Personalized image caption generation using cnn and lstm

Abisha anto ignatious , T judgi

CNN, Image captioning, LSTM, semantics

The Detection of diseases has become a prime issue in medical sciences as population density is fast growing in the world.The Image Captioning is generating a human-readable textual description or a sentence about an image. The proposed CNN-LSTM algorithm comprises the feature extraction process, semantic keywords extraction, facial recognition, and encoder-decoder LSTM networks. A pre-trained CNN is used to extract features from an image. A semantic keywords extraction module is used to identify the objects present in the image. The objects identified are labeled as the semantic tags present in the image. It increases the efficiency of captions in describing the objects and inclusion of these semantic labels in the captions.The model which has been proposed is based on the sets of Artificial Neural Network like Recurrent and Convolutional neural network.The LSTM based language model generates the captions by producing one word at a time. The facial recognition system identifies and recognizes the celebrity faces in the images, Tovalidate these results, we have tested our model with faces dataset which has facial images of 232 celebrities. The instances of the person in the sentence were replaced with their names and personalized captions were generated. The Bilingual evaluation understudy (BLEU) and METEOR scores were generated to calculate the precision of generated captions.

Published Paper   E-Certificate

"Personalized image caption generation using cnn and lstm", IJSDR - International Journal of Scientific Development and Research (www.IJSDR.org), ISSN:2455-2631, Vol.9, Issue 6, page no.889 - 898, June-2024, Available :https://ijsdr.org/papers/IJSDR2406101.pdf

Volume 9 Issue 6, June-2024

Pages : 889 - 898

Paper Reg. ID: IJSDR_211802

Published Paper Id: IJSDR2406101

Downloads: 000347105

Research Area: Science & Technology

Country: Tirunelveli , TamilNadu , India

Published Paper PDF: https://ijsdr.org/papers/IJSDR2406101

Published Paper URL: https://ijsdr.org/viewpaperforall?paper=IJSDR2406101

ISSN: 2455-2631 | IMPACT FACTOR: 9.15 Calculated By Google Scholar | ESTD YEAR: 2016

An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.15 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator

Publisher: IJSDR(IJ Publication) Janvi Wave

This work is licensed under a Creative Commons Attribution 4.0 International License and The Open Definition