You have no items in your shopping cart.
ABSTRACT
Some mobile OCR technologies now on the market are not free, leaving information unavailable to the visually handicapped. Also, some mobile OCR solutions are only available for IOS or Android not both. The project aims to make information available to the people with low vision irrespective of their financial status and/or the mobile phone operating system (Android or IOS) that they use.
This project makes printed and handwritten textual information accessible tovisually impaired (low-vision) students using a mobile Optical Character Recognition (OCR) and Speech Synthesizer system. The Water falls of tware model was used for building software. The Model-View-View Model Software Architecture was used. This Architecture helped inachieving Separation of Concerns which is a crucial Software Design Principle. This Architecture separated the User Interface logic from the Application Data logic. Azure Cognitive Services was used for the Optical Character Recognition (OCR) feature, Google Text-to-Speech Application Programming Interface (API) was used for Speech Synthesis, Kotlin Multi platform Mobile (KMM) was used for deployment on the Android and IOS mobile platform and Unit tests and Espresso were used for automated logic and User Interface testing.
The project can carry out OCR and Speech Synthesis on printed and handwritten texts in imagess to red locally (uploaded from device) and remotely (image URL). It is also free and available for use on the Android and IOS mobile operating systems.
