• Irfan Ayoub
• Dr. Bhawna Sharma
• Dr. Simmi Dutta

Abstract-The healthful growth of the apple business depends on the prompt and accurate identification of apple leaf diseases. Typically, each of these illnesses is examined by knowledgeable professionals individually. This is a laborious task with erratic precision. We thus suggested a low-cost, stable, high accuracy approach for identifying apple leaf diseases in this work. The Mobile-Net concept is used to achieve this. First of all, it is simple to install on mobile devices, it is a low-cost Model when compared to typical deep learning models. Second, with the aid of an algorithm, anybody can successfully complete the apple leaf diseases examination rather than only seasoned professionals. Thirdly, Mobile-Net's accuracy is almost on par with that of current sophisticated deep learning models. Finally, various studies have been conducted to show the efficacy of our suggested strategy for identifying apple leaf diseases. We evaluated the effectiveness and accuracy to well-known CNN models, MobileV3, ResNet152 and InceptionV3. The datasets for apple disease (containing the classifications complicated, frog-eye leaf spot, healthy, powdery mildew, rust, and scab) .

Apple leaf diseases, Mobile device, Mobile-Net, Deep learning.

"Apple Leaf Diseases Identification Using Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 1, page no.d385-d390, January-2023, Available :http://www.jetir.org/papers/JETIR2301346.pdf

"Apple Leaf Diseases Identification Using Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 1, page no. ppd385-d390, January-2023, Available at : http://www.jetir.org/papers/JETIR2301346.pdf