AOS MINI PROJECT Project Title - Disease Detection In ......SHIKHA UPADHYAY 19MCMI04 M.TECH AI 1 STSEM SHWETA TIPLE 19MCMB10 M.TECH IT 1 SEM AOS MINI PROJECT DISEASE DETECTION IN ORANGE

SHIKHA UPADHYAY

19MCMI04

M.TECH AI 1ST SEM

SHWETA TIPLE

19MCMB10

M.TECH IT 1ST SEM

AOS MINI PROJECT

DISEASE DETECTION IN ORANGE

PLANT USING IMAGE PROCESSING

AND DEEP LEARNING

INSTRUCTOR

DR. M. NAAGAMANIAssistant Professor, University of Hyderabad, India

Problem Statement

Agriculture, with its allied sectors, is unquestionably the largest livelihood provider in India, more so in the vast rural areas.

It also contributes a significant figure to the Gross Domestic Product (GDP).

Timely and accurate diagnosis of disease in plants plays a very significant role in crop cultivation as it may reduce the quantity and quality of production.

Ancient practice of disease detection requires a lot of expertise work, visually diagnosing the plant fail to provide accurate results

This may mislead the farmer and worsen the condition.

A variety of Oranges are produced in India. But 10 -24% of loss in production occurs due to disease in same.

Solution

An automated system designed to help identify plant diseases by the

plant’s appearance could be of great help to amateurs in the agricultural

process.

With the marvels of Image Processing and Deep Learning techniques, they

are now being widely used in Precision Agriculture.

So we will apply deep learning to create an algorithm for automated

detection and classification of plant leaf diseases.

Nowadays, Convolutional Neural Networks are considered as the leading

method for object detection.

Why Deep Convolution Neural

Network?

Deep learning has evolved itself as an area of interest to the researchers in the past few

years.

Convolutional Neural Network (CNN) is a well-known deep learning architecture inspired

by the natural visual perception mechanism of the living creatures.

In 1959, Hubel & Wiesel found that cells in animal visual cortex are responsible for

detecting light in receptive fields.

Continued..

First, the key interest for applying CNN lies in the idea of using concept of weight sharing.

Due to lesser parameters, CNN can be trained smoothly and does not suffer overfitting.

Secondly, the classification stage is incorporated with feature extraction stage, both uses

learning process.

Thirdly, it is much difficult to implement large networks using general models of artificial

neural network (ANN) than implementing in CNN.

CNNs are widely being used in various domains due to their remarkable performance

such as image classification, object detection, face detection , speech recognition,

vehicle recognition, diabetic retinopathy , facial expression recognition and many more.

General Model

Architectures

There are several different architectures of deep learning like AlexNet, GoogleNet, LeNet

VGG and ResNet.

LeNet is a 7-level convolutional network by LeCun in 1998 that classifies digits and used by

several banks to recognise hand-written numbers on cheques digitized in 32x32 pixel

greyscale input images.

AlexNet in similar to LeNet with some improvement - max pooling, ReLU nonlinearity, more

data and bigger model implementation (50x speedup over CPU) Trained on two GPUs for

a week Dropout regularization.

GoogleNet proposed a module called the inception modules which includes skip

connections in the network forming a mini module and this module is repeated

throughout the network.

LeNet Architecture

Images of Various Diseased Leaves

System Requirements

System - Intel i5 7th Generation

Storage - 1 TB

RAM - 4 GB (required 4 to 16 GB)

Kaggle provides free access to NVidia K80 GPUs in kernels. This benchmark

shows that enabling a GPU to your Kernel results in a 12.5X speedup during

training of a deep learning model.

So for the code execution we will use Kaggle Kernel.

Data sets Source - Plant Village

Kaggle Kernel Snapshot

Python Libraries

References

Proceedings of 2018 Eleventh International Conference on Contemporary

Computing (IC3), 2-4 August, 2018, Noida, India “Tomato Leaf Disease Detection

using Convolutional Neural Networks” Prajwala TM, Alla Pranathi, Kandiraju Sai

Ashritha, Nagaratna B. Chittaragi*, Shashidhar G. Koolagudi.

“Recent Advances in Convolutional Neural Networks” Jiuxiang Gua,∗ , Zhenhua

Wangb,∗ , Jason Kuenb , Lianyang Mab , Amir Shahroudyb , Bing Shuaib , Ting Liub ,

Xingxing Wangb , Li Wangb , Gang Wangb , Jianfei Caic , Tsuhan Chenc

International Journal of Engineering Science and Computing, March 2017 “Plant

Leaf Disease Detection using Deep Learning and Convolutional Neural Network” Anandhakrishnan MG Joel Hanson1 , Annette Joy2 , Jerin Francis

Thank You!!!!