Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

International Journal of Hybrid Intelligence

A brief survey on image segmentation based on quantum inspired neural network

Václav Snåšel, Jan Platoš, Pankaj Kumar Pal, Siddhartha Bhattacharyya

Published Jan 1, 2023• 3 citations
Publisher

Abstract

Information retrieval is a rudimentary approach which is highly solicited for image analysis research. In classical image analysis, image processing recovers the objects from the noisy images in an efficient way at the cost of substantial time complexity. Quantum computation assisted algorithms play a vital role to extract objects from binary, grey, pure or from true colour images using quantum computing principles which reduces the time complexity while improving the segmentation efficiency. These algorithms take recourse to the quantum superposition principle in achieving the task. A neuro-biological network architecture comprises of different nodes corresponding to the image pixels which are converted to the equivalent qubit neurons in the quantum inspired versions. The ability of information retrieval capability from the images by means of qubit neurons is a much-talked affair now-a-day. In this paper, the authors attempt to present a brief survey on image segmentation techniques using the state-of-the-art techniques including quantum inspired neural networks.

DOI
10.1504/ijhi.2023.129296

Related papers

A Comprehensive Survey of Quantum and Quantum-Inspired Image Segmentation in the Context of Modern Segmentation Methods

Marie Gogolin, Yannick Werner, Alexander Geng +3 more

Abstract Image segmentation remains one of the most extensively studied problems in computer vision, with applications ranging from medical image analysis and autonomous driving to remote sensing and industrial inspection. While deep learning approaches currently dominate the field, interest in quantum computing has motivated the development of quantum and quantum-inspired segmentation techniques that explore alternative strategies for image representation, optimization, and learning. This survey provides a comprehensive review of quantum and quantum-inspired image segmentation methods within the broader context of modern segmentation research. To establish this context, we first examine the evolution of image segmentation methodologies, covering classical image processing techniques, machine learning approaches, and contemporary deep learning architectures.We then organize the existing quantum image segmentation literature into four categories: quantum-inspired, tensor network-based, hybrid quantum-classical, and fully quantum methods. Across these categories, we analyze computational principles, image encoding and representation strategies, application domains, and datasets. We further compare quantum and quantum-inspired approaches with established segmentation paradigms in terms of supervision, scalability, and hardware requirements. Our analysis indicates that quantum-inspired methods currently represent the most developed direction, while hybrid approaches are emerging and fully quantum methods remain constrained by quantum hardware, data encoding costs, and scalability challenges. By connecting quantum image segmentation with the broader evolution of segmentation research, this survey provides a unified perspective on the field. It identifies current trends, open challenges, and promising future directions for researchers exploring the emerging role of quantum computing in image segmentation.

•Sep 14, 2026•0 citations

Quantum-Inspired Approaches to Computer Vision: Current State and Future Prospects

Sara Zein Alabdeen Zaki Ali, Polla Fattah, Sanar Fawzi

Computer vision is confronted with increasing computational bottlenecks and memory requirements hard to scale by normal convolutional neural networks. Quantum-inspired architectures are inspired by quantum mechanics, superposition, entanglement as well as interference to redesign visual information processing in a more efficient way. Quantum convolutional neural networks are one of the biggest improvements as they apply parameterized quantum circuits to explore several input states at a time. Quantum-inspired pruning algorithms have lowered the processing time, and quantum optical neural networks have used the wave nature of light to have parallel characteristics of features. Tensor network architectures are based on quantum physics and can be used to convert high-dimensional image data into information-rich elements and model multi-scale interactions. Hybrid quantum-classical systems can be described as using quantum-inspired processing and the reliability of established deep learning. Attention systems ensure that quantum circuits are dedicated to informative parts of an image, whereas knowledge transfer of classical models stabilizes quantum training. Nonetheless, basic constraints limit applications: the barren plateau problem, measurement overhead, preparation complexity of states and decoherence are all major challenges. The existing applications include quantum-inspired classical algorithms to physical hardware experiments. Thorough benchmarking demonstrates that the classical approaches can be much more effective than the quantum ones. Frameworks such as PennyLane extend accessibility, although best practice and careful consideration of the architecture involving the integration of quantum-inspired and classical computing is critical to realistic computer vision systems.

CRC Press eBooks•May 20, 2026•0 citations

Quantum-Inspired Neural Network For Enhanced Image Recognition

Raj. TF Michael, G. Rmesh, Moorthy Agoramoorthy +2 more

The field of quantum computing has seen significant progress in recent times, leading to the emergence of innovative methodologies across several areas, particularly in machine learning and neural networks. This research study introduces a quantum-inspired neural network (QINN) that has been particularly developed to improve image recognition capabilities. In contrast to conventional neural networks, the Quantum-inspired Neural Network (QINN) utilizes concepts derived from quantum mechanics, including superposition and entanglement, to process and encode information effectively. The paradigm we propose incorporates quantum bits (qubits) as computing units instead of traditional binary nodes, simultaneously enabling the representation of many states. Moreover, the use of the intrinsic parallelism of quantum mechanics is harnessed to provide expedited and more effective data processing, particularly within the concealed levels of the network. The researchers ran benchmark tests using well-recognized image datasets, including CIFAR-10 and ImageNet. The study's findings indicated that QINN displayed superior accuracy rates compared to traditional methods and revealed faster convergence throughout the training process. Additionally, our quantum-inspired methodology demonstrated significant efficacy in analyzing pictures containing nuanced characteristics, highlighting its potential in practical scenarios where precise identification is of utmost importance. In summary, integrating quantum principles with neural network topologies has the potential for groundbreaking advancement in image recognition skills. QINN is a groundbreaking advancement in this domain, emphasizing the unexplored capacity to use quantum phenomena for sophisticated machine learning objectives. Potential areas for future study are the expansion of network scalability to accommodate bigger datasets, exploration of security measures that are resilient against quantum threats, and investigating hybrid models that integrate both quantum and conventional paradigms to enhance overall performance.

International Conference on Intelligent Computing and Control for Engineering and Business Systems (ICCEBS)•Dec 14, 2023•20 citations

A Comparative Review of Quantum and Classical Image Segmentation Techniques: Performance, Complexity, and Future Directions

D.Subhashini, Ch. Raja, K.Raghu +3 more

Image segmentation is one of the basic operations in image processing and computer vision and has applications in the medical field, remote sensing, autonomous systems and object detection. In this paper, comparative review of quantum and classical image segmentations in terms of accuracy, precision and mean Intersection over Union (mIoU) with respect to computational parameters namely execution time, computational complexity, gate complexity, qubit requirements and scalability is presented. While classical deep learning models like U-Net and SegNet have shown excellent segmentation precision and applicability, quantum image segmentation models have the potential to benefit from the quantum parallel computing and achieve significant computational efficiency and complexity reduction. Furthermore, hybrid quantum-classical methods are analyzed, as well as their potential for balancing segmentation accuracy with computational cost. The study offers a holistic comparative approach, identifies the challenges in current research, and suggests research directions for the future to develop scalable quantum image segmentation systems.

•Sep 1, 2026•0 citations

Hybrid Quantum-Classical Neural Networks and its Hyperparameter Optimization-A Study

R Adithya, Joyline Dsa, Adarsh Rag S +1 more

In recent years, the field of machine learning has witnessed a paradigm shift with the emergence of hybrid quantum-classical neural networks. These networks combine the power of classical neural networks with the computational advantages offered by quantum variational circuits. This study presents a comprehensive survey of hybrid quantum-classical machine learning algorithms, focusing on their architecture, performance, and hyperparameter optimization techniques. Introducing the concept of hybrid quantum-classical machine learning and its significance in contemporary image classification tasks. It explores the theoretical foundations of quantum variational circuits and their integration with classical neural network architectures. Special attention is given to prominent algorithms such as Quantum Convolutional Neural Networks, Quanvolutional Neural Networks, and Quantum ResNet, each offering unique advantages in image classification tasks. A major aspect covered in this study is the hyperparameter optimization techniques employed in hybrid quantum-classical machine learning. The chapter discusses quantum-inspired optimization methods tailored for efficiently tuning the hyperparameters of complex neural network models. Through comparative analysis, the effectiveness of these optimization techniques is demonstrated in reducing computational overhead and improving model performance. Moreover, the study also delves into experimental results obtained from benchmarking hybrid quantum-classical models against traditional classical approaches. It highlights the accuracy variations observed across different quantum architectures and explores the impact of architectural permutations on model convergence. Insights gained from these experiments provide valuable guidance for researchers and practitioners seeking to leverage hybrid quantum-classical neural networks in real-world applications.

International Conference on Computing, Semiconductor, Mechatronics, Intelligent Systems and Communications (COSMIC)•Nov 22, 2024•1 citation

Quantum-Inspired Approaches in Healthcare and Bioinformatics

Sara Zein Alabdeen Zaki Ali, Polla Fattah, Sanar Fawzi

Healthcare and bioinformatics are associated with huge and high dimensionality data and inherent uncertainty. Quantum-inspired architectures are based on quantum mechanics, superposition, entanglement and interference, to redesign medical data processing operations in a more efficient way. Quantum-inspired neural networks have an initial positive response in genomics and medical imaging. Tensor network techniques compress the overall genomic sequences efficiently and quantum-inspired PCA show a small-scale improvement in feature retrieval of medical images. One of the most popular models is hybrid quantum-classical systems which are quantum-inspired processing with the reliability of the established machine learning. Nevertheless, there is a lot of poor implementations due to limitations. The existing quantum computers use noisy qubits and 0.1-1% error per qubit. Thousand to millions of logical qubits are needed to simulate drug-sized molecules with molecular simulation which will not be accessible until probably the 2030s. The basic obstacles are state preparation overhead, cost of measurement, decoherence and barren plateau problems. The most successful near-term approaches are quantum-inspired classical algorithms, tensor networks and optimization methods, in a conventional computer. These provide continuous advances in the discovery of drugs, optimization of personalized medicine and optimization of healthcare logistics without the need to have quantum hardware. Although quantum-enhanced molecular property prediction and clinical decision support are promising, clinical validation and benefits are limited and still going on. Even in the case of healthcare, it is most likely to take 10-20+ years before practical quantum advantage is realized due to quantum hardware breakthroughs and regulatory approval.

CRC Press eBooks•May 20, 2026•0 citations
Information retrieval is a rudimentary approach which is highly solicited for image analysis research. In classical image analysis, image processing recovers the objects from the noisy images in an efficient way at the cost of substantial time complexity. Quantum computation assisted algorithms play a vital role to extract objects from binary, grey, pure or from true colour images using quantum computing principles which reduces the time complexity while improving the segmentation efficiency. These algorithms take recourse to the quantum superposition principle in achieving the task. A neuro-biological network architecture comprises of different nodes corresponding to the image pixels which are converted to the equivalent qubit neurons in the quantum inspired versions. The ability of information retrieval capability from the images by means of qubit neurons is a much-talked affair now-a-day. In this paper, the authors attempt to present a brief survey on image segmentation techniques using the state-of-the-art techniques including quantum inspired neural networks.
Abstract Image segmentation remains one of the most extensively studied problems in computer vision, with applications ranging from medical image analysis and autonomous driving to remote sensing and industrial inspection. While deep learning approaches currently dominate the field, interest in quantum computing has motivated the development of quantum and quantum-inspired segmentation techniques that explore alternative strategies for image representation, optimization, and learning. This survey provides a comprehensive review of quantum and quantum-inspired image segmentation methods within the broader context of modern segmentation research. To establish this context, we first examine the evolution of image segmentation methodologies, covering classical image processing techniques, machine learning approaches, and contemporary deep learning architectures.We then organize the existing quantum image segmentation literature into four categories: quantum-inspired, tensor network-based, hybrid quantum-classical, and fully quantum methods. Across these categories, we analyze computational principles, image encoding and representation strategies, application domains, and datasets. We further compare quantum and quantum-inspired approaches with established segmentation paradigms in terms of supervision, scalability, and hardware requirements. Our analysis indicates that quantum-inspired methods currently represent the most developed direction, while hybrid approaches are emerging and fully quantum methods remain constrained by quantum hardware, data encoding costs, and scalability challenges. By connecting quantum image segmentation with the broader evolution of segmentation research, this survey provides a unified perspective on the field. It identifies current trends, open challenges, and promising future directions for researchers exploring the emerging role of quantum computing in image segmentation.
Computer vision is confronted with increasing computational bottlenecks and memory requirements hard to scale by normal convolutional neural networks. Quantum-inspired architectures are inspired by quantum mechanics, superposition, entanglement as well as interference to redesign visual information processing in a more efficient way. Quantum convolutional neural networks are one of the biggest improvements as they apply parameterized quantum circuits to explore several input states at a time. Quantum-inspired pruning algorithms have lowered the processing time, and quantum optical neural networks have used the wave nature of light to have parallel characteristics of features. Tensor network architectures are based on quantum physics and can be used to convert high-dimensional image data into information-rich elements and model multi-scale interactions. Hybrid quantum-classical systems can be described as using quantum-inspired processing and the reliability of established deep learning. Attention systems ensure that quantum circuits are dedicated to informative parts of an image, whereas knowledge transfer of classical models stabilizes quantum training. Nonetheless, basic constraints limit applications: the barren plateau problem, measurement overhead, preparation complexity of states and decoherence are all major challenges. The existing applications include quantum-inspired classical algorithms to physical hardware experiments. Thorough benchmarking demonstrates that the classical approaches can be much more effective than the quantum ones. Frameworks such as PennyLane extend accessibility, although best practice and careful consideration of the architecture involving the integration of quantum-inspired and classical computing is critical to realistic computer vision systems.
The field of quantum computing has seen significant progress in recent times, leading to the emergence of innovative methodologies across several areas, particularly in machine learning and neural networks. This research study introduces a quantum-inspired neural network (QINN) that has been particularly developed to improve image recognition capabilities. In contrast to conventional neural networks, the Quantum-inspired Neural Network (QINN) utilizes concepts derived from quantum mechanics, including superposition and entanglement, to process and encode information effectively. The paradigm we propose incorporates quantum bits (qubits) as computing units instead of traditional binary nodes, simultaneously enabling the representation of many states. Moreover, the use of the intrinsic parallelism of quantum mechanics is harnessed to provide expedited and more effective data processing, particularly within the concealed levels of the network. The researchers ran benchmark tests using well-recognized image datasets, including CIFAR-10 and ImageNet. The study's findings indicated that QINN displayed superior accuracy rates compared to traditional methods and revealed faster convergence throughout the training process. Additionally, our quantum-inspired methodology demonstrated significant efficacy in analyzing pictures containing nuanced characteristics, highlighting its potential in practical scenarios where precise identification is of utmost importance. In summary, integrating quantum principles with neural network topologies has the potential for groundbreaking advancement in image recognition skills. QINN is a groundbreaking advancement in this domain, emphasizing the unexplored capacity to use quantum phenomena for sophisticated machine learning objectives. Potential areas for future study are the expansion of network scalability to accommodate bigger datasets, exploration of security measures that are resilient against quantum threats, and investigating hybrid models that integrate both quantum and conventional paradigms to enhance overall performance.
Image segmentation is one of the basic operations in image processing and computer vision and has applications in the medical field, remote sensing, autonomous systems and object detection. In this paper, comparative review of quantum and classical image segmentations in terms of accuracy, precision and mean Intersection over Union (mIoU) with respect to computational parameters namely execution time, computational complexity, gate complexity, qubit requirements and scalability is presented. While classical deep learning models like U-Net and SegNet have shown excellent segmentation precision and applicability, quantum image segmentation models have the potential to benefit from the quantum parallel computing and achieve significant computational efficiency and complexity reduction. Furthermore, hybrid quantum-classical methods are analyzed, as well as their potential for balancing segmentation accuracy with computational cost. The study offers a holistic comparative approach, identifies the challenges in current research, and suggests research directions for the future to develop scalable quantum image segmentation systems.
In recent years, the field of machine learning has witnessed a paradigm shift with the emergence of hybrid quantum-classical neural networks. These networks combine the power of classical neural networks with the computational advantages offered by quantum variational circuits. This study presents a comprehensive survey of hybrid quantum-classical machine learning algorithms, focusing on their architecture, performance, and hyperparameter optimization techniques. Introducing the concept of hybrid quantum-classical machine learning and its significance in contemporary image classification tasks. It explores the theoretical foundations of quantum variational circuits and their integration with classical neural network architectures. Special attention is given to prominent algorithms such as Quantum Convolutional Neural Networks, Quanvolutional Neural Networks, and Quantum ResNet, each offering unique advantages in image classification tasks. A major aspect covered in this study is the hyperparameter optimization techniques employed in hybrid quantum-classical machine learning. The chapter discusses quantum-inspired optimization methods tailored for efficiently tuning the hyperparameters of complex neural network models. Through comparative analysis, the effectiveness of these optimization techniques is demonstrated in reducing computational overhead and improving model performance. Moreover, the study also delves into experimental results obtained from benchmarking hybrid quantum-classical models against traditional classical approaches. It highlights the accuracy variations observed across different quantum architectures and explores the impact of architectural permutations on model convergence. Insights gained from these experiments provide valuable guidance for researchers and practitioners seeking to leverage hybrid quantum-classical neural networks in real-world applications.
Healthcare and bioinformatics are associated with huge and high dimensionality data and inherent uncertainty. Quantum-inspired architectures are based on quantum mechanics, superposition, entanglement and interference, to redesign medical data processing operations in a more efficient way. Quantum-inspired neural networks have an initial positive response in genomics and medical imaging. Tensor network techniques compress the overall genomic sequences efficiently and quantum-inspired PCA show a small-scale improvement in feature retrieval of medical images. One of the most popular models is hybrid quantum-classical systems which are quantum-inspired processing with the reliability of the established machine learning. Nevertheless, there is a lot of poor implementations due to limitations. The existing quantum computers use noisy qubits and 0.1-1% error per qubit. Thousand to millions of logical qubits are needed to simulate drug-sized molecules with molecular simulation which will not be accessible until probably the 2030s. The basic obstacles are state preparation overhead, cost of measurement, decoherence and barren plateau problems. The most successful near-term approaches are quantum-inspired classical algorithms, tensor networks and optimization methods, in a conventional computer. These provide continuous advances in the discovery of drugs, optimization of personalized medicine and optimization of healthcare logistics without the need to have quantum hardware. Although quantum-enhanced molecular property prediction and clinical decision support are promising, clinical validation and benefits are limited and still going on. Even in the case of healthcare, it is most likely to take 10-20+ years before practical quantum advantage is realized due to quantum hardware breakthroughs and regulatory approval.