Quantum-Classical Image Processing for Scene Classification

Deep-learning-based convolutional neural network (CNN) models are prominent in processing and analyzing sensor signal data, such as images for classification. Data augmentation is a powerful technique used in training such models to avoid overfitting and to improve accuracy. This letter proposes a data augmentation technique using a quantum circuit for image data. The proposed quantum circuit is suitable to implement on real hardware provided by the IBM Quantum Experience platform. In comparison with other classical data augmentation techniques, the proposed technique increased the prediction accuracy of the CNN from 68.65 to 76.03%. However, CNN models for image classification use many parameters during the training process. Quantum computers can efficiently handle large-scale data inputs using qubits for information processing. Hence, we also propose a hybrid quantum-classical convolutional neural network model (HQCNN) for scene classification. The proposed model uses a combination of CNN layers and quantum layers to process images. The proposed HQCNN reduces parameters used for training due to the use of quantum layers in the model. Our experimental results show that the proposed HQCNN can classify the scenes in the UC Merced land-use dataset with an accuracy of 85.28% compared to the other models.