Nowadays lots of students from a variety of streams and departments tend to take screenshot or pictures of lab manuals or records so that they can later do their assignments from it, while copying the same content written [4] in the pictures or screenshot can be a daunting as well as time consuming task but it seems to be the most effective one. But we have to come up with a much better and effective way to do these tasks which we call the ‘textractor’ [10]. This is a python [1] based GUI application to extract any kind of optimal character [2] found in an image file (irrespective of their types) and store it in a file.

It supports 5 languages as of now which consists of English and 4 other Indian languages [8] that are Hindi, Tamil, Odia and Telegu. The language support can be extended to many more languages depending on the user request.

pictures, textractor, image file, language.