Chapter 3Deep learning techniques for image captioning
R. Ramya, S. Vidhya, M. Preethi, and R. Rajalakshmi
3.1 Introduction to image captioning
Creating a textual caption for a set of images is known as image captioning. This translates images, which are seen as a sequence of pixels to a sequence of words, making it an end-to-end sequence to sequence challenge. Both the language or statements and the visuals must be processed for this reason. NVIDIA has developed a tool to assist those with poor or no vision using image captioning technology. It makes it easier for persons who are visually challenged to understand what is going on in a picture. Image captioning comes with an encoder-decoder structure. The image ...
Get Intelligent Systems and Applications in Computer Vision now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
