Machine-Generated Captions for Images using Deep Learning
Author(s):
Karwan Vishweshwar, Kosanam Srinivas, C.A. Daphine Desona Clemency
Keywords:
Deep Learning, LSTM, Caption, Description, Memory, Neural Network, VGG16, Image, CNN
Abstract
The primary objective of the picture caption generator is to automatically produce a suitable text or caption in English. The system's primary goal is to successfully provide appropriate captions for the provided picture. This study presents an image caption generator that, given an input picture, would identify its contents using beam search and greedy search to produce an English phrase. A pretrained deep learning CNN architecture exception model is used to learn image features, while a LSTM model is used to learn textual features, then integrates the results of both to produce a caption. To produce words, phrases, or captions for the provided photos, we use the LSTM model. Using the Convolutional Neural Network with Long Short-Term Memory, this model was created to create a caption generator for images. Features are extracted from the picture using a pre-trained version of VGG16. To create descriptive text for the pictures, LSTM acts as a decoder. This model has been taught to produce descriptive captions or words based on an input picture. The effectiveness of the model is measured by means of blue scores given to the system. The Keras library, NumPy, and Jupyter notebooks are discussed as tools for developing this project. We also talk about the picture categorization task, how CNNs are employed, and the Flickr dataset.
Article Details
Unique Paper ID: 158887

Publication Volume & Issue: Volume 9, Issue 10

Page(s): 807 - 812
Article Preview & Download


Share This Article

Join our RMS

Conference Alert

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

Call For Paper

Volume 10 Issue 10

Last Date for paper submitting for March Issue is 25 June 2024

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews