Generating image description aiding blind people interpretation
J. K. Periasamy, I K Mukilan, Karthik Prasad T · 2022 International Conference on Communication, Computing and Internet of Things (IC3IoT) · 2022
In this paper, we present the model developed to transform images into audibly recognizable sentences (or) captions useful for blinds. We have used Deep learning and the Beam Search technique to summarize the image contents. Image summarization is a powerful, yet challenging problem that opens up many applications for machine learning like a screen reader or scenery describer for the blind which can explain the contents of an image using Text to Speech (TTS), Automatic content filtering on the web etc. This project explores a deep learning solution to identify the objects, their relationship and summarize the events on a given image.