Asked By
Aaliyah
270 points
N/A
Posted on - 05/10/2011
I have a set of images in JPG format. I have Microsoft Office installed. I need to extract the text off the JPG files. How do I do this?
Answered By
MathGirl
0 points
N/A
#91524
Need to extract the text of a image file (OCR)
You will need to use a third party software for OCR. Do you have a scanner by any chance? Scanner software usually comes with a OCR software as a free bundle.
Answered By
Aaliyah
270 points
N/A
#91525
Need to extract the text of a image file (OCR)
I do not want to install a third party software. Is there a way to do it with Microsoft Word?
Answered By
WhizBoy
0 points
N/A
#91526
Need to extract the text of a image file (OCR)
Do you have the Office suite of products installed? Â Can you check if you have a Microsoft Office Tool called "Microsoft Office Document Imaging"? You can give it a shot with it.
Answered By
Aaliyah
270 points
N/A
#91527
Need to extract the text of a image file (OCR)
Yes, I do have Microsoft Office installed and I can see the tool called "Microsoft Office Document Imaging". I opened it up. Unfortunately it only supports MDI and TIFF formats. My file types are JPG!
Answered By
MathGirl
0 points
N/A
#91528
Need to extract the text of a image file (OCR)
Microsoft Office Document Imaging only supports MDI and TIFF. There is a long shot that you can try. That is to convert the JPG to TIFF. You can follow these steps:
-
Open the images JPG with Microsoft Paint
-
Then select save as and from the file type, select "TIFF"
-
Now open up Microsoft Office Document Imaging.
-
Browse and select the TIFF file.
-
Select the OCR option.
This "might" work.
Answered By
WhizBoy
0 points
N/A
#91529
Need to extract the text of a image file (OCR)
You can also use Microsoft Office Picture Manager tool for the file conversion. It is better than using paint. It is a bundled product that comes when you install Microsoft Office suite of products.
Answered By
Aaliyah
270 points
N/A
#91530
Need to extract the text of a image file (OCR)
I used the Microsoft Office Picture Manager to convert the files to TIFF. Then I used Microsoft Office Document Imaging tool to perform OCR on the TIFF image.  I got some text onto Microsoft Word. The extracted text requires fine tuning but at least I got a majority of the text via OCR. Thank you Math Girl and Whiz Boy for the support and advise!
Answered By
WhizBoy
0 points
N/A
#91531
Need to extract the text of a image file (OCR)
Glad to be of assistance! Remember, for OCR you need to have the base images in TIFF. This is the industry accepted format for saving scanned images. It is also the base format for OCR text. JPG does a grainy effect when it compresses the file. TIFF does not introduce gray matter into the image. Therefore TIFF is the best format for OCR.
Answered By
Aaliyah
270 points
N/A
#91532
Need to extract the text of a image file (OCR)
Thank you Whiz Boy! I will make a note of it.
