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

arXiv:2308.11112 · Journal of Data Science and Intelligent Systems

Development of a Novel Quantum Pre-processing Filter to Improve Image Classification Accuracy of Neural Network Models

Farina Riaz, Shahab Abdulla, Hajime Suzuki, Srinjoy Ganguly, Ravinesh Chand Deo, Susan Hopkins

Published May 11, 2025• 1 citation
arXivHTMLPDF

Abstract

This paper proposes a novel quantum pre-processing filter (QPF) to improve the image classification accuracy of neural network (NN) models. A simple four qubit quantum circuit that uses Y rotation gates for encoding and two controlled NOT gates for creating correlation among the qubits is applied as a feature extraction filter prior to passing data into the fully connected NN architecture. By applying the QPF approach, the results show that the image classification accuracy based on the MNIST (handwritten 10 digits) and the EMNIST (handwritten 47 class digits and letters) datasets can be improved, from 92.5% to 95.4% and from 68.9% to 75.9%, respectively. These improvements were obtained without introducing extra model parameters or optimizations in the machine learning process. However, tests performed on the developed QPF approach against a relatively complex German Traffic Sign Recognition Benchmark dataset with 43 distinct class real-life traffic sign images showed a degradation in the classification accuracy. Considering this result, further research into the understanding and the design of a more suitable quantum circuit approach for image classification NNs could be explored utilizing the baseline method proposed in this paper. Received: 2 September 2024 | Revised: 13 January 2025 | Accepted: 7 April 2025 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in GitHub at https://github.com/hajimesuzuki999/qpf. Author Contribution Statement Farina Riaz: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Project administration. Shahab Abdulla: Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Supervision. Hajime Suzuki: Methodology, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Supervision, Project administration. Srinjoy Ganguly: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Supervision, Project administration. Ravinesh C. Deo: Investigation, Resources, Data curation, Writing – review & editing, Supervision. Susan Hopkins: Writing – review & editing, Supervision.

DOI
10.47852/bonviewjdsis52024231

Related papers

The Application of Quantum Pre-processing Filter for Binary Image Classification with Small Samples

Farina Riaz, Shahab Abdulla, Hajime Suzuki +3 more

Over the past few years, there has been significant interest in quantum machine learning (QML) among researchers, as it has the potential to transform the field of machine learning. Several models that exploit the properties of quantum mechanics have been developed for practical applications. In this study, we investigated the application of our previously proposed quantum pre-processing filter (QPF) to binary image classification. We evaluated the QPF on four datasets: MNIST (handwritten digits), EMNIST (handwritten digits and alphabets), CIFAR-10 (photographic images), and GTSRB (real-life traffic sign images). Similar to our previous multi-class classification results, the application of QPF improved the binary image classification accuracy using neural network against MNIST, EMNIST, and CIFAR-10 from 98.9% to 99.2%, 97.8% to 98.3%, and 71.2% to 76.1%, respectively, but degraded it against GTSRB from 93.5% to 92.0%. We then applied QPF in cases using a smaller number of training and testing samples, i.e., 80 and 20 samples per class, respectively. In order to derive statistically stable results, we conducted the experiment with 100 trials choosing randomly different training and testing samples and averaging the results. The result showed that the application of QPF did not improve the image classification accuracy against MNIST and EMNIST but improved it against CIFAR-10 and GTSRB from 65.8% to 67.2% and 90.5% to 91.8%, respectively. Further research will be conducted as part of future work to investigate the potential of QPF to assess the scalability of the proposed approach to larger and complex datasets. Received: 2 September 2024 | Revised: 15 October 2024 | Accepted: 4 December 2024 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in GitHub at https://github.com/hajimesuzuki999/qpf-bic. Author Contribution Statement Farina Riaz: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Project administration. Shahab Abdulla: Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Supervision. Hajime Suzuki: Methodology, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Supervision, Project administration. Srinjoy Ganguly: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Supervision, Project administration. Ravinesh C. Deo: Investigation, Resources, Data curation, Writing – review & editing, Supervision. Susan Hopkins: Writing – review & editing, Supervision.

arXiv:2308.14930•Journal of Data Science and Intelligent Systems•Dec 23, 2024•4 citations

Accurate Image Multi-Class Classification Neural Network Model with Quantum Entanglement Approach

Farina Riaz, Shahab Abdulla, Hajime Suzuki +3 more

Quantum machine learning (QML) has attracted significant research attention over the last decade. Multiple models have been developed to demonstrate the practical applications of the quantum properties. In this study, we first demonstrate that the previously proposed quanvolutional neural network (QuanvNN) using a randomly generated quantum circuit improves the image classification accuracy of a fully connected neural network against the Modified National Institute of Standards and Technology (MNIST) dataset and the Canadian Institute for Advanced Research 10 class (CIFAR-10) dataset from 92.0% to 93.0% and from 30.5% to 34.9%, respectively. We then propose a new model referred to as a Neural Network with Quantum Entanglement (NNQE) using a strongly entangled quantum circuit combined with Hadamard gates. The new model further improves the image classification accuracy of MNIST and CIFAR-10 to 93.8% and 36.0%, respectively. Unlike other QML methods, the proposed method does not require optimization of the parameters inside the quantum circuits; hence, it requires only limited use of the quantum circuit. Given the small number of qubits and relatively shallow depth of the proposed quantum circuit, the proposed method is well suited for implementation in noisy intermediate-scale quantum computers. While promising results were obtained by the proposed method when applied to the MNIST and CIFAR-10 datasets, a test against a more complicated German Traffic Sign Recognition Benchmark (GTSRB) dataset degraded the image classification accuracy from 82.2% to 73.4%. The exact causes of the performance improvement and degradation are currently an open question, prompting further research on the understanding and design of suitable quantum circuits for image classification neural networks for colored and complex data.

Sensors•Mar 2, 2023•35 citations

Quantum-Enhanced Convolutional Neural Networks for Image Classification

Tariq Qayyum, Asadullah Tariq, Muhammad Waqas Haseeb +3 more

In recent years, there has been a growing interest in leveraging the unique properties of quantum computing to develop novel machine learning algorithms and architectures. This research paper presents an investigation of quantum convolutional neural networks (QCNNs), which leverage the unique properties of quantum computing to potentially improve the accuracy and efficiency of image classification tasks. Specifically, the paper explores three different QCNN architectures, including a pure quantum-based QCNN, a hybrid QCNN with a single quantum convolution layer, and a hybrid convolutional architecture with multiple quantum filters. We tested the models on MNIST dataset and the results of the study demonstrate that hybrid architectures that combine quantum and classical processing are more effective than pure quantum-based architectures in image classification tasks. In particular, the third model, the Hybrid Convolution with Multiple Quantum Filters, achieved the highest test set accuracy of 92.7%. The use of multiple quantum filters in conjunction with a classical neural network resulted in enhanced accuracy and efficiency in image classification tasks, highlighting the potential of hybrid architectures for future applications in machine learning tasks.

IEEE Future Networks World Forum (FNWF)•Nov 13, 2023•6 citations

Quantum Generative Adversarial Network and Quantum Neural Network for Image Classification

Arun Pandian J, K. Kanchanadevi, Vadem Chandu Mohan +2 more

In this paper, a Quantum Neural Network (QNN) has been proposed using the Projected Quantum Kernel feature for an image classification task. The QCNN consists of four dense layers; the first layer collects the quantum data as an input and the fourth layer produced the classification output. Moreover, a Quantum Generative Advisory Network (QGAN) has been developed using the patching technique for enhancing the number of samples in the image dataset. The proposed QNN and QGAN are constructed using quantum filters. The MNIST handwritten digit dataset was used to train and test the QNN model performance on image classification. A binary classification dataset was created from the MNIST handwritten digit database using digits 0 and 6. The QGAN generated 221 samples on digits 0 and 6 classes. The generated samples were added to the training dataset for the QNN model. The size of the Filtered MNIST handwritten dataset was extended from 13779 to 14000 samples. There are 12,000 images are split for training and 2,000 images for testing. The principal component analysis technique was used to reduce the dimension of the data. The QNN was trained on the enhanced dataset using a GPU environment. The testing accuracy of the QNN model was 98.65 percent; it is superior to the traditional neural network.

International Conference on Sustainable Computing and Data Communication Systems (ICSCDS)•Apr 7, 2022•8 citations

Handwritten Numeric Image Classification with Quantum Neural Network using Quantum Computer Circuit Simulator

Achmad Benny Mutiara, Muhammad Amir, Rina Refianti +1 more

Quantum Computer is a computer machine using principles of quantum mechanics in doing its computation. The Quantum Computer Machine itself is still in the development stage and has not been deployed yet, however TensorFlow provides a library for hybrid quantum-classical machine learning called TensorFlow Quantum (TFQ). One of the quantum computing models is the Quantum Neural Network (QNN). QNN is adapted from classical neural networks capable of processing qubit data and passing quantum circuits. QNN is a machine learning model that allows quantum computers to classify image data. The image data used is classical data, but classical data cannot reach a superposition state. So in order to carry out this protocol, the data must be readable into a quantum device that provides superposition. QNN uses a supervised learning method to predict image data. Quantum Neural Network (QNN) with a supervised learning method for classifying handwritten numeric image data is implemented using a quantum computer circuit simulation using the Python 3.6 programming language. The quantum computer circuit simulation is designed using library Cirq and TFQ. The classification process is carried out on Google Colab. The results of training on the QNN model obtained a value of 0.337 for the loss value and 0.3427 for the validation loss value. Meanwhile, the hinge accuracy value from the training results is 0.8603 for the hinge accuracy value with training data and 0.8669 for the hinge accuracy validation value. Model testing is done by providing 100 handwritten number images that are tested, with 53 image data of number three and 47 image data of number six. The results obtained for the percentage of testing accuracy are 100% for the number three image and 100% for the number six image. Thus, the total percentage of testing is 100%.

International Journal of Advanced Computer Science and Applications•Jan 1, 2020•5 citations

Design of quantum filter for hybrid quantum-classical convolutional neural networks

Yunqian Wang, Chao Chen, Wei Huang

Convolutional neural networks are widely used in image recognition problems as they have many advantages compared to other techniques. Parametrized quantum circuit, at the same time, is widely used for supervised learning task like images classification. Here we design two quantum filters for hybrid quantum-classical convolutional neural network for image recognition tasks using parametrized quantum circuit. We demonstrate the potential of these quantum filters by applying them to UCI digits dataset, and show that the hybrid quantum-classical convolutional neural network can accomplish classification tasks with a high learning accuracy. To explore how the quantum filter enhances the feature mapping process, we carry out a series of simulation experiments on different parametrized quantum circuit structure, quantum filter depth, and tasks of varying difficulty. The proposed quantum filters achieve excellent classification accuracy under a limited number of qubits available in current hardware, indicating the promising application potential of it in image recognition.

International Conference on Information Technology and Biomedical Engineering (ICITBE)•Dec 1, 2021•1 citation
This paper proposes a novel quantum pre-processing filter (QPF) to improve the image classification accuracy of neural network (NN) models. A simple four qubit quantum circuit that uses Y rotation gates for encoding and two controlled NOT gates for creating correlation among the qubits is applied as a feature extraction filter prior to passing data into the fully connected NN architecture. By applying the QPF approach, the results show that the image classification accuracy based on the MNIST (handwritten 10 digits) and the EMNIST (handwritten 47 class digits and letters) datasets can be improved, from 92.5% to 95.4% and from 68.9% to 75.9%, respectively. These improvements were obtained without introducing extra model parameters or optimizations in the machine learning process. However, tests performed on the developed QPF approach against a relatively complex German Traffic Sign Recognition Benchmark dataset with 43 distinct class real-life traffic sign images showed a degradation in the classification accuracy. Considering this result, further research into the understanding and the design of a more suitable quantum circuit approach for image classification NNs could be explored utilizing the baseline method proposed in this paper. Received: 2 September 2024 | Revised: 13 January 2025 | Accepted: 7 April 2025 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in GitHub at https://github.com/hajimesuzuki999/qpf. Author Contribution Statement Farina Riaz: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Project administration. Shahab Abdulla: Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Supervision. Hajime Suzuki: Methodology, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Supervision, Project administration. Srinjoy Ganguly: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Supervision, Project administration. Ravinesh C. Deo: Investigation, Resources, Data curation, Writing – review & editing, Supervision. Susan Hopkins: Writing – review & editing, Supervision.
Over the past few years, there has been significant interest in quantum machine learning (QML) among researchers, as it has the potential to transform the field of machine learning. Several models that exploit the properties of quantum mechanics have been developed for practical applications. In this study, we investigated the application of our previously proposed quantum pre-processing filter (QPF) to binary image classification. We evaluated the QPF on four datasets: MNIST (handwritten digits), EMNIST (handwritten digits and alphabets), CIFAR-10 (photographic images), and GTSRB (real-life traffic sign images). Similar to our previous multi-class classification results, the application of QPF improved the binary image classification accuracy using neural network against MNIST, EMNIST, and CIFAR-10 from 98.9% to 99.2%, 97.8% to 98.3%, and 71.2% to 76.1%, respectively, but degraded it against GTSRB from 93.5% to 92.0%. We then applied QPF in cases using a smaller number of training and testing samples, i.e., 80 and 20 samples per class, respectively. In order to derive statistically stable results, we conducted the experiment with 100 trials choosing randomly different training and testing samples and averaging the results. The result showed that the application of QPF did not improve the image classification accuracy against MNIST and EMNIST but improved it against CIFAR-10 and GTSRB from 65.8% to 67.2% and 90.5% to 91.8%, respectively. Further research will be conducted as part of future work to investigate the potential of QPF to assess the scalability of the proposed approach to larger and complex datasets. Received: 2 September 2024 | Revised: 15 October 2024 | Accepted: 4 December 2024 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in GitHub at https://github.com/hajimesuzuki999/qpf-bic. Author Contribution Statement Farina Riaz: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Project administration. Shahab Abdulla: Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Supervision. Hajime Suzuki: Methodology, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Supervision, Project administration. Srinjoy Ganguly: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Supervision, Project administration. Ravinesh C. Deo: Investigation, Resources, Data curation, Writing – review & editing, Supervision. Susan Hopkins: Writing – review & editing, Supervision.
Quantum machine learning (QML) has attracted significant research attention over the last decade. Multiple models have been developed to demonstrate the practical applications of the quantum properties. In this study, we first demonstrate that the previously proposed quanvolutional neural network (QuanvNN) using a randomly generated quantum circuit improves the image classification accuracy of a fully connected neural network against the Modified National Institute of Standards and Technology (MNIST) dataset and the Canadian Institute for Advanced Research 10 class (CIFAR-10) dataset from 92.0% to 93.0% and from 30.5% to 34.9%, respectively. We then propose a new model referred to as a Neural Network with Quantum Entanglement (NNQE) using a strongly entangled quantum circuit combined with Hadamard gates. The new model further improves the image classification accuracy of MNIST and CIFAR-10 to 93.8% and 36.0%, respectively. Unlike other QML methods, the proposed method does not require optimization of the parameters inside the quantum circuits; hence, it requires only limited use of the quantum circuit. Given the small number of qubits and relatively shallow depth of the proposed quantum circuit, the proposed method is well suited for implementation in noisy intermediate-scale quantum computers. While promising results were obtained by the proposed method when applied to the MNIST and CIFAR-10 datasets, a test against a more complicated German Traffic Sign Recognition Benchmark (GTSRB) dataset degraded the image classification accuracy from 82.2% to 73.4%. The exact causes of the performance improvement and degradation are currently an open question, prompting further research on the understanding and design of suitable quantum circuits for image classification neural networks for colored and complex data.
In recent years, there has been a growing interest in leveraging the unique properties of quantum computing to develop novel machine learning algorithms and architectures. This research paper presents an investigation of quantum convolutional neural networks (QCNNs), which leverage the unique properties of quantum computing to potentially improve the accuracy and efficiency of image classification tasks. Specifically, the paper explores three different QCNN architectures, including a pure quantum-based QCNN, a hybrid QCNN with a single quantum convolution layer, and a hybrid convolutional architecture with multiple quantum filters. We tested the models on MNIST dataset and the results of the study demonstrate that hybrid architectures that combine quantum and classical processing are more effective than pure quantum-based architectures in image classification tasks. In particular, the third model, the Hybrid Convolution with Multiple Quantum Filters, achieved the highest test set accuracy of 92.7%. The use of multiple quantum filters in conjunction with a classical neural network resulted in enhanced accuracy and efficiency in image classification tasks, highlighting the potential of hybrid architectures for future applications in machine learning tasks.
In this paper, a Quantum Neural Network (QNN) has been proposed using the Projected Quantum Kernel feature for an image classification task. The QCNN consists of four dense layers; the first layer collects the quantum data as an input and the fourth layer produced the classification output. Moreover, a Quantum Generative Advisory Network (QGAN) has been developed using the patching technique for enhancing the number of samples in the image dataset. The proposed QNN and QGAN are constructed using quantum filters. The MNIST handwritten digit dataset was used to train and test the QNN model performance on image classification. A binary classification dataset was created from the MNIST handwritten digit database using digits 0 and 6. The QGAN generated 221 samples on digits 0 and 6 classes. The generated samples were added to the training dataset for the QNN model. The size of the Filtered MNIST handwritten dataset was extended from 13779 to 14000 samples. There are 12,000 images are split for training and 2,000 images for testing. The principal component analysis technique was used to reduce the dimension of the data. The QNN was trained on the enhanced dataset using a GPU environment. The testing accuracy of the QNN model was 98.65 percent; it is superior to the traditional neural network.
Quantum Computer is a computer machine using principles of quantum mechanics in doing its computation. The Quantum Computer Machine itself is still in the development stage and has not been deployed yet, however TensorFlow provides a library for hybrid quantum-classical machine learning called TensorFlow Quantum (TFQ). One of the quantum computing models is the Quantum Neural Network (QNN). QNN is adapted from classical neural networks capable of processing qubit data and passing quantum circuits. QNN is a machine learning model that allows quantum computers to classify image data. The image data used is classical data, but classical data cannot reach a superposition state. So in order to carry out this protocol, the data must be readable into a quantum device that provides superposition. QNN uses a supervised learning method to predict image data. Quantum Neural Network (QNN) with a supervised learning method for classifying handwritten numeric image data is implemented using a quantum computer circuit simulation using the Python 3.6 programming language. The quantum computer circuit simulation is designed using library Cirq and TFQ. The classification process is carried out on Google Colab. The results of training on the QNN model obtained a value of 0.337 for the loss value and 0.3427 for the validation loss value. Meanwhile, the hinge accuracy value from the training results is 0.8603 for the hinge accuracy value with training data and 0.8669 for the hinge accuracy validation value. Model testing is done by providing 100 handwritten number images that are tested, with 53 image data of number three and 47 image data of number six. The results obtained for the percentage of testing accuracy are 100% for the number three image and 100% for the number six image. Thus, the total percentage of testing is 100%.
Convolutional neural networks are widely used in image recognition problems as they have many advantages compared to other techniques. Parametrized quantum circuit, at the same time, is widely used for supervised learning task like images classification. Here we design two quantum filters for hybrid quantum-classical convolutional neural network for image recognition tasks using parametrized quantum circuit. We demonstrate the potential of these quantum filters by applying them to UCI digits dataset, and show that the hybrid quantum-classical convolutional neural network can accomplish classification tasks with a high learning accuracy. To explore how the quantum filter enhances the feature mapping process, we carry out a series of simulation experiments on different parametrized quantum circuit structure, quantum filter depth, and tasks of varying difficulty. The proposed quantum filters achieve excellent classification accuracy under a limited number of qubits available in current hardware, indicating the promising application potential of it in image recognition.