTC+2، كتب Teo: > > Thanks for your help. how can i get the coordinates, and how do i > check if they are correct? > > Il giorno mercoledì 25 marzo 2020 10:41:07 UTC+1, Essam Zaky ha > scritto: >> >> You need now to check the coordinates returned from tesseract ,use >> hocr output and check if words coordinates are returned correctly if yes >> so >> it is a bug in pdf generation >> >> if the coordinates are wrong it's bug in tesseract >> >> for me i used before library called itextsharp to generate searchable >> pdf , the library ported from itext java library , it gives good pdf >> output >> >> >> بتاريخ الأربعاء، 25 مارس، 2020 11:25:46 ص UTC+2، كتب Teo: >>> >>> Ok I think that it's a pdf generation module, because the txt is >>> almost the same with the exception of some "the" which tesseract sees >>> as >>> "thè". >>> >>> Il giorno mercoledì 25 marzo 2020 07:25:11 UTC+1, Essam Zaky ha >>> scritto: You need to know which to improve tesserct engine or PDF generation so compare text file from abby and tesserct if the result is highly different you need to improve image quality or improve LSTM if the result of tesseract is good so you need to enhance the PDF generation module بتاريخ الأربعاء، 25 مارس، 2020 7:04:14 ص UTC+2، كتب Teo: > > The quality is already very good, but is lower than abby > finereader. In attachment there is a comparison between abby and > gimagereader ocr, and you can see the difference. How we can > improve it? > > > > -- 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 view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/a43268d6-b716-4ecb-b591-affeaa859896%40googlegroups.com.
[tesseract-ocr] Re: How to improve ocr reader?
So I guess the error in PDF generation module you have one of the following option -try to enhance the bug by your self -raise an issue in Tesseract issues , but check first that the issue is not exist in list of issues -Use other extrenal library to create searchable pdf depending on hocr before tesseract add feature of generating pdf i used library called itextsharp to generate the pdf and the result was very good for me بتاريخ الخميس، 26 مارس، 2020 10:54:50 م UTC+2، كتب Teo: > > Ok coordinates seem correct. > > Il giorno giovedì 26 marzo 2020 19:13:52 UTC+1, Essam Zaky ha scritto: >> >> read this document >> https://tesseract-ocr.github.io/tessdoc/Command-Line-Usage >> >> the following command can return the coordinates >> >> tesseract testing/eurotext.png testing/eurotext-eng -l eng hocr >> >> >> hocr contain the word as a text and coordinate >> you can open the image in any image editor such as MSpaint and check the >> returned coordinates represent the word in images >> >> Best Regards >> >> بتاريخ الخميس، 26 مارس، 2020 1:10:22 م UTC+2، كتب Teo: >>> >>> Thanks for your help. how can i get the coordinates, and how do i check >>> if they are correct? >>> >>> Il giorno mercoledì 25 marzo 2020 10:41:07 UTC+1, Essam Zaky ha scritto: You need now to check the coordinates returned from tesseract ,use hocr output and check if words coordinates are returned correctly if yes so it is a bug in pdf generation if the coordinates are wrong it's bug in tesseract for me i used before library called itextsharp to generate searchable pdf , the library ported from itext java library , it gives good pdf output بتاريخ الأربعاء، 25 مارس، 2020 11:25:46 ص UTC+2، كتب Teo: > > Ok I think that it's a pdf generation module, because the txt is > almost the same with the exception of some "the" which tesseract sees as > "thè". > > Il giorno mercoledì 25 marzo 2020 07:25:11 UTC+1, Essam Zaky ha > scritto: >> >> You need to know which to improve tesserct engine or PDF generation >> >> so compare text file from abby and tesserct >> if the result is highly different you need to improve image quality >> or improve LSTM >> >> if the result of tesseract is good so you need to enhance the PDF >> generation module >> >> بتاريخ الأربعاء، 25 مارس، 2020 7:04:14 ص UTC+2، كتب Teo: >>> >>> The quality is already very good, but is lower than abby finereader. >>> In attachment there is a comparison between abby and gimagereader ocr, >>> and >>> you can see the difference. How we can improve it? >>> >>> >>> >>> -- 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 view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/9a423ce2-e982-437d-b106-29f61765a4c0%40googlegroups.com.
[tesseract-ocr] Re: How to improve ocr reader?
Ok coordinates seem correct. Il giorno giovedì 26 marzo 2020 19:13:52 UTC+1, Essam Zaky ha scritto: > > read this document > https://tesseract-ocr.github.io/tessdoc/Command-Line-Usage > > the following command can return the coordinates > > tesseract testing/eurotext.png testing/eurotext-eng -l eng hocr > > > hocr contain the word as a text and coordinate > you can open the image in any image editor such as MSpaint and check the > returned coordinates represent the word in images > > Best Regards > > بتاريخ الخميس، 26 مارس، 2020 1:10:22 م UTC+2، كتب Teo: >> >> Thanks for your help. how can i get the coordinates, and how do i check >> if they are correct? >> >> Il giorno mercoledì 25 marzo 2020 10:41:07 UTC+1, Essam Zaky ha scritto: >>> >>> You need now to check the coordinates returned from tesseract ,use hocr >>> output and check if words coordinates are returned correctly if yes so it >>> is a bug in pdf generation >>> >>> if the coordinates are wrong it's bug in tesseract >>> >>> for me i used before library called itextsharp to generate searchable >>> pdf , the library ported from itext java library , it gives good pdf output >>> >>> >>> بتاريخ الأربعاء، 25 مارس، 2020 11:25:46 ص UTC+2، كتب Teo: Ok I think that it's a pdf generation module, because the txt is almost the same with the exception of some "the" which tesseract sees as "thè". Il giorno mercoledì 25 marzo 2020 07:25:11 UTC+1, Essam Zaky ha scritto: > > You need to know which to improve tesserct engine or PDF generation > > so compare text file from abby and tesserct > if the result is highly different you need to improve image quality or > improve LSTM > > if the result of tesseract is good so you need to enhance the PDF > generation module > > بتاريخ الأربعاء، 25 مارس، 2020 7:04:14 ص UTC+2، كتب Teo: >> >> The quality is already very good, but is lower than abby finereader. >> In attachment there is a comparison between abby and gimagereader ocr, >> and >> you can see the difference. How we can improve it? >> >> >> >> -- 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 view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/6e127b74-c57f-4b79-94bd-e766d254f2cd%40googlegroups.com. The main topics of theoretical computer science are taught in most computer Science and engineering curricula, but are not presented as a foundation for omputer studies. Most courses—and their reference textbooks—are highly sed in their choice of topics. Very often they overemphasize traditional areas such as formal languages and automata—and pay little or no attention to yer important topics—such as formal semantics or computational complexity. The organization of this book results from our strongly held belief that oretical computer science should be viewed as the cornerstone of computer ence and engineering curricula. Computer specialists, in their everyday life, must be able to translate actual problems into abstractions based on the use of ormal models, to manipulate such formal descriptions, and to reason about their _ Properties in a rigorous way. This very special attitude differentiates the com- puter specialist from most other technical professionals. For these reasons, we suggest that an exposure to theoretical computer science topics should be given in the early stage of computer science education, particularly at the undergraduate level. Theoretical topics should not be viewed as options that can be added late in the curricula. Rather, they must be viewed as ee Wa Viieel oc
[tesseract-ocr] Re: How to improve ocr reader?
read this document https://tesseract-ocr.github.io/tessdoc/Command-Line-Usage the following command can return the coordinates tesseract testing/eurotext.png testing/eurotext-eng -l eng hocr hocr contain the word as a text and coordinate you can open the image in any image editor such as MSpaint and check the returned coordinates represent the word in images Best Regards بتاريخ الخميس، 26 مارس، 2020 1:10:22 م UTC+2، كتب Teo: > > Thanks for your help. how can i get the coordinates, and how do i check if > they are correct? > > Il giorno mercoledì 25 marzo 2020 10:41:07 UTC+1, Essam Zaky ha scritto: >> >> You need now to check the coordinates returned from tesseract ,use hocr >> output and check if words coordinates are returned correctly if yes so it >> is a bug in pdf generation >> >> if the coordinates are wrong it's bug in tesseract >> >> for me i used before library called itextsharp to generate searchable pdf >> , the library ported from itext java library , it gives good pdf output >> >> >> بتاريخ الأربعاء، 25 مارس، 2020 11:25:46 ص UTC+2، كتب Teo: >>> >>> Ok I think that it's a pdf generation module, because the txt is almost >>> the same with the exception of some "the" which tesseract sees as "thè". >>> >>> Il giorno mercoledì 25 marzo 2020 07:25:11 UTC+1, Essam Zaky ha scritto: You need to know which to improve tesserct engine or PDF generation so compare text file from abby and tesserct if the result is highly different you need to improve image quality or improve LSTM if the result of tesseract is good so you need to enhance the PDF generation module بتاريخ الأربعاء، 25 مارس، 2020 7:04:14 ص UTC+2، كتب Teo: > > The quality is already very good, but is lower than abby finereader. > In attachment there is a comparison between abby and gimagereader ocr, > and > you can see the difference. How we can improve it? > > > > -- 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 view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/cae9a132-fb12-4512-bc3f-79c2d948a615%40googlegroups.com.
[tesseract-ocr] Re: How to improve ocr reader?
Thanks for your help. how can i get the coordinates, and how do i check if they are correct? Il giorno mercoledì 25 marzo 2020 10:41:07 UTC+1, Essam Zaky ha scritto: > > You need now to check the coordinates returned from tesseract ,use hocr > output and check if words coordinates are returned correctly if yes so it > is a bug in pdf generation > > if the coordinates are wrong it's bug in tesseract > > for me i used before library called itextsharp to generate searchable pdf > , the library ported from itext java library , it gives good pdf output > > > بتاريخ الأربعاء، 25 مارس، 2020 11:25:46 ص UTC+2، كتب Teo: >> >> Ok I think that it's a pdf generation module, because the txt is almost >> the same with the exception of some "the" which tesseract sees as "thè". >> >> Il giorno mercoledì 25 marzo 2020 07:25:11 UTC+1, Essam Zaky ha scritto: >>> >>> You need to know which to improve tesserct engine or PDF generation >>> >>> so compare text file from abby and tesserct >>> if the result is highly different you need to improve image quality or >>> improve LSTM >>> >>> if the result of tesseract is good so you need to enhance the PDF >>> generation module >>> >>> بتاريخ الأربعاء، 25 مارس، 2020 7:04:14 ص UTC+2، كتب Teo: The quality is already very good, but is lower than abby finereader. In attachment there is a comparison between abby and gimagereader ocr, and you can see the difference. How we can improve it? -- 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 view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/b3293cc3-4766-4020-85b5-de6ad282aa6c%40googlegroups.com.
[tesseract-ocr] Re: How to improve ocr reader?
You need now to check the coordinates returned from tesseract ,use hocr output and check if words coordinates are returned correctly if yes so it is a bug in pdf generation if the coordinates are wrong it's bug in tesseract for me i used before library called itextsharp to generate searchable pdf , the library ported from itext java library , it gives good pdf output بتاريخ الأربعاء، 25 مارس، 2020 11:25:46 ص UTC+2، كتب Teo: > > Ok I think that it's a pdf generation module, because the txt is almost > the same with the exception of some "the" which tesseract sees as "thè". > > Il giorno mercoledì 25 marzo 2020 07:25:11 UTC+1, Essam Zaky ha scritto: >> >> You need to know which to improve tesserct engine or PDF generation >> >> so compare text file from abby and tesserct >> if the result is highly different you need to improve image quality or >> improve LSTM >> >> if the result of tesseract is good so you need to enhance the PDF >> generation module >> >> بتاريخ الأربعاء، 25 مارس، 2020 7:04:14 ص UTC+2، كتب Teo: >>> >>> The quality is already very good, but is lower than abby finereader. In >>> attachment there is a comparison between abby and gimagereader ocr, and you >>> can see the difference. How we can improve it? >>> >>> >>> >>> -- 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 view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/a4934f98-f1bc-4fcf-9bc1-c4805c143094%40googlegroups.com.
[tesseract-ocr] Re: How to improve ocr reader?
I discovered that the problem is not with reading, but with exporting to pdf. As I have tried to save both readings as txt files and they are almost the same. So how can I make the export more like abby's? With the text precisely on the document, all aligned I mean .. Il giorno mercoledì 25 marzo 2020 10:25:46 UTC+1, Teo ha scritto: > > Ok I think that it's a pdf generation module, because the txt is almost > the same with the exception of some "the" which tesseract sees as "thè". > > Il giorno mercoledì 25 marzo 2020 07:25:11 UTC+1, Essam Zaky ha scritto: >> >> You need to know which to improve tesserct engine or PDF generation >> >> so compare text file from abby and tesserct >> if the result is highly different you need to improve image quality or >> improve LSTM >> >> if the result of tesseract is good so you need to enhance the PDF >> generation module >> >> بتاريخ الأربعاء، 25 مارس، 2020 7:04:14 ص UTC+2، كتب Teo: >>> >>> The quality is already very good, but is lower than abby finereader. In >>> attachment there is a comparison between abby and gimagereader ocr, and you >>> can see the difference. How we can improve it? >>> >>> >>> >>> -- 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 view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/06e4a583-3b9a-48e6-95ca-7591f77ad615%40googlegroups.com.
[tesseract-ocr] Re: How to improve ocr reader?
Ok I think that it's a pdf generation module, because the txt is almost the same with the exception of some "the" which tesseract sees as "thè". Il giorno mercoledì 25 marzo 2020 07:25:11 UTC+1, Essam Zaky ha scritto: > > You need to know which to improve tesserct engine or PDF generation > > so compare text file from abby and tesserct > if the result is highly different you need to improve image quality or > improve LSTM > > if the result of tesseract is good so you need to enhance the PDF > generation module > > بتاريخ الأربعاء، 25 مارس، 2020 7:04:14 ص UTC+2، كتب Teo: >> >> The quality is already very good, but is lower than abby finereader. In >> attachment there is a comparison between abby and gimagereader ocr, and you >> can see the difference. How we can improve it? >> >> >> >> -- 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 view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/f0f76fd5-51fe-4b65-af63-04ba1bcebd97%40googlegroups.com.
[tesseract-ocr] Re: How to improve ocr reader?
You need to know which to improve tesserct engine or PDF generation so compare text file from abby and tesserct if the result is highly different you need to improve image quality or improve LSTM if the result of tesseract is good so you need to enhance the PDF generation module بتاريخ الأربعاء، 25 مارس، 2020 7:04:14 ص UTC+2، كتب Teo: > > The quality is already very good, but is lower than abby finereader. In > attachment there is a comparison between abby and gimagereader ocr, and you > can see the difference. How we can improve it? > > > > -- 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 view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/4e5af415-9b61-4f02-bd55-1e2a865987b7%40googlegroups.com.
