Plant leaf diseases pose a serious threat to agricultural productivity worldwide, resulting in substantial financial losses and food poverty. Sustainable farming practices and efficient management of many diseases depend on early and accurate detection. However, conventional approaches frequently suffer from drawbacks such as their lack of robustness and sensitivity to environmental changes. To improve the identification and classification of plant leaf diseases, this work proposes a novel hybrid strategy that combines texture analysis with deep learning approaches. The study integrates texture descriptors, like the gray-level co-occurrence matrix (GLCM) and local binary patterns (LBP), for structural analysis with convolutional neural networks (CNNs) for high-level feature extraction. Using the complementary advantages of texture analysis and deep learning, the hybrid model seeks to overcome the drawbacks of solo methods. Using a 70–30 train-test split, the model was trained and assessed using a dataset of photos of sick plant leaves. Performance was evaluated using key measures such as F1-score, recall, accuracy, and precision. The results show that the suggested hybrid model performs better than conventional techniques, with an accuracy of 98.2% as opposed to 92.5% for CNNs operating alone. Additionally, the model demonstrated increased resilience to changing noise levels and environmental circumstances. The results highlight how this integrated approach has the potential to transform agricultural disease control and enhance crop health and food security. Future studies should examine scalability and real-time implementation across various crop varieties and environmental settings to advance precision agriculture practices.