Quantum Convolutional Neural Network for Image Retrieval

Guoming Chen, Qiang Chen, Shun Long +3 more

Shangshang Shi, Zhimin Wang, Jiaxin Li +4 more

Yuchen Sun, Dongfen Li, Qiuyu Xiang +6 more

Jing Wang, Meng Zhang, Junsen Lai +1 more

Quantum Convolutional Neural Network (QCNN) is an integration of classical convolutional neural networks and quantum computing, designed to leverage the unique advantages of quantum computing to enhance machine learning models. It holds promise for providing novel perspectives in solving complex pattern recognition tasks. In the process of image recognition, factors such as the type of convolutional layers, pooling layers, and sample sets significantly influence the recognition results. This study conducts experimental validation on QCNN-based image recognition, investigating the impact of different convolutional layer types, pooling layer types, and image sample datasets on the accuracy of QCNN recognition. Additionally, future development trends of QCNN are discussed.

Baraa Tantawi, Hamza Kamel Ahmed, Malak Magdy +2 more

Various neurological problems such as brain tumors, strokes, and Alzheimer's disease can all be detected and treated with the help of medical imaging. The level of image analysis determines how accurate and reliable a diagnosis made using Magnetic Resonance Imaging (MRI) will be. As a result, the intricate design of brain structures as well as the presence of noise and aberrations in the recorded pictures might make it difficult at times. This study proposes a Quantum Convolutional Neural Networks (QCNN)-based classification model for brain MRI images. Preprocessing and QCNN-based categorization comprise the two key components of the proposed model. A publicly available real brain MRI dataset is used to test the proposed model. The proposed model is extremely promising, according to the experimental findings. The results also demonstrated that the proposed QCNN outperforms its traditional convolutional neural network counterpart. The proposed model looks very promising, according to the experimental findings. The results additionally demonstrated that the proposed QCNN outperforms its traditional convolutional neural network counterpart. It achieved a 96.1% total accuracy.

Yanxuan Lü, Qing Zhong Gao, Jinhu Lü +2 more

Artificial neural networks have achieved great success in many fields ranging from image recognition to video understanding. However, its high requirements for computing and memory resources have limited further development on processing big data with high dimensions. In recent years, advances in quantum computing show that building neural networks on quantum processors is a potential solution to this problem. In this paper, we propose a novel neural network model named Quantum Convolutional Neural Network (QCNN), aiming at utilizing the computing power of quantum systems to accelerate classical machine learning tasks. The designed QCNN is based on implementable quantum circuits and has a similar structure as classical convolutional neural networks. Numerical simulation results on the MNIST dataset demonstrate the effectiveness of our model.