As the global population continues to grow, the demand for agricultural production is on the rise. Plant diseases pose significant challenges to the agriculture industry and its management. Historically, humans have relied on visual recognition to identify plant diseases, a process often marred by subjectivity and time constraints. To streamline disease recognition, machine learning techniques leveraging images of plant leaves have emerged. Timely detection is crucial as these diseases can profoundly impact a plant's development. Crop loss due to pathogens like bacteria, viruses, and fungi has plagued agriculture for centuries on a global scale. The widespread availability of smartphones and recent advancements in deep learning-based computer vision have paved the way for smartphone-based disease detection. We have employed a dataset consisting of diverse images of both healthy and diseased plant leaves captured under controlled conditions to train a deep convolutional neural network. These breakthroughs have now opened the door to global-scale mobile-phone-based plant disease diagnosis, particularly with the advent of larger publicly available image datasets and advancements in Artificial Intelligence (AI) and Deep Learning (DL). This research demonstrates the significant potential for improved accuracy in this field, as AI and DL, a subset of Machine Learning (ML), continue to advance. Various ML models have been applied to the task of identifying and classifying plant diseases, and this work provides a comprehensive exploration of DL models tailored to represent a wide spectrum of plant diseases.