IJFANS International Journal of Food and Nutritional Sciences

ISSN PRINT 2319 1775 Online 2320-7876

Visual Assistance For Visually Impaired People Using Image Caption and Text To Speech

Main Article Content

Venkataramana N1,a)Nagesh P2,b) Prabha B 3,c)
» doi: 10.48047/IJFANS/11/S6/039

Abstract

Picture captioning has recently become a new difficult challenge that gathered everyone interest, which is being able to automatically define an image's content with properly formatted text English sentences. it can make a great impact by assisting people who are visually impaired better recognitionof theircircumstances. 9 By taking the images of surrounding environment then make use of these photos to generate captions that can be read out visual amplification impaired, so that they can get a better sense of what's going on around them. In this p1a1per To extract features, we used a combination of convolutional neural networks of the images and then LSTM was used (Long short-term memory) to generate text from these features. The obtained text is then converted into speech so that it can be read out. Our model generates highly descriptive captions that canpotentially greatly improve the lives of visually impaired people.

Article Details