 This paper proposes a novel approach for detecting crop diseases by combining convolutional neural networks, CNNs, with handcrafted features, HCF. CNNs were used to extract high-level features from the input data, while HCF was used to capture low-level features such as color and texture. The resulting hybrid model was then tested on both whole leaf images and image patches containing individual lesions. The experimental results showed that the proposed model achieved the classification accuracy of 99.93% for the whole leaf images and 99.74% for the image patches with lesions. This indicates that the proposed method outperforms existing approaches and demonstrates the effectiveness of feature fusion for crop disease detection. This article was authored by Radhika Bogwat and Yogesh Danduwait.