Geolocation and tracking services are much needed in the present world to make life easier and safer for humans where it involves a wide range of situations such as locating an address for postal services or crime case where tracking is an essential task to help the victims.
OCR can be used to track locations by extracting the information from the images in certain situations. Every day we see so many cases where it involves people missing. If by any chance there are any photos related to the crime, the OCR application can extract text from the images and helps to track their locations and find them in time if possible. Often these kinds of situations involve images from the wild, that is the information in the images is in the form of unstructured data, and it is hard to extract the text.
The main aim of this project is to build a robust OCR application to extract information from the digital pictures where the text is called “text in the wild”.
Furthermore, this system can be performed in a real-world environment as well. OCR has various applications such as Passport recognition, automatic number plate recognition, Invoices recognition, credit card recognition, converting handwritten texts to digital text, and many more.