AUDIO CAPTION GENERATION FROM IMAGES USING DEEP LEARNING

Abstract

Visually impaired individuals face various types of difficulties as they cannot visualize the natural environment. To overcome this problem, the proposed system would automatically generate captions for an input images and convert the generated caption to an audio format so that visually impaired individuals can listen to the generated captions. Captioning is performed using Deep Learning algorithm Convolution Neural Network (CNN), Recurrent Neural Network (RNN) and Long Short-Term Memory.