A novel deep learning based hybrid approach for pepper leaf diseases detection

Plant disease detection in agriculture is a significant challenge, with potential benefits in monitoring crop fields and identifying symptoms on plant leaves. However, most systems underperform due to varying leaf disease patterns, limiting detection precision. A hybrid deep learning model was developed to address this issue, focusing on detecting and recognizing pepper leaf illness. Automating the recognition of leaf diseases can boost farming production. To solve this problem, we proposed state of art a hybrid deep learning model was used. Our objectives are a construct better pepper leaf disease detection method and model using hybrid techniques in deep learning by using Combinations of CNN-TL, CNN-CAE, CNN-HOG, and CNN-DBN models were trained, validated and tested. The accuracy of each pepper leaf disease detection model was assessed. The hybrid CNN-TL model has 100% accuracy, the CNN-CAE model 96.7%, the CNN-HOG mode 100%, and the CNN-DBN 100%. The hybrid CNN-TL, CNN-HOG, CNN-DBN model identified pepper leaf diseases well. The findings suggest hybrid deep learning can detect pepper leaf illness. Farmers and agriculture specialists can identify and manage pepper leaf illnesses faster with such approaches, improving pepper output and sustainability.