Cotton cultivation plays a crucial role in global agriculture; however, its productivity is significantly affected by various plant diseases that reduce yield, fibre quality, and economic returns. Early and accurate identification of these diseases is essential for effective crop management and sustainable agricultural practices. Traditional disease diagnosis methods primarily rely on manual visual inspection, which is time consuming, subjective, and often dependent on expert knowledge, making them impractical for large scale field monitoring. Recent advancements in artificial intelligence and computer vision have enabled the development of automated plant disease detection systems. Nevertheless, many existing approaches are limited by manual feature extraction, poor scalability, and restricted real world applicability. To address these challenges, this research proposes an advanced MATLAB based framework for automatic identification of cotton leaf diseases using deep learning and image analysis techniques. The proposed system utilizes a Convolutional Neural Network to perform end to end feature extraction and classification of cotton leaf images into multiple categories, including Healthy, Aphids, Armyworm, Bacterial Blight, Powdery Mildew, and Target Spot. The methodology incorporates image pre-processing, data augmentation, and optimized network training to improve model robustness against variations in illumination, texture, and disease severity. Additionally, a user friendly Graphical User Interface is developed within MATLAB to enable practical deployment, allowing users to train models using organized dataset folders, upload test images, and obtain real time disease prediction results. Experimental evaluation demonstrates that the proposed Convolutional Neural Network based framework achieves high classification accuracy and strong generalization capability compared to conventional machine learning methods. The automatic feature learning capability of deep learning eliminates the need for manual feature engineering while improving classification efficiency and reliability. The developed system offers a scalable and user oriented solution for early disease detection, supporting precision agriculture and intelligent crop management. Furthermore, the framework provides a foundation for future extensions such as real time field monitoring, mobile application deployment, and integration with IoT based smart farming systems.