This paper presents an image-recognition technique using quantum annealing. We used four handwritten numbers of 0, 1, 2, and 3 from the MNIST (Modified National Institute of Standards and Technology) digit classification dataset as images to be recognized. We used two models in this study which were basically the same as a simple neural network, one had one fully connected layer and the other had 3x3 Sobel filters in front of that layer. The images were first resized to 1/2 the original in both directions, and pixel data were converted to 196 one-dimension data then output to four outputs through a fully coupled neural network. The optimum values of 196 x 4 weights and 4 bias values of the fully connected layer were obtained by quantum annealing in which the loss function is expressed as Hamiltonian of the Ising model. The weights and biases are multi-valued variables consisting of multiple spin variables in the Ising model. Quantum annealing was simulated using Pyqubo to create Ising models from flexible mathematical expressions. Prediction accuracy when using the Sobel filters reached about 95% and Sobel filter improved it by about 5%.
This paper presents an image-recognition technique using quantum annealing. We used four handwritten numbers of 0, 1, 2, and 3 from the MNIST (Modified National Institute of Standards and Technology) digit classification dataset as images to be recognized. We used two models in this study which were basically the same as a simple neural network, one had one fully connected layer and the other had 3x3 Sobel filters in front of that layer. The images were first resized to 1/2 the original in both directions, and pixel data were converted to 196 one-dimension data then output to four outputs through a fully coupled neural network. The optimum values of 196 x 4 weights and 4 bias values of the fully connected layer were obtained by quantum annealing in which the loss function is expressed as Hamiltonian of the Ising model. The weights and biases are multi-valued variables consisting of multiple spin variables in the Ising model. Quantum annealing was simulated using Pyqubo to create Ising models from flexible mathematical expressions. Prediction accuracy when using the Sobel filters reached about 95% and Sobel filter improved it by about 5%.
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%.
An improved quantum neural network based on a parameterized quantum circuit for 0 or 1 classification of images is designed in this paper. A classical handwritten digital image of size28×28pixels is compressed into a4×4pixel image, whose 16 classical images represent the probability amplitudes of a 4-qubit state input in the quantum state preparation circuit. The output and corresponding 0 or 1 labels are used as training data for supervised learning of a parameterized quantum recognition circuit composed of 4 qubits. The complete design process is studied in detail, including the input of classical data, quantum state preparation, the output recognition of images by the parameterized quantum circuit, and the projection measurement of the designated readout qubit. In the training of the network parameters, the goal of minimizing the loss function is to achieve optimal quantum circuit parameters. In the performance comparison experiments, handwritten digital images from the MNIST dataset are used to conduct recognition tests on two specific digits, and the test accuracy is 98.88%. The recognition accuracy rate increases by 8.13% compared with the recognition performance before the improvement. The quantum image recognition network designed in this paper can be extended to multiclass classification applications.
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.
A digital recognition paradigm integrating a hybrid quantum-traditional neural network is developed for numerical recognition, whereby quantum computing and conventional neural networks may collaborate. This model integrates parameterized quantum circuits within a convolutional framework to attain a combination of embedding and direct output. The input from the convolutional fully connected layer functions as the control parameter for the quantum layer and is subjected to a sequence of transformations for feature processing. This structure's potential is evidenced by digit recognition on the MNIST dataset for digital applications. The approach employs transfer learning, integrating convolutional and deep image feature extraction using hybrid networks, thereby mitigating the overfitting problem associated with a singular convolutional network on limited sample datasets. The findings demonstrate the model's efficacy, utility, and superior generalization capability. The recognition rates of the direct output hybrid network and the embedded hybrid network on the MNIST dataset increased by 0.0398 and 0.0211, respectively, in comparison to a convolutional network. Following transfer learning and feature fusion, the recognition rates of the hybrid model on small sample datasets exceed those of a singular network, achieving 83%, so validating the model's learning and generalization proficiency for digital applications.
The rapid growth of computer vision and increasingly complex image recognition tasks has exposed fundamental computational limitations of classical machine learning models, motivating the exploration of quantum computing as an emerging new paradigm. This paper presents a comprehensive benchmarking study of classical and quantum machine learning models for image recognition on the MNIST handwritten digit dataset, evaluating both traditional models, a Classical Support Vector Machine (CSVM) and a Quantum Support Vector Machine (QSVM), and deep neural network models, a Classical Convolutional Neural Network (CCNN) and a Quantum Convolutional Neural Network (QCNN), across four performance dimensions: classification accuracy, computational runtime, parameter count, and memory requirements. Experiments are conducted as functions of both feature dimensionality and sample size, and across CPU and GPU execution environments, providing a controlled, multidimensional comparison to address gaps in prior work. For the SVM-based models, QSVM consistently outperforms CSVM in accuracy, reaching ∼ 0.90 versus ∼ 0.85 at 1,000 samples, with a higher computational cost. A feature count of 10 qubits and a sample size in the range of 200 -- 500 emerge as practical operating points that balance accuracy and runtime. For the neural network models, CCNN and QCNN achieve comparable classification accuracy, both exceeding 0.96 at 64 features and 60,000 samples, yet QCNN offers superior parameter and memory efficiency at higher feature counts, while incurring higher runtime. Across both model families, quantum models consistently outperform classical models by greater margins in accuracy as feature dimensionality or sample size increases.
Classical computing has borne witness to the development of machine learning. The integration of quantum technology into this mix will lead to unimaginable benefits and be regarded as a giant leap forward in mankind's ability to compute. Demonstrating the benefits of this integration now becomes essential. With the advance of quantum computing, several machine-learning techniques have been proposed that use quantum annealing. In this study, we implement a matrix factorization method using quantum annealing for image classification and compare the performance with traditional machine-learning methods. Nonnegative/binary matrix factorization (NBMF) was originally introduced as a generative model, and we propose a multiclass classification model as an application. We extract the features of handwritten digit images using NBMF and apply them to solve the classification problem. Our findings show that when the amount of data, features, and epochs is small, the accuracy of models trained by NBMF is superior to classical machine-learning methods, such as neural networks. Moreover, we found that training models using a quantum annealing solver significantly reduces computation time. Under certain conditions, there is a benefit to using quantum annealing technology with machine learning.