PROJECT TITLE :

Theme-Related Keyword Extraction from Free Text Descriptions of Image Contents for Tagging - 2018

ABSTRACT:

This Project discusses a method for automatic theme-related keyword extraction from users' natural language comments on their photographs and videos. 'Theme’ indicates the ideas circumscribing and describing the content of the photos and videos such as pets, natural sites, palaces and places. The strategy employs a deep learning algorithm, RNN(Recurrent Neural Network) that's smart at recognizing implicit patterns of sequential data. The tactic has been applied to the development of a place-related image content DB, and delivers reasonably good performance even in case the live (i.e. themes of image contents) is abstract and imprecise.