Converting text from scanned image to editable text

Question

Hi all, I am working on a project where I want to be able to upload an image(pdf) of a form that was filled in by hand then to convert it into text that will be later saved in a database. I am hoping to use OCR for recognition but I've never used it before so any help will be appreciated.
This will be done in WPF and it's a desktop application.
Thank you

Jony Green · Answer

I find another free online ocr tool, it can recognize text from image(http://www.online-code.net/ocr.html) and recognize text from pdf online( http://www.online-code.net/pdf-to-word.html ).

Chris Wolten · Answer

Normal 0 false false false EN-US X-NONE AR-SA /* Style Definitions */ table.MsoNormalTable{mso-style-name:"Table Normal";mso-tstyle-rowband-size:0;mso-tstyle-colband-size:0;mso-style-noshow:yes;mso-style-priority:99;mso-style-qformat:yes;mso-style-parent:"";mso-padding-alt:0mm 5.4pt 0mm 5.4pt;mso-para-margin:0mm;mso-para-margin-bottom:.0001pt;mso-pagination:widow-orphan;font-size:11.0pt;font-family:"Calibri","sans-serif";mso-ascii-font-family:Calibri;mso-ascii-theme-font:minor-latin;mso-fareast-font-family:"Times New Roman";mso-fareast-theme-font:minor-fareast;mso-hansi-font-family:Calibri;mso-hansi-theme-font:minor-latin;mso-bidi-font-family:Arial;mso-bidi-theme-font:minor-bidi;} We tried a few open source (free) options but as George stated, the support wasn't there. To add, it just didn't have the accuracy we needed. In the end, we ended up using leadtools ocr. We based our application on the code located here: http://support.leadtools.com/CS/forums/41362/ShowPost.aspx

George eric · Answer

Do you extract text from PDF document or Just an Image? Though PDF is an image technically, yet there are differences between each others. Please update with this question, I may direct a help for you.

George eric · Answer

Do you extract text from PDF document or Just an Image? Though PDF is an image technically, yet there are differences between each others. Please update with this question, I may direct a help for you.

Bennet Raj · Answer

The coding fully run but it is not extract the text and TextInPdf.txt file is empty. If you have any idea Kindly get me back.

George eric · Answer

THe above dll works fine with PDF, but i never apply it to scanned image myself.So If you have time and find something to help, please share with me, later I may develop a PDF tool. Thanks in Advance.

George eric · Answer

Sorry Avuya, As I really never used itexysharp for my developing, cause lack of direct supports, so I really dont know OCR is not there. So Sorry for the misinfos for you. But you can just download Spire.pdf for a free try and figure out how to slove. I think that may helps a little bit. Again I am sorry to recommend something I only heard for you. Please Forgive.

Avuya Mxoli · Answer

Thanks a lot, I checked out ItextSharp but the ICR software is not there yet hey. Thank you though

George eric · Answer

Ok, I see. It is truly hard to operate a scanned images. As for details, since I am also not sure, you better contact them. If you are looking for a Free SDK, I would like to recommend you ItextSharp. Free and Open source. But notice the disadvantage of lacking direct help or support in advance. Any way, Good luck to you.

Avuya Mxoli · Answer

thanx Eric I will try that out but you do understand that the text has been written by hand? will it be that simple to extract handwriting? Oh and just for interest, I mentioned in my question that I will be using OCR well after research it came to my attention that ICR will do the trick although I could not find any free SDK on the net

George eric · Answer

Hi Avuya. I am sorry that I don't know the direct solution to convert text from pdf to editable text. But I came up with this. You extract text from pdf and then write it to the editable text. How do you think? With the help of Spire.PDF . //Create a pdf document. PdfDocument doc = new PdfDocument(); doc.LoadFromFile(@"Sample2.pdf"); StringBuilder buffer = new StringBuilder(); IList images = new List (); foreach (PdfPageBase page in doc.Pages) { buffer.Append(page.ExtractText()); foreach (Image image in page.ExtractImages()) { images.Add(image); } } doc.Close(); //save text String fileName = "TextInPdf.txt"; File.WriteAllText(fileName, buffer.ToString()); //save image int index = 0; foreach (Image image in images) { String imageFileName = String.Format("Image-{0}.png", index++); image.Save(imageFileName, ImageFormat.Png); } // Launching the Text file. System.Diagnostics.Process.Start(fileName); }

Avuya Mxoli · Answer

is there anyone here that can advise me?

Converting text from scanned image to editable text

Madhanmohan Devarajan