A Concise Review of Crop Disease Identification: Integrating Conventional and Deep Learning Feature Extraction for Effective Diagnosis and Mitigation Strategies

Crop leaf diseases are a serious problem for farmers, as they can lead to severe crop losses. Therefore, early detection and identification of crop leaf diseases is necessary. Crop diseases are a significant contributor to substantial losses in crop production on a global scale annually. To mitigate the financial consequences resulting from plant diseases, it is crucial to maintain the well-being of plants throughout various phases of their growth and development. The manifestation of infections is predominantly observed in plant leaves, making them a commonly utilized medium for disease diagnosis and recognition. The task of visually identifying diseases in plants poses a considerable challenge and necessitates considerable expertise. The rapid development of feature extraction has transformed the field of computer vision, especially in the field of agriculture. The detection of crop leave diseases can be accomplished by examination of the symptoms and extracting pertinent features. Consequently, the extraction of features assumes a pivotal role in such systems. This manuscript highlights the importance of examining both conventional and deep learning-oriented methodologies for the purpose of extracting features. These insights and techniques are versatile, as they can be applied to address the various afflictions that impact different crops.