Hybrid Quantum-Classical Image Processing by Merging Enhanced Flexible Qubit Representation for Quantum Images equipped with Probability Distribution (EFQRQI-PD) and Machine Learning for Enhanced Accuracy

Image processing principles and techniques represent a significant advancement in modern technology, offering invaluable contributions to numerous sectors. Despite their efficacy, conventional AI and ML-based image processing algorithms encounter inherent limitations that obstruct their scalability and performance. The main aim of the proposed research project is to develop image processing algorithm based on quantum computing and machine learning principles, utilizing amplitude encoding for transition between classical bits and qubits. This initiative seeks to meet the urgent requirement for developing effective image processing techniques by crafting a system capable of efficiently predicting unseen patterns. By achieving this goal, the project aims to significantly enhance the efficiency and accuracy of image processing tasks, thereby enabling more informed decision-making and promotion developments in various fields reliant on visual data analysis. The team involved in this project has an existing research partnership. This partnership is focused on advancing the field of quantum image processing and creating theoretical algorithms. This partnership involves joint research, sharing of knowledge, and co-authoring papers in respected academic journals and conferences.

Faculty Supervisor:

Ajmery Sultana

Student:

Partner:

Vellore Institute of Technology

Discipline:

Computer science

Sector:

Quantum Science; Technology; Artificial Intelligence

University:

Algoma University

Program: