• B.Sreejitha
• Prof. K. Venkata Ramanaiah
• G. Geethanjali
• C. Mounika
• P. Mohammad Fazil

Snap captioning refers to the textual description of a snap. The main motivation behind snap captioning is to help vision defective people by making less dependent on others. The approach of snap captioning process helps vision defective people to know the things going around them by listening the speech of the snap description produced by g TTS (Google text to sound) library. In this project we mainly focused on attention based mechanism in which image features are extracted using VGG16 (visual geometry group) and these features are transformed to linguistic format using LSTM (long short term memory).We have come with a proposed system where we used a modified LSTM known as g LSTM (guided LSTM).It is used to bring about the textual description of a snap under the usage of global semantic information. g LSTM primarily produces long sentence of a scenario. The description obtained from snap is judged by make use of BLEU score.

VGG16, g LSTM, g TTS, BLEU score

"CAPTIONING OF A SNAP FOR VISION DEFECTIVE PEOPLE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 5, page no.c585-c587, May-2022, Available :http://www.jetir.org/papers/JETIR2205375.pdf

"CAPTIONING OF A SNAP FOR VISION DEFECTIVE PEOPLE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 5, page no. ppc585-c587, May-2022, Available at : http://www.jetir.org/papers/JETIR2205375.pdf