Quantum Convolutional Neural Networks (QCNNs) have recently emerged as a promising approach for enhancing various computer vision tasks, such as object detection, image segmentation, and classification. By leveraging quantum computing principles and utilizing qubits instead of classical bits, QCNNs offer potential improvements over traditional Convolutional Neural Networks (CNNs). This paper presents a simulated QCNN model based on the framework proposed by Caro et al. (2022) to analyze its performance across different classification tasks. We evaluate the QCNN’s effectiveness on two distinct datasets with varying image dimensions, providing insights into its strengths and limitations. Our analysis identifies the scenarios in which QCNNs outperform classical CNNs and where their performance may be constrained, contributing to a better understanding of the impact of image size and class complexity on QCNN performance.