In the dynamic field of computer vision and image classification, the choice of a deep learning model plays a crucial role in achieving optimal performance across various applications. This study conducts a comparative analysis of three distinct convolution neural network (CNN) architectures: MobileNetV2, VGG19, and a simplified CNN model. The objective is to assess their effectiveness in image classification tasks. MobileNetV2, recognized for its lightweight design, demonstrates notable efficiency in computational resource usage, making it well-suited for deployment on resource-constrained devices. VGG19, characterized by its deep and intricate structure, exhibits a strong ability to capture complex hierarchical features, albeit with increased computational demands. The simplified CNN model, designed to strike a balance between complexity and performance, emerges as a practical alternative in scenarios where a compromise between accuracy and resource efficiency is sought.

Image Classification, Convolution Neural Network (CNN), Comparative Analysis Accuracy (CAA), MobileNetV2, VGG19.