Quantum Machine Learning Models for Image Recognition

terraquantum.swiss article

[PDF] Quantum machine learning for image classification

https://terraquantum.swiss/assets/mcjx43jr-10-machine-learning-2023-quantum-m…

Here, we propose two hybrid quantum-classical models: a neural network with parallel quantum layers and a neural network with a quanvolutional layer, which address image classiﬁcation problems. The input data to the quantum layers are m features from the previous classical fully connected layer, divided into c parts, with each part being a vector of q values, x = (φ1, φ2, ..., φq) ∈Rq. To encode these classical fea-tures into quantum Hilbert space, we use the “angle em-bedding” method, which rotates each qubit in the ground state around the X-axis on the Bloch sphere [38] by an angle proportional to the corresponding value in the in-put vector: |ψ⟩= Remb x (x) |ψ0⟩, where |ψ0⟩= |0⟩⊗q. Hybrid Quantum Neural Network with quanvolutional layer, HQNN-Quanv In this section, we give a detailed description of our second hybrid quantum approach for solving the problem of recognizing numbers from the MNIST dataset, based on the combination of a quanvolutional layer and classi-cal fully connected layers.

Visit

eureka.patsnap.com article

Quantum Mechanical Models Enabling Faster Image Recognition

https://eureka.patsnap.com/report-quantum-mechanical-models-enabling-faster-i…

Quantum mechanical models offer a paradigm shift by leveraging quantum principles such as superposition, entanglement, and quantum parallelism.

Visit

ieeexplore.ieee.org article

Quantum Machine Learning for Image Classification: A Hybrid Model of Residual Network with Quantum Support Vector Machine | IEEE Conference Publication | IEEE Xplore

https://ieeexplore.ieee.org/abstract/document/11160179/

Quantum Machine Learning for Image Classification: A Hybrid Model of Residual Network with Quantum Support Vector Machine | IEEE Conference Publication | IEEE Xplore. # Quantum Machine Learning for Image Classification: A Hybrid Model of Residual Network with Quantum Support Vector Machine. Recently, there has been growing attention on combining quantum machine learning (QML) with classical deep learning approaches as computational techniques are key to improving the performance of image classification tasks.This study presents a hybrid approach that uses ResNet-50 (Residual Network) for feature extraction and Quantum Support Vector Machines (QSVM) for classification in the context of potato disease detection. Classical machine learning as well as deep learning models often struggle with high-dimensional and complex datasets necessitating advanced techniques like quantum computing to improve classification efficiency.In our research, we use ResNet-50 to extract deep feature representations from RGB images of potato diseases.

Visit

arxiv.org article

[2304.09224] Quantum machine learning for image classification

https://arxiv.org/abs/2304.09224

# Quantum Physics. # Title:Quantum machine learning for image classification. | Subjects: | Quantum Physics (quant-ph); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) |. | Cite as: | arXiv:2304.09224 [quant-ph] |. | | (or arXiv:2304.09224v2 [quant-ph] for this version) |. | | Focus to learn more arXiv-issued DOI via DataCite |. | Related DOI: | Focus to learn more DOI(s) linking to related resources |. ### References & Citations. ## BibTeX formatted citation. # Bibliographic and Citation Tools. # Recommenders and Search Tools. # arXivLabs: experimental projects with community collaborators. arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community?

Visit

ui.adsabs.harvard.edu research

Quantum Machine Learning for Image Classification: A Hybrid Model of Residual Network with Quantum Support Vector Machine - ADS

https://ui.adsabs.harvard.edu/abs/2025arXiv251023659F/abstract

## Quantum Machine Learning for Image Classification: A Hybrid Model of Residual Network with Quantum Support Vector Machine. Recently, there has been growing attention on combining quantum machine learning (QML) with classical deep learning approaches, as computational techniques are key to improving the performance of image classification tasks. This study presents a hybrid approach that uses ResNet-50 (Residual Network) for feature extraction and Quantum Support Vector Machines (QSVM) for classification in the context of potato disease detection. Classical machine learning as well as deep learning models often struggle with high-dimensional and complex datasets, necessitating advanced techniques like quantum computing to improve classification efficiency. The resulting features are processed through QSVM models which apply various quantum feature maps such as ZZ, Z, and Pauli-X to transform classical data into quantum states. This research highlights the advantages of integrating quantum computing into image classification and provides a potential disease detection solution through hybrid quantum-classical modeling.

Visit