A Proposed Approach for AI Doodle Generation with a Hybrid Intelligent Agent

Dyaneshwar Bavakar; Ramesh Shahabade; Vishal Vilas Shinde; Bhargav Vivek Modak; Manas Narendra Telavane; Shantanu Parameswara

doi:10.36948/ijfmr.2024.v06i02.17871

A Proposed Approach for AI Doodle Generation with a Hybrid Intelligent Agent

Author(s)	Dyaneshwar Bavakar, Ramesh Shahabade, Vishal Vilas Shinde, Bhargav Vivek Modak, Manas Narendra Telavane, Shantanu Parameswara
Country	India
Abstract	Doodles are a form of human expression and communication that capture the essence of concepts and emotions in a simple and intuitive way. However, generating doodles from natural language descriptions is a challenging task that requires both understanding the meaning and context of the input, and producing the appropriate strokes and shapes of the output. In this paper, we present our approach to tackle this problem. Our proposed system leverages the vector-based nature of doodles and the semantic relationships of words. We propose use of a dataset of arrays of coordinates as drawn by humans (stored as vectors) to train our agent. There are several mechanisms that enable the agent to handle different aspects of the task, such as input word filtering, semantic mapping and keyword weighing, finding out closest words to input in the agent’s dictionary using vector embeddings, running one or multiple deep learning models in parallel depending on the number of objects, using the semantic mappings to train the assembler to linearly translate, transform or scale objects as per their semantic positional relationship, and using the turtle to draw the objects on a canvas. We identify and outline possible benchmarks, tests to evaluate the performance and quality of the agent using various metrics and user feedback. We also discuss the potential applications and implications of such an agent, such as art and design, education, and therapy.
Keywords	Artificial intelligence, Doodle Generation, Hybrid intelligent systems, Intelligent systems, Multi-agent systems, Natural language processing, Neural networks, Semantic search, Vector images.
Field	Engineering
Published In	Volume 6, Issue 2, March-April 2024
Published On	2024-04-22
Cite This	A Proposed Approach for AI Doodle Generation with a Hybrid Intelligent Agent - Dyaneshwar Bavakar, Ramesh Shahabade, Vishal Vilas Shinde, Bhargav Vivek Modak, Manas Narendra Telavane, Shantanu Parameswara - IJFMR Volume 6, Issue 2, March-April 2024. DOI 10.36948/ijfmr.2024.v06i02.17871
DOI	https://doi.org/10.36948/ijfmr.2024.v06i02.17871
Short DOI	https://doi.org/gtrstx

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Copyright Permission Form and Undertaking Form Cover Page Vol 6 Isu 2 Cover Page Vol 6 Isu 1 Cover Page Vol 5 Isu 6 Research Paper Format

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9898-5948-55	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

A Proposed Approach for AI Doodle Generation with a Hybrid Intelligent Agent

Share this