Turn Image into Text - Java

Question

This is an interesting topic. Basically, I have an image that contains some text. How do I extract the text from the image?

I have already tried many things, but everything I do is very tedious and usually does not work. I am simply wondering if there is a fairly easy way to do this.

I have come upon this: http://sourceforge.net/projects/javaocr/. I have tried this for hours, but I cannot get it to take an Image and turn it into a String of text from the image.

Thank you all in advance!

You could also find this helpful: http://stackoverflow.com/questions/9480831/java-ocr-api-open-source-on-eclipse/9481603#9481603 — Nikolay, May 03 '12 at 04:42

score 7 · Accepted Answer · edited May 23 '17 at 10:30

7

You need to look into Java OCR implementations. Take a look at this question: Java OCR

edited May 23 '17 at 10:30

Community

1
1

answered May 02 '12 at 18:31

Josh Diehl

2,782
2
30
39

Thanks, do you know how well this works? – Dylan Wheeler May 02 '12 at 18:33
Haven't tried it personally, but it will depend a lot on the clarity of the text on the image you are parsing. – Josh Diehl May 02 '12 at 18:34
The text is extremely easy to read. I will look into this, thanks! – Dylan Wheeler May 02 '12 at 18:39
Can you supply me with code for how to make this work? I have fiddled around with it for hours and I cannot get it to take an image and make it into a String. – Dylan Wheeler May 02 '12 at 21:59
Please do not link to other questions in your answer, instead please flag as duplicate. – Christian Stewart May 10 '13 at 23:29

score 4 · Answer 2 · answered May 04 '12 at 02:13

4

Tess4J, a JNA wrapper around Tesseract engine, supports APIs that take BufferedImage, File, or image data as input, and return String as output.

answered May 04 '12 at 02:13

nguyenq

7,964
1
15
15

I know I'm commenting after 3 years but your answer shoul be the right ansswer 'javaOCR' has many problems but this API works very well. – SlimenTN Jun 18 '15 at 08:47

score 2 · Answer 3 · edited May 23 '17 at 11:55

2

You need an OCR (optical character recognizer) library or write your own. Check out this SO question.

edited May 23 '17 at 11:55

Community

1
1

answered May 02 '12 at 18:31

Pablo Santa Cruz

170,119
31
233
283

Thanks, do you know how well this works? – Dylan Wheeler May 02 '12 at 18:33

score 0 · Answer 4 · answered May 02 '12 at 18:35

0

Try this character recognition library: http://sourceforge.net/projects/javaocr/

answered May 02 '12 at 18:35

Jonathan

7,311
5
27
35

Turn Image into Text - Java

4 Answers4

Linked

Related