Skip to content

arjunmohnot/Image-To-Text

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 

Repository files navigation

This application recognizes handwritten text of different fonts and styles by improving the design structure of the traditional Artificial Neural Network (ANN).

The results are then fed into Optical Character Recognition (OCR) as an electronic translation of images of handwritten, typewritten or printed text into machine-editable text. This also has an option to convert the text into audio.

Techonologies used This app was made in android studio and the model that we used for text recognition was Google vision for AI To select the area of image we intergrated android image cropper library.To save the soft copy of the text recognized by the model we used file Writter api.

Intergrating all these things togather was a tough task.Words with multiple fonds in single word were not being correclty recognized by the application.On some photos, especially photos without any text,precision can vary a lot depending on the type of image.Special characters of dirrent languages had precision problem and if they were not fed in the ocr they were wrongly recognized.

Click on the apk and then click on install.It may create a popup to install from unknown sources ,toggle that on and then continue with the installation.The options are displayed on the home screen which ever task you want to perform.You can either caputre a photo or upload from your gallery.The text icon converts image to speach.The voice icon converts speach to text which can be save as a doccument if required.

Team:-Arjun Mohnot: Main developer Tanmay Jain : Text recognition Arnav Chauhan :Image processing Tunap Paul : Saving files Siddhanth Iyer :UI and UX