Simple Tesseract OCR — Java

Rahul Vaish
1 min readJun 14, 2018

--

Let’s see a very simple example of OCR implemented in Java.

Step#1: Download tessdata [eng.traineddata]

Step #2: Get a sample image (Grayscale converted) with something written on it.

Step#3: Add the below dependency in the pom.xml-

Step#4: Write the below code snippet to perform OCR-

Step#5: On executing the above code, the output is displayed on console :)

P.S. So far, the best OCR to choose on production code can be found with Google Vision API (which scans and results the image attributes as REST JSON).

--

--