Image Captioning is generating a caption for a given image using Deep Learning.
Dataset used is Flickr8k Dataset available on kaggle. It have 8K images and every image has 5 captions so that makes it a total of 8000*5 = 40,000 captions.
This project can be used as a base for more complex projects like
- Automatic surveillance using CCTV cameras to detect crimes/accidents.
- Aid to the blind people by using a camera to detect scenes in front of them.
- Automatic Captioning can help, make Google Image Search as good as Google Search, as then every image could be first converted into a caption and then search can be performed based on the caption.