Real-Time Multiple Guava Leaf Disease Detection from a Single Leaf Using Hybrid Deep Learning Technique

Abstract

The guava plant has achieved viable significance in subtropics and tropics owing to its flexibility to climatic environments, soil conditions and higher human consumption. It is cultivated in vast areas of Asian and Non-Asian countries, including Pakistan. The guava plant is vulnerable to diseases, specifically the leaves and fruit, which result in massive crop and profitability losses. The existing plant leaf disease detection techniques can detect only one disease from a leaf. However, a single leaf may contain symptoms of multiple diseases. This study has proposed a hybrid deep learning-based framework for the real-time detection of multiple diseases from a single guava leaf in several steps. Firstly, Guava Infected Patches Modified MobileNetV2 and U-Net (GIP-MU-NET) has been proposed to segment the infected guava patches. The proposed model consists of modified MobileNetv2 as an encoder, and the U-Net model's up-sampling layers are used as a decoder part. Secondly, the Guava Leaf Segmentation Model (GLSM) is proposed to segment the healthy and infected leaves. In the final step, the Guava Multiple Leaf Diseases Detection (GMLDD) model based on the YOLOv5 model detects various diseases from a guava leaf. Two self-collected datasets (the Guava Patches Dataset and the Guava Leaf Diseases Dataset) are used for training and validation. The proposed method detected the various defects, including five distinct classes, i.e., anthracnose, insect attack, nutrition deficiency, wilt, and healthy. On average, the GIP-MU-Net model achieved 92.41% accuracy, the GLSM gained 83.40% accuracy, whereas the proposed GMLDD technique achieved 73.3% precision, 73.1% recall, 71.

Lyme rashes disease classification using deep feature fusion technique

“…The results showed that the proposed Deep Feature Fusion technique model performed better than the cited study. It prevented a fair comparison of the study's findings to those of other, more reliable studies 67‐69 …”

Segmentation and classification of skin lesions using hybrid deep learning method in the Internet of Medical Things

“…It achieved 93.8% accuracy on the ISIC‐2017 dataset. Second, in 2021, Khan et al 20 . developed Deep CNN, which applied moth flame optimization with deep learning features to segment and classify skin lesions.…”

“…Dermoscopy is used to collect photographs of the skin, while a biopsy and a microscope are required to obtain images of other medical structures. 14 15,16 and other deep learning algorithms [17][18][19][20][21][22] have shown great progress in various skin cancer classifications, with excellent accuracy and robustness. Extraction of discriminative features from photos of skin lesions has been used to obtain outstanding classification results using DenseNet, 23 InceptionNet, 24 and ResNet.…”

“…The difficulty of differentiating malignant from benign skin lesions has prompted the development of several cutting‐edge techniques. Convolutional Neural Networks (CNNs) 15,16 and other deep learning algorithms 17–22 have shown great progress in various skin cancer classifications, with excellent accuracy and robustness. Extraction of discriminative features from photos of skin lesions has been used to obtain outstanding classification results using DenseNet, 23 InceptionNet, 24 and ResNet 25 .…”

Deep Learning Method to Detect the Road Cracks and Potholes for燬mart燙ities

“…The use of deep learning (DL) can play a vital role in solving real-life problems after the advancements in computer systems, especially graphical processing units (GPUs). DL automation in areas of various domains is straightforward, such as medical [11,12], agriculture [13][14][15], proper water resources supply [16], facial expression identification [17] and in cities surveillance [18]. In recent years, the most exciting topic has been damage, cracks, and pothole detection of road surfaces using artificial intelligence.…”