IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)
Quantum Image Classification Using MDA-Condensed Features
Kai-Yu Lu, Yu-Hsiang Chen, Tien-Yen Chiu, Chih‐Wei Tang
Abstract
Classical images are converted into quantum image representations before quantum image classification. Reducing the number of input qubits is critical in quantum neural network (QNN)–based image classification since it reduces the search space of optimal solution during training. Thus, this paper proposes an image classification method using quantum neural networks. Multiple discriminant analysis (MDA) extracts task-aware image features for classification. The proposed shallow quantum neural network-based model exhibits higher classification accuracy with a small number of parameters. Experimental results show that the proposed method achieves higher 4-, 6-, 8-, and 10-class classification accuracy despite using a small number of input qubits and a small number of parameters on the MNIST dataset, being compared with the existing quantum-based method and CNN-based method.