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

IEEE Information Technology, Networking, Electronic and Automation Control Conference (ITNEC)

Handwritten numeral recognition with a quantum neural network model

Mao Yaxuan, Kazuyuki Aihara

Published Dec 1, 2017• 0 citations
Publisher

Abstract

Handwritten numeral recognition has generated significant interest in last several years owing to its sundry application potentials in the fields of image processing and computer vision. Recently, quantum neural networks (QNN) have been found to be efficient for information processing, such as image classification, recognition and optimization, owing to its distinct features. Therefore, in this study, a QNN based handwritten character recognition system is studied. Experiments are conducted with the data from the MNIST database. Back-propagation (BP) algorithm and particle swarm optimization (PSO) algorithm are used during the training process to improve the performance of the QNN. The resulting recognition rate of this proposed system is up to 99.16%. The results of the experiments clearly demonstrate the superiority of the proposed QNN in terms of its convergence speed and recognition rate as compared to other classical recognition methods, and simultaneously show the superiority of the QNN in solving character recognition problems.

DOI
10.1109/itnec.2017.8284824

Related papers

Handwritten digital recognition method based on quantum neural networks

Li Peng

The handwritten digital recognition is an important problem of pattern recognition field. An approach to handwritten digital recognition is presented based on multi-level transfer function quantum neural networks (QNN) and multi-layer classifiers. The QNN is trained and tested by the MNIST database. The experimental results indicate the method achieves excellent performance in terms of recognition rates and recognition reliability, and show the superiority and potential of QNN in solving pattern recognition problems.

Jisuanji gongcheng yu sheji•Jan 1, 2007•2 citations

A Multi-layer Quantum Neural Networks Recognition System for Handwritten Digital Recognition

Daqi Zhu, Rushi Wu

In this paper, a handwritten digital recognition system based on multi-level transfer function quantum neural networks (QNN) and multi-layer classifiers is proposed. The recognition system proposed consists of two layer sub-classifiers, namely first-layer QNN coarse classifier and second-layer QNN numeral pairs classifier. Handwritten digital recognition experiments are performed by using data from MNIST database. Experiment results indicate the proposed QNN recognition system achieves excellent performance in terms of recognition rates and recognition reliability, and at the same time show the superiority and potential of QNN in solving pattern recognition problems.

International Conference on Natural Computation (ICNC)•Jan 1, 2007•13 citations

An Optimized Hybrid Quantum-Classical Neural Network Model for Handwritten Digit Classification

Vu-Quoc-Minh Nguyen, Trung-Khanh Le, Trong-Tu Bui +1 more

Quantum computers are the latest dream of humans in solving nondeterministic polynomial problems. These problems include machine learning and object classification. However, commercial quantum computers are still not available. In the meantime, scientists developed hybrid models by combining Convolutional Neural Networks (CNN) and Quantum Neural Networks (QNN) to apply quantum computing to artificial intelligence (AI) applications. The hybrid model accelerates the processing of an AI machine by combining the advantage of CNN in feature extraction with the parallel computing capability of QNN. In this study, we optimized the existing hybrid models with a fewer number of qubits to improve the performance of QNN on digit recognition. The study also presents the implementation of the model using Qiskit, describes the training process, and analyzes the impact of the number of qubits and quantum gates on the classification results. Experiments show that Hybrid Quantum-Classical Neural Networks (H-QNN) have the potential to outperform pure CNN. Finally, the study suggests future improvements, including the optimization of quantum algorithms and extending experiments to more complex data sets.

International Conference on Integrated Circuits, Design, and Verification (ICDV)•Jun 16, 2025•0 citations

Handwritten digit recognition using quantum convolution neural network

Ravuri Daniel, B. Prasad, Prudhvi Kiran Pasam +3 more

The recognition of handwritten digits holds a significant place in the field of information processing. Recognizing such characters accurately from images is a complex task because of the vast differences in people's writing styles. Furthermore, the presence of various image artifacts such as blurring, intensity variations, and noise adds to the complexity of this process. The existing algorithm, convolution neural network (CNN) is one of the prominent algorithms in deep learning to handle the above problems. But there is a difficulty in handling input data that differs significantly from the training data, leading to decreased accuracy and performance. In this work, a method is proposed to overcome the aforementioned limitations by incorporating a quantum convolutional neural network algorithm (QCNN). QCNN is capable of performing more complex operations than classical CNNs. It can achieve higher levels of accuracy than classical CNNs, especially when working with noisy or incomplete data. It has the potential to scale more efficiently and effectively than classical CNNs, making them better suited for large-scale applications. The effectiveness of the proposed model is demonstrated on the modified national institute of standards and technology (MNIST) dataset and achieved an average accuracy of 91.08%.

IAES International Journal of Artificial Intelligence•Nov 30, 2023•7 citations

Implementation of Handwritten Character Recognition using Quanvolutional Neural Network

Annapurna P Patil, Sharmishtha Pandey, Nikunj Das Kasat +3 more

Image classification is the process in which a computer can perform analysis on an image and identify the class in which that particular image falls under. In conventional classification models (Convolutional Neural Networks or CNN), data collection and processing takes a large amount of time in days or even weeks. CNN models also have less scalability and require a lot of resources. To overcome this problem, quantum computing can be used not just for enhancing the scalability but it also provides exponential speedups because they have the ability to perform massively parallel computations. The problem with the CNNs is that they need large numbers of parameters and run into an overfitting problem with small datasets. This work is an implementation of Quanvolutional Neural Networks (QNN), which is a quantum-hybrid model, to recognise English characters using EMNIST letters dataset for training. The results of this model are then compared to a CNN model in terms of accuracy and loss. The results show that the use of a quantum layer can significantly increase the accuracy as well as decrease the training time of a classification model.

IEEE North Karnataka Subsection Flagship International Conference (NKCon)•Nov 20, 2022•4 citations

Quantum Neural Network in Recognition of Handwritten Numerals

Jie Zhou, QIANG GAN, Adam Krzyżak +1 more

This paper adopts a new kind of neural network — Quantum Neural Network (QNN) to recognize handwritten numerals. QNN combines the advantages of neural modelling and fuzzy theoretic principles. Novel experiments have been designed for the in-depth studies of applying the QNN to both synthesized confusing images and real data. Tests on synthesized data examine QNN's fuzzy feature space with an intention to illustrate its mechanism and characteristics, while studies on real data prove its great potential as a handwritten numeral classifier and the special role it plays in the multi-expert systems. Detailed comparisons and analyses of experimental results are given. An effective decision-fusion system is proposed and high reliability of 99.10% has been accomplished.

Series in machine perception and artificial intelligence•Jun 1, 1999•6 citations
Handwritten numeral recognition has generated significant interest in last several years owing to its sundry application potentials in the fields of image processing and computer vision. Recently, quantum neural networks (QNN) have been found to be efficient for information processing, such as image classification, recognition and optimization, owing to its distinct features. Therefore, in this study, a QNN based handwritten character recognition system is studied. Experiments are conducted with the data from the MNIST database. Back-propagation (BP) algorithm and particle swarm optimization (PSO) algorithm are used during the training process to improve the performance of the QNN. The resulting recognition rate of this proposed system is up to 99.16%. The results of the experiments clearly demonstrate the superiority of the proposed QNN in terms of its convergence speed and recognition rate as compared to other classical recognition methods, and simultaneously show the superiority of the QNN in solving character recognition problems.
The handwritten digital recognition is an important problem of pattern recognition field. An approach to handwritten digital recognition is presented based on multi-level transfer function quantum neural networks (QNN) and multi-layer classifiers. The QNN is trained and tested by the MNIST database. The experimental results indicate the method achieves excellent performance in terms of recognition rates and recognition reliability, and show the superiority and potential of QNN in solving pattern recognition problems.
In this paper, a handwritten digital recognition system based on multi-level transfer function quantum neural networks (QNN) and multi-layer classifiers is proposed. The recognition system proposed consists of two layer sub-classifiers, namely first-layer QNN coarse classifier and second-layer QNN numeral pairs classifier. Handwritten digital recognition experiments are performed by using data from MNIST database. Experiment results indicate the proposed QNN recognition system achieves excellent performance in terms of recognition rates and recognition reliability, and at the same time show the superiority and potential of QNN in solving pattern recognition problems.
Quantum computers are the latest dream of humans in solving nondeterministic polynomial problems. These problems include machine learning and object classification. However, commercial quantum computers are still not available. In the meantime, scientists developed hybrid models by combining Convolutional Neural Networks (CNN) and Quantum Neural Networks (QNN) to apply quantum computing to artificial intelligence (AI) applications. The hybrid model accelerates the processing of an AI machine by combining the advantage of CNN in feature extraction with the parallel computing capability of QNN. In this study, we optimized the existing hybrid models with a fewer number of qubits to improve the performance of QNN on digit recognition. The study also presents the implementation of the model using Qiskit, describes the training process, and analyzes the impact of the number of qubits and quantum gates on the classification results. Experiments show that Hybrid Quantum-Classical Neural Networks (H-QNN) have the potential to outperform pure CNN. Finally, the study suggests future improvements, including the optimization of quantum algorithms and extending experiments to more complex data sets.
The recognition of handwritten digits holds a significant place in the field of information processing. Recognizing such characters accurately from images is a complex task because of the vast differences in people's writing styles. Furthermore, the presence of various image artifacts such as blurring, intensity variations, and noise adds to the complexity of this process. The existing algorithm, convolution neural network (CNN) is one of the prominent algorithms in deep learning to handle the above problems. But there is a difficulty in handling input data that differs significantly from the training data, leading to decreased accuracy and performance. In this work, a method is proposed to overcome the aforementioned limitations by incorporating a quantum convolutional neural network algorithm (QCNN). QCNN is capable of performing more complex operations than classical CNNs. It can achieve higher levels of accuracy than classical CNNs, especially when working with noisy or incomplete data. It has the potential to scale more efficiently and effectively than classical CNNs, making them better suited for large-scale applications. The effectiveness of the proposed model is demonstrated on the modified national institute of standards and technology (MNIST) dataset and achieved an average accuracy of 91.08%.
Image classification is the process in which a computer can perform analysis on an image and identify the class in which that particular image falls under. In conventional classification models (Convolutional Neural Networks or CNN), data collection and processing takes a large amount of time in days or even weeks. CNN models also have less scalability and require a lot of resources. To overcome this problem, quantum computing can be used not just for enhancing the scalability but it also provides exponential speedups because they have the ability to perform massively parallel computations. The problem with the CNNs is that they need large numbers of parameters and run into an overfitting problem with small datasets. This work is an implementation of Quanvolutional Neural Networks (QNN), which is a quantum-hybrid model, to recognise English characters using EMNIST letters dataset for training. The results of this model are then compared to a CNN model in terms of accuracy and loss. The results show that the use of a quantum layer can significantly increase the accuracy as well as decrease the training time of a classification model.
This paper adopts a new kind of neural network — Quantum Neural Network (QNN) to recognize handwritten numerals. QNN combines the advantages of neural modelling and fuzzy theoretic principles. Novel experiments have been designed for the in-depth studies of applying the QNN to both synthesized confusing images and real data. Tests on synthesized data examine QNN's fuzzy feature space with an intention to illustrate its mechanism and characteristics, while studies on real data prove its great potential as a handwritten numeral classifier and the special role it plays in the multi-expert systems. Detailed comparisons and analyses of experimental results are given. An effective decision-fusion system is proposed and high reliability of 99.10% has been accomplished.