Quantum Neural Network for Image Feature Extraction using MNIST

Quantum neural networks (QNNs) are becoming increasingly recognized as a viable method for addressing complex challenges in image classification. Feature extraction is a vital component in digital image processing since it significantly impacts the accuracy and success of picture classification and identification tasks. Nevertheless, there is a conspicuous absence of efficient quantum feature extraction methods, as current approaches mostly concentrate on rudimentary picture features rather than thoroughly addressing both the overall characteristics of classical and quantum images. In order to fill this need, this research study presents a new and innovative method for extracting image features termed image global features (IGF), which focuses on representing the overall energy of images by creating dual quantum image global features. This method utilizes the quantum superposition of two quantum state characteristics to depict the overall characteristics of two quantum images. The suggested method underwent thorough testing using quantum picture reconstruction and fidelity assessments on nine categories of classical images, resulting in an overall fidelity over 97%. Moreover, the efficacy of the IGF technique is confirmed by contrasting its performance in picture categorization assignments with the convolutional feature extraction technique on the MNIST dataset, showcasing its better capabilities.