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 Information Technology

Leveraging Quantum computing for synthetic image generation and recognition with Generative Adversarial Networks and Convolutional Neural Networks

Roopa Golchha, Gyanendra K. Verma

Published Apr 9, 2024• 13 citations
Publisher
DOI
10.1007/s41870-024-01835-9

Related papers

A Deep Learning-Based Target Recognition Method for Entangled Optical Quantum Imaging System

Yong Wang, Huishi Xia, Mu Zhou +2 more

Quantum imaging has the characteristics of non-locality and strong anti-interference ability, and it has received much attention. However, the target after entangled optical quantum imaging loses its local appearance structure, and it is difficult to be recognized accurately. Therefore, this paper proposes a denoise and target recognition method for entangled optical quantum imaging system. Specifically, we design the restore conditional generative adversarial network (RestoreCGAN) to restore and reconstruct the missing edge contour structure of the target. Then, we design the two-stream feature fusion convolutional neural network (TSFFCNet) to extract deep semantic features and shallow features for target recognition. The experimental results show that RestoreCGAN outperforms the state-of-the-art methods in terms of both PSNR and SSIM. Moreover, the recognition accuracy of the RestoreCGAN in combination with the TSFFCNet reaches 97.42%. This proves that the deep learning method is effective for denoise and target recognition of entangled optical quantum imaging system.

IEEE Transactions on Instrumentation and Measurement•Jan 1, 2023•8 citations

High resolution image generation based on quantum generative adversarial networks

Yunwei Deng, Mingxuan Chen, Chen Gong +1 more

Computer Vision and Image Understanding•Jul 29, 2026•2 citations

Enhancing Generative AI Models Through Quantum Computing for Improved Text and Image Generation

Manthan Jindal

•Jan 1, 2025•1 citation

Analysis of Influencing Factors in Digital Image Recognition Based on Quantum Convolutional Neural Networks

Jing Wang, Meng Zhang, Junsen Lai +1 more

Quantum Convolutional Neural Network (QCNN) is an integration of classical convolutional neural networks and quantum computing, designed to leverage the unique advantages of quantum computing to enhance machine learning models. It holds promise for providing novel perspectives in solving complex pattern recognition tasks. In the process of image recognition, factors such as the type of convolutional layers, pooling layers, and sample sets significantly influence the recognition results. This study conducts experimental validation on QCNN-based image recognition, investigating the impact of different convolutional layer types, pooling layer types, and image sample datasets on the accuracy of QCNN recognition. Additionally, future development trends of QCNN are discussed.

International Conference on Optical Communications and Networks (ICOCN)•Jul 28, 2025•1 citation

State of the Art an Hybrid Fast Deep Learning Approach:h-QGAN for Healthcare Image Data

Chapala Maharana, Ch. Sanjeev Kumar Dash, Ajit Ku. Behera

We find machine learning applications in healthcare industry, business intelligence, natural language processing, image processing, robotics, production industry management and monitoring, space craft analytics. We have used one of the hybrid deep learning models for image data analytics in healthcare. This implementation is made using quantum GAN (generative adversarial network). Quantum computer has the advantage of processing data ata faster rate than classical computers. It uses qubits than bits to represent the data in a smallerdimension than the existing higher dimension of the original data and found effective than classical computers in terms of data processing speed. The healthcare image data is found in fewer amounts and of low quality. Generative adversarial network is used to generate synthetic data for rarehealthcare image data. GAN with quantum latent space called quantum generative adversarial network (QGAN) is used to generate high amount of image data ata faster rate. It makes the decision making with better accuracy than classical convolutional neural network approach. The proposed work is a combination of QGAN which is combination of QGAN and QNN called hybrid QGAN (h-GAN) learning from Covid-19 lungs image datasets from kaggle repository.

OITS International Conference on Information Technology (OCIT)•Dec 18, 2025•0 citations

Quantum Generative Algorithms and Networks for image synthesis, optimization, and analysis to address classification problems

Sarvapriya M. Tripathi

•Apr 21, 2026•0 citations
Quantum imaging has the characteristics of non-locality and strong anti-interference ability, and it has received much attention. However, the target after entangled optical quantum imaging loses its local appearance structure, and it is difficult to be recognized accurately. Therefore, this paper proposes a denoise and target recognition method for entangled optical quantum imaging system. Specifically, we design the restore conditional generative adversarial network (RestoreCGAN) to restore and reconstruct the missing edge contour structure of the target. Then, we design the two-stream feature fusion convolutional neural network (TSFFCNet) to extract deep semantic features and shallow features for target recognition. The experimental results show that RestoreCGAN outperforms the state-of-the-art methods in terms of both PSNR and SSIM. Moreover, the recognition accuracy of the RestoreCGAN in combination with the TSFFCNet reaches 97.42%. This proves that the deep learning method is effective for denoise and target recognition of entangled optical quantum imaging system.
Quantum Convolutional Neural Network (QCNN) is an integration of classical convolutional neural networks and quantum computing, designed to leverage the unique advantages of quantum computing to enhance machine learning models. It holds promise for providing novel perspectives in solving complex pattern recognition tasks. In the process of image recognition, factors such as the type of convolutional layers, pooling layers, and sample sets significantly influence the recognition results. This study conducts experimental validation on QCNN-based image recognition, investigating the impact of different convolutional layer types, pooling layer types, and image sample datasets on the accuracy of QCNN recognition. Additionally, future development trends of QCNN are discussed.
We find machine learning applications in healthcare industry, business intelligence, natural language processing, image processing, robotics, production industry management and monitoring, space craft analytics. We have used one of the hybrid deep learning models for image data analytics in healthcare. This implementation is made using quantum GAN (generative adversarial network). Quantum computer has the advantage of processing data ata faster rate than classical computers. It uses qubits than bits to represent the data in a smallerdimension than the existing higher dimension of the original data and found effective than classical computers in terms of data processing speed. The healthcare image data is found in fewer amounts and of low quality. Generative adversarial network is used to generate synthetic data for rarehealthcare image data. GAN with quantum latent space called quantum generative adversarial network (QGAN) is used to generate high amount of image data ata faster rate. It makes the decision making with better accuracy than classical convolutional neural network approach. The proposed work is a combination of QGAN which is combination of QGAN and QNN called hybrid QGAN (h-GAN) learning from Covid-19 lungs image datasets from kaggle repository.