CAPTIONARY- an AI-powered caption generator

Need of a hearing or visual aid ? Or need to track & annotate a prodigious amount of visual data or want to classify the images based on places you visited..? Worry not, Captionary has got you covered.

Either social media platforms, professional interactions, or transmission of humongous data, all of these are dominated by visuals and imageries. And with the conventional growth rate, keeping a track of all the visual data could be annoying, tedious, and time-engrossing.

If our era is the next industrial revolution, as many claim, AI is surely one of its driving forces…

Here, Captionary, an image caption generator, which is a web-application, comes in, to ease the task of managing the visual data and direct it according to one’s needs.

Captionary has a broad range of applications some of which are image/video processing in self-drive cars, classifying one’s pics into dogs, mountains, etc., creating a better environment for the visually impaired when used with text to voice converter and can also be used as a social media caption generator when used with right data sets.

The Backend of Captionary was made using python, machine learning, and use of data sets to train the model, and the frontend was made using flask.

Captionary in its current stage of development has a wide range of applications and will have a hundred more when trained with the right data sets to display more bold and striking captions..!

Project developed by: Charvi Bannur, Jaswin Kotian, Rohit Singh, Srushti V Reddy