This video shows my final degree project called "AROCR: System for digitalization and augmented representation for text in real time".
AROCR is able to digitalize the words in a real time video, and render them in the same video following the movement of the camera. This is done using features in the video frames, and using that as a moving reference in the other frames.
The word digitalized can be used as a input for other aplication as a voice synthesizer, or used for accesiblity usages.
This project was done using:
OpenCV: for video input and feature extractor.
Tesseract ocr: To capture the text
OpenGL: To render the interface
Finally in this video you can see the final result (text and augmented representation), the movement computation with the features, and the final interface with the movement of the camera.
nice program, did you share the sources or do you plan to?
chaiebnadhem 10 months ago