Read the text from image(TIFF,bmp) file using OCR in c#.net

Question

Hi

I am trying to read the text from the image file (TIFF, BMP) using OCR in c#.net.

But while reading the content, most of the text are wrong. For sample, in the image file, the content is Page. But when i read that content it is recognized as

Papa. I don't know what is the reason for the that.

Can any one give me an idea about how to solve this issue.

Thanks.

buyi wen · Answer

What you need is called OCR, and I always use this ocr service to read text from image in c# http://www.xspdf.com/guide-ocr/text-recognition-from-image/

Selva Ganapathy · Answer

Hi Krishnan, Please let me know the text of the image you need to extract may different font style and even a written text? if the the concept behind the following blog may helps you with huge iteration in it. http://www.c-sharpcorner.com/Blogs/13601/ Regards, Selva Ganapathy K

barcode addict · Answer

Hey, Arron Thank you for offering such a detailed OCR reading solution. As the method you mentioned, I just have one small question that are you using a developed OCR SDK to achieve reading text from image? By the way, a free OCR utility is not enough for me to read text from image? why do I have to install a mature image processing SDK ?

Ayman · Answer

Normal 0 false false false EN-US X-NONE AR-SA Are you implementing your own OCR engine or you are using a tool for OCR? Implementing your own OCR will not be easy and it will take long time. A better way to implement your OCR application is to use free engines like MODI or Tesseract. Or you can buy a commercial engine like leadtools engine. In my experience, commercial engines usually give better performance and results because they get better maintenance than free ones. Note that the suggestion made by Arron requires you to have MS Office installed on every machine where your solution is used. /* 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:0in 5.4pt 0in 5.4pt;mso-para-margin:0in;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;}

Kshitija Varma · Answer

Hi Arron, Please help.I am stuck at an exception while reading tif file using my c# code. The code is as follows: private void ReadFile(string path) { try { MODI.Document objModi = new MODI.Document(); objModi.Create(path); if (!objModi.Dirty) { for (int i = 0; i { objModi.Images[i].OCR(MODI.MiLANGUAGES.miLANG_ENGLISH, true, true); break; } } objModi.Save(); String strText = ""; for (int i = 0; i { strText += objModi.Images[0].Layout.Text; break; //string.Compare( } objModi.Close(false); MessageBox.Show(strText); } catch (Exception ex) { MessageBox.Show(ex.Message); } } The exception is coming at the highlighted line. It reads- {"Attempted to read or write protected memory. This is often an indication that other memory is corrupt."}. I have searched everywhere but could not find any solution. Please note that this code is able to read a part of a huge file nicely. But when it comes to reading the original file (45Mb size), this exception comes. Thanks, Kshitija

arron lee · Answer

Please do as the following steps: 1 Make sure your computer and your scanner are on and in proper working order. Your scanner should have the latest drivers installed. This will help it to best handle the Optical Character Recognition (OCR) program , which translates images to text. Your computer should be free of viruses and spyware. 2 Most computer scanners come with an OCR application. In the unlikely event that you don't have one, download and install an OCR program. SimpleOCR (simpleocr.com) is free to download and it can handle virtually any simple scanner to Word transfers. 3 Now that you are prepared to work with the actual document, place it into your scanner. If you have a document feeder your material needs to be face up, and the top of the pages should face the feeder. If not, or if your material is not in a single page form then place it under the lid on the scanner glass, in the upper right-hand corner. Scan and save the file. 4 Open the image. Save the image in the TIFF format by selecting "Save as" from the "File" menu and name it with a "TIFF" format. 5 Navigate to the "Start" menu and select "Programs," "Microsoft Office Tools" and "Microsoft Office Document Imaging." 6 From the "File" menu, select "Open" to open your scanned document that has been saved in the *.TIFF format. 7 From the "Tools" menu, select "Send Text to Word." A prompt will indicate that this process will take time. Click "OK" to confirm. Depending on your computer's speed, the process will take anywhere from a few moments to a minute or two. 8 When the process is done, Microsoft Word will automatically load your document, which you can edit and format as you please. Btw, it is very important to choose a good image tool to help you with your work. For example, the Tiff processing SDK must be compatible with your OCR SDK. Remember to check its free trial package first if possible and choose one whose way of processing is simple and fast. It can save a lot of time for you. I hope you success. Good luck. Best regards, Arron

Read the text from image(TIFF,bmp) file using OCR in c#.net

Answers (6)