0

I want to read content(text data) from jpg image. Can someone give me a sample java program to refer.

The image would be a white page. The text would be in black. How do I extract data(lines/alphabets) and print it.

Help would be much appreciated.

Thanks

VGR
  • 40,506
  • 4
  • 48
  • 63
Chirag Patel
  • 9
  • 2

2 Answers2

1

Take a look at this SO question for OCR in Java. Once you are able to pull out the text, doing manipulations on the text can be taken care of by using Apache Lucene. Also, in case you are interested in image metadata as well, Apache Tika might be useful.

Community
  • 1
  • 1
Aritra
  • 1,234
  • 12
  • 20
0

Pay attention for products by ABBYY. For example there is ABBYY Cloud OCR SDK – cloud-based OCR technology. It has very high recognition accuracy, a lot of documentation and good support.

You can try to use it in several easy steps:
1. Create a free account
2. Create an application using code samples for Java

If you need additional help, use ABBYY's forum or publish your questions in comments below. I work for ABBYY and ready to help you.

Vitalik Kudryavtsev
  • 233
  • 2
  • 13