Open AccessCaption to Voice Bot for Assistive Vision
Author(s) -
S Nandita
Publication year - 2021
Publication title -
international journal for research in applied science and engineering technology
Language(s) - English
Resource type - Journals
ISSN - 2321-9653
DOI - 10.22214/ijraset.2021.35244
Subject(s) - closed captioning , computer science , component (thermodynamics) , artificial intelligence , object (grammar) , interface (matter) , natural (archaeology) , comprehension , computer vision , natural language processing , human–computer interaction , image (mathematics) , history , physics , archaeology , bubble , maximum bubble pressure method , parallel computing , thermodynamics , programming language
Over the last few years, with the rapid development of artificial intelligence, the generation of the caption of images has progressively caught the considerable interest of several artificial intelligence research groups and has become a fascinating and tedious mission. A large component of scene comprehension, which encompasses the knowledge of computer vision and natural language processing, is image caption, which automatically produces natural language explanations according to the content observed in an image. The applications of such an image caption are substantial and noteworthy. The prime intention of the project is to build an object detection and captioning module that produces captions from the features extracted from the input images fed to the module in the form of audio and interface it with a virtual text reader, a read-aloud technology. Additionally, both these features can be accomplished using live images. The module as a whole helps the visually impaired identify objects and their positions.