Automated image captioning
Teo, Sabrina Jingya
Date of Issue2017
School of Electrical and Electronic Engineering
Technology advancement has brought about many changes in human interaction. Information can now be easily accessed through the web and data can be stored online. This results in an influx of data stored on the web. Due to development in technologies, automated identification has become a popular subject. It caused any changes in the way human store and process image data. Other than efficient storage and classification of the massive data which is the initial purpose that sparks the interest in the field, automated identification can help the lives of the less fortunate. This project makes use of Tesseract, an optical character recognition engine and text- to-speech system to aim to build a system to assist the visually impaired on their daily interactions and activities especially in accessing printed materials. Texts are the most common form of data input on the computer or mobile phone. With decrease visibility, the visually impaired is restricted to information accessible on electronic devices. This system will improve their access to these information.
DRNTU::Engineering::Electrical and electronic engineering
Final Year Project (FYP)
Nanyang Technological University