Comparison of CNN models for picture description application
Ayushi Srivastava, Isha Meena, K. Manisha, Ankita Bansal · 2022
Blindness makes life tough for those who suffer from it, but machine learning can assist the visually impaired with their day - to - day tasks. Presently, image to speech is a relatively new and naïve topic. It’s a machine learning problem that requires both natural language processing and computer vision to analyze visual content. In this context, this work focuses on the development of a photo-to-speech application for the visually impaired people. The work’s ideology aims to make an impact on society so that visually impaired people can achieve equality. We merged picture and text processing in this work to build a practical deep learning application.