This research paper takes a close look at how the grey-level co-occurrence matrix (GLCM), support vector machine (SVM), and multi-class support vector machine (MSVM) methods for texture analysis can be used to find diseases that affect cotton crops. In the field of agriculture, Cotton is vital as the world economy mostly depends on it. Still, the sensitivity of the cotton crop to several diseases seriously jeopardizes productivity and quality. Integration of sophisticated image processing and machine learning techniques has become a potential answer for early and accurate disease identification to handle this problem. The first part of this review emphasizes the need for cotton crops in agriculture and the need for strong disease-detecting techniques. A comprehensive examination of the GLCM approach is presented, focusing on its ability to extract textural features from images. The SVM method is then evaluated for its relevance to disease detection in cotton crops and its efficacy in classification tasks. This paper also discusses the MSVM, a sophisticated variation of the SVM that enables concurrent classification of many categories. Comparative studies are undertaken to assess the advantages and disadvantages of GLCM, SVM, and MSVM for disease detection in cotton crops. The review of significant studies and implementations facilitates comprehension of the beneficial outcomes of these strategies. Moreover, challenges and potential areas for improvement in current methodologies are discussed, setting the stage for future research directions. The overarching objective of this review is to offer a consolidated understanding of state-of-the-art techniques for detecting diseases in cotton crops and to guide researchers, practitioners, and policymakers in implementing effective and scalable solutions for sustainable cotton cultivation.