Bapuji Institute of Engineering and Technology

Department of Information and Science and Engineering

Final phase
Detection of plants leaf Diseases using image
Segmentation and soft Computing Techniques

UNDER THE GUIDANCE OF

Prof . PATIL N.S M Tech Dr. POORNIMA B.Ph.D.
Associate Professor Head of Department
PRESENTED BY

DIVYA J [4BD17IS403] SHARANASHREE N Y[4BD15IS087]

PRIYANKA B K[4BD17IS406] POOJA S A[4BD15IS058]
 ABSTRACT

Agricultural productivity is something on which economy highly depends. Reasons that disease detection in
  plants important role in agriculture field. If proper care is not taken in this area then it causes serious effects
on plants and due to which respective product quality, quantity or productivity is affected. Detection of plant
disease through some automatic technique is beneficial as it reduces a large work of monitoring in big
farms of crops, and Algorithm for image segmentation technique which is used for automatic detection and
classification of plant leaf diseases, is done by using genetic algorithm.
 INTRODUCTION

 Automatic detection of the diseases by just seeing the symptoms on the plant leaves makes it easier also
machine vision to provide image based automatic process control.
 Image segmentation is grouping an image into different parts. In this Thresholding process is advanced color
method This process is based on various features found in the image.
 Genetic algorithm searches from a large sampling of the cost surface. Large number of variables can be
processed and Gives a number of optimum solutions, different image segmentation results can be obtained.

Fig: Fungal disease

 PROBLEM STATEMENT

There is lack of advanced automatic technique for detection of leaf diseases and
identification of diseases in initial stage through naked eyes is a most difficult task. This
causes huge economic loss for farmers.

OBJECTIVES
To process the data of the leaf picture from plant dataset.
Extract the feature from pre-processed data.
Accurately classify the leaf disease.
Evaluate performance analysis

 
EXISTING SYSTEM
The existing method for plant disease detection is simply naked eye observation by experts through which
identification and detection of plant diseases done

DISADVANTAGES

 We need large team of experts to detect diseases.

 Continuous monitoring of plants is required.

 Cost of existing system is high when we implemented for large farms.

 Farmers do not have proper facilities.

 PROPOSED SYSTEM

ADVANTAGES
 At very early stage itself it detects the symptoms of diseases.
 Automatic detection of the diseases by just seeing the symptoms.
 Also supports machine vision to provide image based automatic process .
 REQUIREMENTS SPECIFICATION

FUNCTIONAL REQUIREMENTS
 Image Acquisition
 Database Operations
 Colour Co-occurrence Method

NON-FUNCTIONAL REQUIREMENTS
 Scalability
 Reliability
 Flexibility
 Performance
 Cost
 HARDWARE AND SOFTWARE REQUIREMENTS

Hardware Requirements
 Processor : Corei3 or higher
 Hard disk : 20GB
 RAM : 4GB

Software Requirements
 Operating System : Ubuntu 18 or higher
 Tools used : Python 3.7 and above
 Database : MySQL/My SQLite
 SYSTEM DESIGN

Architecture of proposed system

 Farm landowners and plant caretakers could be benefited a lot with an early disease detection
 The image processing algorithms and techniques are used to designed the segment the diseases
SEQUENCE DIAGRAM
DATAFLOW DIAGRAM
8 Flow chart
 Steps for implementation

Image acquisition
Preprocessing
Mostly green colored pixels
Removing
Clustering
Computing the features using co-occurrence methodology

ALGORITHM USED
Gaussian naive bayes classifier
Mean shift
LIBRARIES USED
import numpy as np
import pandas as pd
import cv2
Implementation steps
 RGB image acquisition
p =0
 for i in range(img.shape[0]):
 for j in range(img.shape[1]):
 B = img[i][j][0]
 G = img[i][j][1]
 R = img[i][j][2]
 if (B > 110 and G > 110 and R > 110):
 p += 1

 Convert the input image from RGB to HSI format

#Changing colour-space
#imghsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
imghls = cv2.cvtColor(roi, cv2.COLOR_BGR2HLS)
cv2.imshow('HLS', imghls)
imghls[np.where((imghls==[30,200,2]).all(axis=2))] = [0,200,0]
cv2.imshow('new HLS', imghls)
codes
Masking and removal of the green-pixels and
mask = cv2.bitwise_and(originalroi,originalroi,mask = thresh)
cv2.imshow('masked out img',mask)
Segment the components and obtain the useful segments
#Creating rectangular roi around contour
height, width, _ = canny.shape
min_x, min_y = width, height
max_x = max_y = 0
frame = canny.copy()
# computes the bounding box for the contour, and draws it on the frame,
for contour, hier in zip(contours, hierarchy):
(x,y,w,h) = cv2.boundingRect(contours[maxid])
min_x, max_x = min(x, min_x), max(x+w, max_x)
min_y, max_y = min(y, min_y), max(y+h, max_y)
if w > 80 and h > 80:
 Evaluating feature parameters for classification
 Area
 Infa area
 perimeter
Configuring CLASSIFIER for disease detection
from sklearn.naive_bayes import GaussianNB
RESULT
Validation of disease affected area within image final prediction with test dataset and trained dataset
acquired
 conclusion
This project presents the survey on different diseases classification techniques used for plant leaf disease detection and an
algorithm for image segmentation technique that can be used for automatic detection as well as classification of plant leaf
diseases later. Grape, corn, tomato, pepper, apple, and blueberry are some of those species on which proposed algorithm is
trained and tested. Therefore, related diseases for these plants were taken for identification. With very less computational
efforts the optimum results were obtained, which also shows the efficiency of proposed algorithm in recognition and
classification of the leaf diseases. Another advantage of using this method is that the plant diseases can be identified at early
stage or the initial stage.