Plants play an important role in providing food around the world. Various environmental factors lead to the occurrence of plant diseases, which lead to significant crop losses. However, manual detection of plant diseases is a laborious and error-prone process. This can be an unreliable method of detecting and preventing the spread of plant diseases. The introduction of advanced technologies, such as machine learning (ML) and deep learning (DO), can help overcome these problems by providing early detection of plant diseases. The article discusses the latest achievements in the use of machine learning and deep learning methods for the detection of plant diseases. The study focused on publications from 2012 to 2023, as well as practices discussed in this study that demonstrate the effectiveness of using these methods to increase the accuracy and efficiency of plant disease detection. This study also discusses the challenges and limitations associated with the use of MO and DL for plant disease detection, such as issues related to data availability, image quality, and differentiation between healthy and diseased plants. In the course of the study, we will provide valuable information that will provide researchers and specialists in the field of plant disease detection with solutions to these problems and limitations, give a comprehensive understanding of the current state of research in this area, highlight the advantages and limitations of these methodologies, and also provide potential solutions to overcome difficulties that arise during their implementation. Incorrect labels occur due to inaccuracies made in the process of manual annotation of plant images. It helps to prevent errors that occur when diagnosing plant diseases. A convolutional neural network (CNN) is used to classify images based on a set of verity data.