Enhancement of Plant Disease Detection Framework using Cloud Computing and GPU Computing

GPUs are very useful in high performance computing. With the emerging new trend of cloud environments with GPU instances are now gaining popularity in many real time applications. GPUs in a cloud environment still needs a long way to initiate various challenges in a cloud .The gap for making this as a shared resource in the cloud is still at preliminary level and still limited to many real life problems like plant disease detection at a grass root level. Timely information to farmers about diseases is still a great bottleneck for farmers. Due to this, farmers pour many rounds of pesticides to prevent their crops from diseases. But due to lack of proper ICT, farmers are not informed properly about their crop diseases which result in high loss to ecological balance and community people. Thus, to solve the problem of delayed updation about their crop diseases to farmers, GPU processing is used instead of Normal CPU processing on the cloud. This research paper focuses on the applications of GPU Computing within cloud and to study the performance of GPU image processing and Normal CPU image processing with respect to plant disease detection framework. This paper also addresses the problem of throttling in normal CPU when used for large datasets. GPU processors had shown a four-fold increase in performance as compared to normal datasets. GPU results shown 63 times faster as compared to normal CPU for analyzing 52,486 images of healthy and diseased leaf images. This include 16 plant types and 55 leaf diseases.

Download Full-text

Leaf Disease Detection using Deep Learning Algorithm

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.c5965.029320 ◽

2020 ◽

Vol 9 (3) ◽

pp. 3172-3175

Keyword(s):

Image Processing ◽

Plant Disease ◽

Learning Algorithm ◽

Image Feature ◽

Disease Detection ◽

Proper Solution ◽

Classification Image ◽

Deep Learning Algorithm ◽

Crop Diseases ◽

Crop Disease

India is a nation of agriculture and over 70 per cent of our population relies on farming. A portion of our national revenue comes from agriculture. Agriculturalists are facing loss due to various crop diseases and it becomes tedious for cultivators to monitor the crop regularly when the cultivated area is huge. So the plant disease detection is important in agriculture field. Timely and accurate disease detection is important for the loss caused due to crop diseases which affects adversely on crop quality and yield. Early diagnosis and intervention can reduce the loss of plant due to disease and reduce the unnecessary drug usage. Earlier, automatic detection of plant disease was performed by image processing. For disease detection and classification, image processing tools and the machine learning mechanism are proposed. Crop disease will be detected through various stages of image processing such as image acquisition, pre-processing of image, image feature extraction, feature classification, disease prediction and fertilizer recommendation.detection of disease is important because it will may help farmers to provide proper solution to prevent these disease.

Download Full-text

Plant disease detection using computational intelligence and image processing

Journal of Plant Diseases and Protection ◽

10.1007/s41348-020-00368-0 ◽

2020 ◽

Author(s):

Vibhor Kumar Vishnoi ◽

Krishan Kumar ◽

Brajesh Kumar

Keyword(s):

Image Processing ◽

Computational Intelligence ◽

Plant Disease ◽

Disease Detection

Download Full-text

PLANT DISEASE DETECTION USING IMAGE PROCESSING AND MACHINE LEARNING ALGORITHM

Journal of Xidian University ◽

10.37896/jxu14.7/012 ◽

2020 ◽

Vol 14 (7) ◽

Keyword(s):

Machine Learning ◽

Image Processing ◽

Plant Disease ◽

Learning Algorithm ◽

Disease Detection ◽

Machine Learning Algorithm

Download Full-text

Solving Current Limitations of Deep Learning Based Approaches for Plant Disease Detection

Symmetry ◽

10.3390/sym11070939 ◽

2019 ◽

Vol 11 (7) ◽

pp. 939 ◽

Cited By ~ 28

Author(s):

Marko Arsenovic ◽

Mirjana Karanovic ◽

Srdjan Sladojevic ◽

Andras Anderla ◽

Darko Stefanovic

Keyword(s):

Deep Learning ◽

Plant Disease ◽

Real Life ◽

Weather Conditions ◽

Plant Diseases ◽

Disease Classification ◽

Generative Adversarial Networks ◽

Disease Detection ◽

Single Leaf ◽

The Impact

Plant diseases cause great damage in agriculture, resulting in significant yield losses. The recent expansion of deep learning methods has found its application in plant disease detection, offering a robust tool with highly accurate results. The current limitations and shortcomings of existing plant disease detection models are presented and discussed in this paper. Furthermore, a new dataset containing 79,265 images was introduced with the aim to become the largest dataset containing leaf images. Images were taken in various weather conditions, at different angles, and daylight hours with an inconsistent background mimicking practical situations. Two approaches were used to augment the number of images in the dataset: traditional augmentation methods and state-of-the-art style generative adversarial networks. Several experiments were conducted to test the impact of training in a controlled environment and usage in real-life situations to accurately identify plant diseases in a complex background and in various conditions including the detection of multiple diseases in a single leaf. Finally, a novel two-stage architecture of a neural network was proposed for plant disease classification focused on a real environment. The trained model achieved an accuracy of 93.67%.

Download Full-text