Plant diseases are a vital risk to crop yield and early detection of plant diseases remains a complex task for the farmers due to the similar appearance in color, shape, and texture. In this work, authors have proposed an automatic plant disease detection technique using deep ensemble neural networks (DENN). Transfer learning is employed to fine-tune the pre-trained models. Data augmentation techniques include image enhancement, rotation, scaling, and translation are applied to overcome overfitting. This paper presents a detailed taxonomy on the performance of different pre-trained neural networks and presents the performance of a weighted ensemble of those models relevant to plant leaf disease detection. Further, the performance of the proposed work is evaluated on publicly available plant village dataset, which comprises of 38 classes collected from 14 crops. The performance of DENN outperform state-of-the-art pre-trained models such as ResNet 50 & 101, InceptionV3, DenseNet 121 & 201, MobileNetV3, and NasNet. Performance evaluation of the proposed model demonstrates that effective in categorizing various types of plant diseases that comparatively outperform pre-trained models.

Transfer learning-based deep ensemble neural network for plant leaf disease detection

Plant Leaf Disease Identification and Prescription Suggestion Using Deep Learning

Precision farming is one way of many to meet a 70 percent increase in global demand for agricultural products on current agricultural land by 2050 at reduced need of fertilizers and efficient use of water resources. The catalyst for the emergence of precision farming has been satellite positioning and navigation followed by Internet-of-Things, generating vast information that can be used to optimize farming processes in real-time. Statistical tools from data mining, predictive modeling, and machine learning analyze pattern in historical data, to make predictions about future events as well as intelligent actions. This special issue presents the latest development in statistical inference, machine learning and optimum control for precision farming.

Learning from Data to Optimize Control in Precision Farming

Chilli is among the most commonly used spices globally and is an integral part of many cuisines. Many countries like Mexico, India, China, and Korea are known for growing and consuming chillies. Amongst all, India is the largest producer of chillies worldwide. When cultivated on a large scale, these crops are highly susceptible to fungal, pests, weeds, bacterial, viral and pathogen attacks that substantially hinder production. Among these plant attacks, the most common is Chilli anthracnose, caused by the Colletotrichum fungus, which affects the leaves and the fruit of the chilli plant, causing a devastating loss to the farmers. Our paper proposes a solution based on Deep Neural Network (DNN) using transfer learning to classify disease-affected Anthracnose chillies from Healthy chillies. This study has developed a dataset by collecting the chilli samples from the University of Agricultural Sciences, Dharwad and chilli farms in Kusugal, outskirts of Hubli. The dataset consists of 4 classes with two types of chilli; red and green. Each coloured chilli has two stages; the healthy stage and the Anthracnose diseased stage. Here, different pre-trained DNN architectures and transfer learning methods are used to train the model on our dataset. Finally, the results are compared based on accuracy and model size for all architectures trained on the proposed dataset. And choose the architecture with the smallest model size and high accuracy for embedding in an edge device.

Identification of Anthracnose in Chillies using Deep Learning on Embedded Platforms

https://www.ijcrt.org/download1.php?file=IJCRT2106092.pdf

Plant leaf disease detection using deep learning

Plant disease is an ongoing challenge for smallholder farmers, which threatens income and food security. The recent revolution in smartphone penetration and computer vision models has created an opportunity for image classification in agriculture. Convolutional Neural Networks (CNNs) are considered state-of-the-art in image recognition and offer the ability to provide a prompt and definite diagnosis. In this paper, the performance of a pre-trained ResNet34 model in detecting crop disease is investigated. The developed model is deployed as a web application and is capable of recognizing 7 plant diseases out of healthy leaf tissue. A dataset containing 8,685 leaf images; captured in a controlled environment, is established for training and validating the model. Validation results show that the proposed method can achieve an accuracy of 97.2% and an F1 score of greater than 96.5%. This demonstrates the technical feasibility of CNNs in classifying plant diseases and presents a path towards AI solutions for small holder farmers.

Gandham Harish

Papers

Plant leaf disease detection using deep learning

Plant leaf disease detection using deep learning