Call for Papers:Vol.10 Issue.6

Submission
Last date		 30-Dec-2024
Acceptance Status In One Day
Paper Publish In Two Days
Submit ManuScript

News & Updates

Submit Article

Dear Authors, Article publish in our journal for Volume-10,Issue-6. For article submission on below link: Submit Manuscript


Join As Board

Dear Reviewer, You can join our Reviewer team without given any charges in our journal. Submit Details on below link: Join As Board


Paper Publication Charges

IJARIIE APP
Download Android App

For Authors

Archives

IJARIIE Board

Downloads

Android App

Download IJARIIE APP

Authors

Title: :  "VocPix: Image Captioning using CNN and LSTM"
PaperId: :  19942
Published in:   International Journal Of Advance Research And Innovative Ideas In Education
Publisher:   IJARIIE
e-ISSN:   2395-4396
Volume/Issue:    Volume 9 Issue 2 2023
DUI:    16.0415/IJARIIE-19942
Licence: :   IJARIIE is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Author NameAuthor Institute
Bhushan Arun AmbhoreSinhgad College Of Engineering, Pune
Linal Anil PatilSinhgad College Of Engineering, Pune
Manasi Shekhar PatilSinhgad College Of Engineering, Pune
Niket Sitaram SharmaSinhgad College Of Engineering, Pune
Hitesh E. ChaudhariSinhgad College Of Engineering, Pune

Abstract

Computer Engineering
Deep learning, CNN, LSTM, Machine learning, Neural Networks, Text-To-Speech
With billions of users on sites like Facebook, Twitter, Instagram, and YouTube, social media has become an essential component of modern life. Social media has fundamentally altered how we communicate, share information, and engage with one another. It has also changed how we both consume and produce material. Therefore, an image caption generator has become essential in today's culture because it is necessary for social media addicts or people who are blind. It is a kind of algorithm or software program that makes use of Deep Learning techniques and analyses an image's visual information before converting it into plain language. It can be used as a plugin on the popular social networking sites of today to suggest appropriate captions for users to include with their postings. The goal of the suggested research is to create an image caption, also known as a description of an image, and to translate it into different languages, using CNN-LSTM architecture. To use the current word as input for the prediction of the following word, CNN layers will help in retrieving input data, and LSTM will extract essential information as it processes input. Python 3 and machine learning will be the programming languages used. This study will go into great detail about the many Neural networks involved, including their structures and functions. The program that converts created captions into spoken words is called a text-to-speech synthesizer, and it uses Natural Language Processing (NLP) to analyze and process the text. The text is subsequently converted into a synthesized speech representation using digital signal processing (DSP) technology. Here, we've created a practical text-to-speech synthesizer in the form of an easy-to-use application that reads aloud generated captions as synthesized speech. The proposed deep learning approach aims at generating the best caption for a particular image by analyzing and extracting various features from images and converting that textual caption into speech using Text-To-Speech (TTS).

Citations

Copy and paste a formatted citation or use one of the links to import into a bibliography manager and reference.

IJARIIE Bhushan Arun Ambhore, Linal Anil Patil, Manasi Shekhar Patil, Niket Sitaram Sharma, and Hitesh E. Chaudhari. ""VocPix: Image Captioning using CNN and LSTM"" International Journal Of Advance Research And Innovative Ideas In Education Volume 9 Issue 2 2023 Page 2873-2880
MLA Bhushan Arun Ambhore, Linal Anil Patil, Manasi Shekhar Patil, Niket Sitaram Sharma, and Hitesh E. Chaudhari. ""VocPix: Image Captioning using CNN and LSTM"." International Journal Of Advance Research And Innovative Ideas In Education 9.2(2023) : 2873-2880.
APA Bhushan Arun Ambhore, Linal Anil Patil, Manasi Shekhar Patil, Niket Sitaram Sharma, & Hitesh E. Chaudhari. (2023). "VocPix: Image Captioning using CNN and LSTM". International Journal Of Advance Research And Innovative Ideas In Education, 9(2), 2873-2880.
Chicago Bhushan Arun Ambhore, Linal Anil Patil, Manasi Shekhar Patil, Niket Sitaram Sharma, and Hitesh E. Chaudhari. ""VocPix: Image Captioning using CNN and LSTM"." International Journal Of Advance Research And Innovative Ideas In Education 9, no. 2 (2023) : 2873-2880.
Oxford Bhushan Arun Ambhore, Linal Anil Patil, Manasi Shekhar Patil, Niket Sitaram Sharma, and Hitesh E. Chaudhari. '"VocPix: Image Captioning using CNN and LSTM"', International Journal Of Advance Research And Innovative Ideas In Education, vol. 9, no. 2, 2023, p. 2873-2880. Available from IJARIIE, https://ijariie.com/AdminUploadPdf/_VocPix__Image_Captioning_using_CNN_and_LSTM__ijariie19942.pdf (Accessed : 19 September 2024).
Harvard Bhushan Arun Ambhore, Linal Anil Patil, Manasi Shekhar Patil, Niket Sitaram Sharma, and Hitesh E. Chaudhari. (2023) '"VocPix: Image Captioning using CNN and LSTM"', International Journal Of Advance Research And Innovative Ideas In Education, 9(2), pp. 2873-2880IJARIIE [Online]. Available at: https://ijariie.com/AdminUploadPdf/_VocPix__Image_Captioning_using_CNN_and_LSTM__ijariie19942.pdf (Accessed : 19 September 2024)
IEEE Bhushan Arun Ambhore, Linal Anil Patil, Manasi Shekhar Patil, Niket Sitaram Sharma, and Hitesh E. Chaudhari, ""VocPix: Image Captioning using CNN and LSTM"," International Journal Of Advance Research And Innovative Ideas In Education, vol. 9, no. 2, pp. 2873-2880, Mar-App 2023. [Online]. Available: https://ijariie.com/AdminUploadPdf/_VocPix__Image_Captioning_using_CNN_and_LSTM__ijariie19942.pdf [Accessed : 19 September 2024].
Turabian Bhushan Arun Ambhore, Linal Anil Patil, Manasi Shekhar Patil, Niket Sitaram Sharma, and Hitesh E. Chaudhari. ""VocPix: Image Captioning using CNN and LSTM"." International Journal Of Advance Research And Innovative Ideas In Education [Online]. volume 9 number 2 (19 September 2024).
Vancouver Bhushan Arun Ambhore, Linal Anil Patil, Manasi Shekhar Patil, Niket Sitaram Sharma, and Hitesh E. Chaudhari. "VocPix: Image Captioning using CNN and LSTM". International Journal Of Advance Research And Innovative Ideas In Education [Internet]. 2023 [Cited : 19 September 2024]; 9(2) : 2873-2880. Available from: https://ijariie.com/AdminUploadPdf/_VocPix__Image_Captioning_using_CNN_and_LSTM__ijariie19942.pdf
BibTex EndNote RefMan RefWorks

Number Of Downloads


Last download on 9/19/2024 2:09:48 PM

Save in Google Drive

Similar-Paper

TitleArea of ResearchAuther NameAction
A Review on Ad Makers- Creation & Design Advertising CampaignsComputer EngineeringSwapnil Ohol1 Download
DETECTING FACIAL FORGERIES USING NOVEL FREQUENCY CONVOLUTIONAL NEURAL NETWORKComputer ScienceChikati Madhava Rao Download
Detecting Diabetes Early and Classifying Risk with Interpretable Deep Learning ModelsComputer ScienceMohmad Ahmed Ali Download
Enhance Accuracy of Medical Disease Prediction Using Machine Learning TechniquesMachine LearningSandeep Singh Sikarwar Download
Transformer-based Generative Adversarial Network (GAN) hybrid model for sentiment analysisInformation Technologyhridesh kumar Download
A Step Ahead in Operational Resilience - Integrating Observability with DevOpsComputer EngineeringAmit Sengupta Download
The Influence of Artificial Intelligence and Human-Computer Interaction on Enhancing Children's Learning ExperiencesComputer Engineering,Supriya S Kendhuli Download
Medicinal Plants Identification Using Deep LearningComputer Engineering Rohan Kumar Verma Download
“How to balance automation and ethics when rolling out AI automation in an Educational Framework”Computer SciecneSudhakar mishra Download
Microservices Fault Tolerance PatternsComputer EngineeringAmit Sengupta Download
Forecasting and Categorization of Cardiac Arrhythmia using Soft Computational ApproachesComputer Science and EngineeringDr. Sivaprakash. C Download
Enhancing CybersecurityComputer EngineeringG Tarun Download
Microservices Design PatternsComputer EngineeringAmit Sengupta Download
The Novel Approach to Detect Kidney Stones Using Deep Learning and Convolutional Neural NetworksCSEN Manjunatha Download
An investigation into the use of deep learning and image processing in the domain of diabetic medical careCSEHR Ravikumar Download
12