ABSTRACT

Agricultural productivity is something on which economy highly depends. This is the one of the
reasons that disease detection in plants plays an important role in agriculture field, as having
disease in plants are quite natural. 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 at very early stage itself it detects the
symptoms of diseases i.e. when they appear on plant leaves. This project presents a system for
leaf image processing which is used for automatic detection and classification of plant leaf
diseases.
Plant Disease Detection using in Image Processing

CHAPTER 1: INTRODUCTION

1.1 Background

The naked eye observation of experts is the main approach adopted in practice for detection and
identification of plant diseases. But, this requires continuous monitoring of experts which might
be prohibitively expensive in large farms. Further, in some developing countries, farmers may
have to go long distances to contact experts, this makes consulting experts too expensive and
time consuming and moreover farmers are unaware of non-native diseases. Automatic detection
of plant diseases in an important research topic as it may prove benefits in monitoring large
fields of crops, and thus automatically detect the diseases from the symptoms that appear on the
plant leaves. This enables machine vision that is to provide image based automatic inspection,
process control and robot guidance. Comparatively, visual identification is labor intensive, less
accurate By SGDM the texture features are calculated and the classification is done using
squared distance technique. Grape fruit peel maybe infected by several diseases. Real time
specific weed discrimination technique using multilevel wavelet decomposition was proposed
by Siddiqil et.al. In this histogram equalization is used for preprocessing, features are extracted
from wavelet decomposition and finally classified by Euclidean distance method. Automatic
classification of leaf diseases is done based on high resolution multispectral and stereo images
.Sugar beet leaves are used in this approach. Segmentation is the process that is carried out to
extract the diseased region and the plant diseases are graded by calculating the quotient of
disease spot and leaf areas. An optimal threshold value for segmentation can be obtained using
weighted-Parzen-window.

1.2 Motivation

The agronomic requirements though in radically different ways to those currently used this has
given rise to many new chances to service. So they should be tested via non-destructive
techniques Leaves are delicate part of plant, the evaluation of agricultural harvest Classification
is dynamic. The most important visual property is leafs texture and color. Hence, classification
of leaf disease is necessary in evaluating agricultural produce, increasing market value and
meeting quality standards. Identifying and taking further dealings for further diffusion of the
diseases it is also helpful.

Department of Page 2
Plant Disease Detection using in Image Processing

1.3 Problem statement

The process will be too slow, if the identification and categorization is done through
physical techniques, we need the expert’s help sometimes it will be error prone and who
are less available. The labor’s classify based on color, size etc.

1.4 Solution to Problem

If disease detection methods are recorded into automatic system by using appropriate
program design language then the effort will be error free and faster.

1.5 Objective

There are two main characteristics of plant disease detection machine-learning methods that
must be achieved, they are: speed and accuracy. There is need for developing technique such as
automatic plant disease detection and classification using leaf image processing techniques.
This will prove useful technique for farmers and will alert them at the right time before
spreading of the disease over large area. Solution is composed of four main phases; in the first
phase we create a color transformation structure for the RGB leaf image and then, we apply
color space transformation for the color transformation structure. Then image is segmented
using the K-means clustering technique. In the second phase, unnecessary part (green area)
within leaf area is removed. In third phase we calculate the texture features for the segmented
infected object. Finally, in the fourth phase the extracted features are passed through a
classifier.

Department of Page 3
Plant Disease Detection using in Image Processing

CHAPTER 2: LITERATURE SURVEY

2.1 Leaf Disease Severity Measurement Using Image Processing

Sanjay B. Patil, Dr. Shrikant K. Bodhe, Leaf Disease Severity Measurement Using Image
Processing” mentioned in their research that Fungi-caused diseases in sugarcane are the most
predominant diseases which appear as spots on the leaves. If not treated on time, causes the
severe loss. Excessive use of pesticide for plant diseases treatment increases the cost and
environmental pollution so their use must be minimized. This can be achieved by targeting the
diseases places, with the appropriate quantity and concentration of pesticide by estimating
disease severity using image processing technique. Simple threshold and Triangle thresh
holding methods are used to segment the leaf area and lesion region area respectively. Finally
diseases are categories by calculating the quotient of lesion area and leaf area. The accuracy of
the experiment is found to be 98.60 %. Research indicates that this method to calculate leaf
disease severity is fast and accurate. Disease symptoms of the plant vary significantly under the
different stages of the disease so to the accuracy with which the severity of the disease
measured is depends upon segmentation of the image. Simple threshold segmentation is used to
calculate the leaf area but this method is not suitable to calculate the area of the lesion region
because of varying characteristics of the lesion region. Triangle method of the thresh holding
used here to segment the lesion region. The average accuracy of the experiment is 98.60 %.
Thus image processing technology to measure plant disease severity is convenient and accurate.
This eliminates subjectivity of traditional methods and human induced errors. It will helps to
farmers to decide the specific quantity for pesticide application which reduces the cost and
environmental pollution.

2.2 Plant Disease Detection And Its Treatment Using Image Processing
Jundare Manisha, Jundare Pallavi, Jundare Pragati, Prof. C.S.Aryan, “Plant Disease Detection
and its Treatment using Image Processing” mentioned in their research that India is farming
nation, Approx. 20 % of harvest yield is missing universal due to pest attack every year which
is valued around Rs. 90,000 million. Saving 5 Rs. is like earning 5 Rs. farmers have been using
a pesticide, which increases the crop yield to avoid loss. Remains problems in environment due
to large use of pesticides harms to soil, sharp toxicity to humans and natural world, change in
insect type in agro ecosystems, high cost of control practices etc.

Department of Page 4
Plant Disease Detection using in Image Processing

Fungus are very known dangerous insects there on grass of plant, send out steamy honeydew,
reason loss of leaves and harm the harvest surrender. The visual judgment of farmers is
counting of whiteflies has been mostly relied. The illustration decision by farmers for bulk of
whiteflies has been less accurate Because of the identification skills has different levels. In
laboratory also detection of present whiteflies on leaves, it takes extended time for detection of
whiteflies at early on stages has become important because off inimical importance of harvests
and strong impacts of damage levels. In proposed solution, using web application, whiteflies on
leaves of plant at early stages we are calculating no. of eggs also. farmers to use pesticide as
early as possible It will give correct idea . They can avoid damage and control whiteflies, By
this technique, farmers are capable of improve 80 % of lost that will cause due to pest
occurrence. Thus, is important to correctly diagnose a disease before proffering management
options. Diagnosis, being the process of determining the cause of a problem requires the
attention of an expert. extract the features of infected leaf and the classification of plant diseases
From these methods, we can accurately identify and classify various plant diseases and provide
suitable treatment using image processing techniques.

2.3 Leaf Disease Detection and Classification Using Image Processing

Prakash M. Mainkar, Shreekant Ghorpade, Mayur Adawadkar, ”Plant “Plant Disease Detection
and its Treatment using Image Processing Leaf Disease Detection and Classification Using
Image Processing Techniques”, mentioned in their research that Agriculture is the mainstay of
the Indian economy. Almost 70% people depend on it & shares major part of the GDP.
Diseases in crops mostly on the leaves affects on the reduction of both quality and quantity of
agricultural products. Perception of human eye is not so much stronger so as to observe minute
variation in the infected part of leaf. In this paper, we are providing software solution to
automatically detect and classify plant leaf diseases. In this we are using image processing
techniques to classify diseases & quickly diagnosis can be carried out as per disease. This
approach will enhance productivity of crops. It includes several steps viz. image acquisition,
image pre-processing, segmentation, features extraction and neural network based
classification. The study reviews and summarizes image processing techniques for several plant
species that have been used for recognizing plant diseases. The major techniques used are K-
means clustering, GLCM and BPNN. Some of the challenges in these techniques are
optimization of the technique for a specific plant, effect of the background noise in the acquired
image and automation technique for a continuous automated monitoring of plant leaf diseases
under real world field conditions.
Department of Page 5
Plant Disease Detection using in Image Processing

The proposed approach is a valuable approach, which can significantly support an accurate
detection of leaf diseases in a little computational effort. Further future work can be extended
by developing better segmentation technique; selecting better feature extraction and
classification algorithms and NNs in order to increase the recognition rate of final classification
process. Also by computing severity and amount of disease present on the crop, only necessary
and sufficient amount of pesticides can be used making agriculture production system
economically efficient. So there is a scope of improvement.

Department of Page 6
Plant Disease Detection using in Image Processing

CHAPTER 3: SYSTEM DESIGN

3.1 Block Diagram:

The block diagram of the project “Plant Disease Detection using in Image
Processing” is as shown in the Figure.

Fig1: Figure : Block diagram for Plant Disease Detection using in

Image Processing

DATA ACQUISITION UNIT: Leaf images captured using camera.

DATA PROCESSING UNIT: It receives images from acquisition unit and MATLAB
software is used for feature extraction and to develop classification algorithm.

CONTROLLING UNIT: 89S52 is used as a controller .is accepts the serial data from
processing unit.

GSM UNIT: GSM Module is used to send alert sms about leaf disease to the farmer.

POWER SUPPLY: Power supply of 12V and 5V is used to power the controlling unit and
switching unit respectively

Department of Page 7
Plant Disease Detection using in Image Processing

3.2 Software Flow for disease detection in Matlab

Leaf Input Noise Enhance- Segme Extraction of

Image Filter ment ntation Features

Training Testing

Classification K-Nearest Neighbor

Output Classifier

A. Image Acquisition: In Acquisition Process Diseases images of the plants are capture
through the High Resolution camera. This image is in RGB(Red, Green and Blue) form. Color
conversion structure for the RGB leaf image is created, and then, a device independent color
space conversion for the color variation manufacture is applied such as HIS model.

B. Image Pre-processing: To remove noise in image or other object removal, Image clipping
i.e. cropping of the leaf image to get the interested image region. Image smoothing is done
using the smoothing filter. Image enhancement is carried out for increasing the Contrast.

C. Image Segmentation: Segmentation means partition of image into diverse part of same skin
tone or having some likeness dissection means parceling of picture into different part of same
elements or having some likeness. The division should be possible utilizing different.

D. Feature Extraction: The input image is enhanced to protect information of the pretentious
pixels before color from the background. The color space equally is used to reduce effect of
illumination and distinguish between disease and non-disease leaf color inventively the
resulting color pixels are clustered to acquire groups of colors in the image.

E. Classification: In plant leaf categorization leaf is classified based on its different

morphological facial exterior. Some of the classification techniques used Component Analysis,
k-Nearest national Classifier. Plant leaf infection classification has wide application in
cultivation

Department of Page 8
Plant Disease Detection using in Image Processing

CHAPTER 4: HARDWARE DETAILS

MICROCONTROLLER UNIT:
The AT89S52 microcontroller is used for programming in order to control the appliances.
AT89S52 is a low-power, high-performance CMOS 8-bit microcontroller with 8K bytes of in-
system programmable Flash memory. The device is manufactured using Atmel’s high-density
nonvolatile memory technology and is compatible with the industry-standard 80C51 instruction
set and pin out. The on-chip Flash allows the program memory to be reprogrammed in-system
or by a conventional nonvolatile memory programmer.

By combining a versatile 8-bit CPU with in-system programmable Flash on a monolithic chip,
the Atmel AT89S52 is a powerful microcontroller, which provides a highly flexible and cost-
effective solution to many, embedded control applications. The AT89S52 provides the
following standard features: 8K bytes of Flash, 256 bytes of RAM, 32 I/O lines, Watchdog
timer, two data pointers, three 16-bit timer/counters, a six-vector two-level interrupt
architecture, a full duplex serial port, on-chip oscillator, and clock circuitry.

In addition, the AT89S52 is designed with static logic for operation down to zero frequency and
supports two software selectable power saving modes. The Idle Mode stops the CPU while
allowing the RAM, timer/counters, serial port, and interrupt system to continue functioning.
The Power-down mode saves the RAM contents but freezes the oscillator, disabling all other
chip functions until the next interrupt.

The following are some of the capabilities of 8051 microcontroller.

1. Internal ROM and RAM

2. I/O ports with programmable pins
3. Timers and counters
4. Serial data communication

Department of Page 9
Plant Disease Detection using in Image Processing

The 8051 architecture consists of these specific features:

1. 16 bit PC and data pointer (DPTR)
2. 8 bit program status word (PSW)
3. 8 bit stack pointer (SP)
4. Internal ROM 4K
5. Internal RAM of 128 bytes
6. 4 register banks, each containing 8 registers
7. 80 bits of general purpose data memory
8. 32 input/output pins arranged as four 8 bit ports: P0-P3
9. Two 16 bit timer/counters: T0-T1
10. Two external and three internal interrupt sources Oscillator and clock circuits.

SERIAL PORT INTERFACE

The mode communication between pc and microcontroller is serial.

MAX 232
MAX232 IC is a line driver which has two receivers (converts from RS232 to TTL voltage
levels) and two drivers (converts from TTL logic to RS232 voltage levels) and is used for
interfacing the microcontroller to the computer. This is because the logical’0’ and logical’1’ in
a controller are represented by 0v and 5v respectively while the same is represented by a
voltage range of +3v to +12v and -3v to -12v in the serial port of computer. This voltage
conversion is done by the line driver so that there is a proper voltage interface between them.

RS232
The RS232 standard interfaces between two different types of equipment, Data Terminal
Equipment (DTE) and Data Communication Equipment (DCE). The DTE is microcontroller,
which receiver data and DCE is Max6232, which is responsible for transferring data. A simplex
asynchronous data transmission is used; i.e. PC will send data to micro controller through
RS232. The voltage levels for RS-232 standard is -3v to -25v at logic high level and logic level
low of + 3v to +15v and +3v to +25v.

Department of Page
10
Plant Disease Detection using in Image Processing

INTERFACE BETWEEN RS232 & MICROCONTROLLER

Fig 5.3: Interface between RS232 & Microcontroller

To allow the compatibility among the data communication equipment made by

various manufacturers, an interfacing factor called RS-232 was set by the Electronics
Industries Association (EIA) in 1960. Later it was modified and called RS-232A. RS-
232B, RS-232C were later issued. Today, RS-232 is most widely used serial I/O
interfacing standard. Since the standard was set a long before the advent of TTL logic
family, its input and output voltage levels are not TTL compatible. In RS-232, a 1 is
represented by -3volt to -25volt, while a 0 bit is +3 to +25v, making -3 to +3v
undefined. For this reason, to convert any RS-232 to a microcontroller system we must
use voltage converters such as MAX-232 to convert TTL logic levels to RS-232 voltage
levels and vice-versa. MAX-232 IC chips are commonly referred to as line drivers.

MAX 232:

Fig 5.4

Department of Page
11
Plant Disease Detection using in Image Processing

Since the RS 232 is not compatible with today’s microprocessor and microcontroller, a
need of line driver to convert the RS 232’s signals to TTL voltage levels that will be acceptable
to the 8051’s TxD and RxD pins. One example of such a converter is MAX 232 from Maxim
Corp. The MAX 232 converts the RS 232 voltage levels to TTL voltage levels and vice-versa.
One advantage of the MAX 232 chip is that it uses +5V power source, which is the same as the
voltage source for the 8051, and MAX 232, with no need for the dual power supplies that are
common in many older systems.

The MAX 232 has two sets of line drivers for transferring and receiving data. The line
drivers used for TxD are called T1 and T2, while the line drivers for RxD are designated as R1
and R2. In many applications only one of each is used. For example T1 and R1 are use together
to TxD and RxD of 8051, and the second set is left unused.

DC MOTOR
A DC motor is any of a class of rotary electrical machines that converts direct current electrical
energy into mechanical energy. The most common types rely on the forces produced by
magnetic fields. Nearly all types of DC motors have some internal mechanism, either
electromechanical or electronic, to periodically change the direction of current flow in part of
the motor.

DC motors were the first form of motor widely used, as they could be powered from existing
direct-current lighting power distribution systems. A DC motor's speed can be controlled over a
wide range, using either a variable supply voltage or by changing the strength of current in its
field windings. Small DC motors are used in tools, toys, and appliances. The universal
motor can operate on direct current but is a lightweight brushed motor used for portable power
tools and appliances. Larger DC motors are currently used in propulsion of electric vehicles,
elevator and hoists, and in drives for steel rolling mills. The advent of power electronics has
made replacement of DC motors with AC motors possible in many applications.

The Basic DC Motor

The DC Motor or Direct Current Motor to give it its full title, is the most commonly used
actuator for producing continuous movement and whose speed of rotation can easily be
controlled, making them ideal for use in applications were speed control, servo type control,

Department of Page
12
Plant Disease Detection using in Image Processing
and/or positioning is required. A DC motor consists of two parts, a “Stator” which is the
stationary part and a “Rotor” which is the rotating part. The result is that there are basically
three types of DC Motor available.

 Brushed Motor – This type of motor produces a magnetic field in a wound rotor (the
part that rotates) by passing an electrical current through a commentator and carbon
brush assembly, hence the term “Brushed”. The stators (the stationary part) magnetic
field is produced by using either a wound stator field winding or by permanent magnets.
Generally brushed DC motors are cheap, small and easily controlled.

 Brushless Motor – This type of motor produce a magnetic field in the rotor by using
permanent magnets attached to it and commutation is achieved electronically. They are
generally smaller but more expensive than conventional brushed type DC motors
because they use “Hall effect” switches in the stator to produce the required stator field
rotational sequence but they have better torque/speed characteristics, are more efficient
and have a longer operating life than equivalent brushed types.

 Servo Motor – This type of motor is basically a brushed DC motor with some form of
positional feedback control connected to the rotor shaft. They are connected to and
controlled by a PWM type controller and are mainly used in positional control systems
and radio controlled models.

Features

 100RPM 12V DC motors with Gearbox

 3000RPM base motor
 6mm shaft diameter with internal hole
 125gm weight
 Same size motor available in various rpm
 1.2kgcm torque
 No-load current = 60 mA(Max), Load current = 300 mA(Max)

Department of Page
13
Plant Disease Detection using in Image Processing

DC MOTOR

Inside view of Centre Shaft Economy Series DC Motor

Department of Page
14
Plant Disease Detection using in Image Processing

Wireless Transmitter And Receiver Using RF Module

A wireless radio frequency (RF) transmitter and receiver can be easily made
using HT12D Decoder,HT12E Encoder and ASK RF Module. Wireless transmission can be
done by using 433Mhz or 315MHz ASK RF Transmitter and Receiver modules. In these
modules digital data is represented by different amplitudes of the carrier wave, hence this
modulation is known as Amplitude Shift Keying (ASK). Radio Frequency (RF) transmission is
more strong and reliable than Infrared (IR) transmission due to following reasons :

 Radio Frequency signals can travel longer distances than Infrared.

 Only line of sight communication is possible through Infrared while radio frequency
signals can be transmitted even when there is obstacles.
 Infrared signals will get interfered by other IR sources but signals on one frequency
band in RF will not interfered by other frequency RF signals.

An RF module (radio frequency module) is a (usually) small electronic device used to transmit
and/or receive radio signals between two devices. In an embedded system it is often desirable to
communicate with another device wirelessly. This wireless communication may be
accomplished through optical communication or through radio frequency (RF) communication.
For many applications the medium of choice is RF since it does not require line of sight. RF
communications incorporate transmitter and a receiver. They are of various types and ranges.
Some can transmit up to 500 feet. RF modules are widely used in electronic design owing to the
difficulty of designing radio circuitry. Good electronic radio design is notoriously complex
because of the sensitivity of radio circuits and the accuracy of components and layouts required
to achieve operation on a specific frequency. In addition, reliable RF communication circuit
requires careful monitoring of the manufacturing process to ensure that the RF performance is
not adversely affected. Finally, radio circuits are usually subject to limits on radiated emissions,
and require Conformance testing and certification by standardization organization such
as ETSI or the U.S. Federal Communications Commission (FCC). For these reasons, design
engineers will often design a circuit for an application which requires radio communication and
then "drop in" a pre-made radio module rather than attempt a discrete design, saving time and
money on development.
Department of Page
15
Plant Disease Detection using in Image Processing
RF modules are most often used in medium and low volume products for consumer applications
such as garage door openers, wireless alarm or monitoring systems, industrial remote controls,
smart sensor applications, and wireless home automation systems. They are sometimes used to
replace older infra red communication designs as they have the advantage of not requiring line-
of-sight operation.

Several carrier frequencies are commonly used in commercially available RF modules,

including those in the industrial, scientific and medical (ISM) radio bands such as 433.92 MHz,
915 MHz, and 2400 MHz. These frequencies are used because of national and international
regulations governing the used of radio for communication. Short Range Devices may also use
frequencies available for unlicensed such as 315 MHz and 868 MHz.

RF modules may comply with a defined protocol for RF communications such

as Zigbee, Bluetooth low energy, or Wi-Fi, or they may implement a proprietary protocol.

Transmitter (TX)

HT12E Encoder IC will convert the 4 bit parallel data given to pins D0 – D3 to serial data and
will be available at DOUT. This output serial data is given to ASK RF Transmitter. Address
inputs A0 – A7 can be used to provide data security and can be connected to GND (Logic
ZERO) or left open (Logic ONE). Status of these Address pins should match with status of
address pins in the receiver for the transmission of the data. Data will be transmitted only when
the Transmit Enable pin (TE) is LOW. 1.1MΩ resistor will provide the necessary external
resistance for the operation of the internal oscillator of HT12E.

Receiver (RX)

ASK RF Receiver receives the data transmitted using ASK RF Transmitter. HT12D decoder
will convert the received serial data to 4 bit parallel data D0 – D3. The status of these address
pins A0-A7 should match with status of address pin in the HT12E at the transmitter for the
transmission of data. The LED connected to the above circuit glows when valid data
transmission occurs from transmitter to receiver. 51KΩ resistor will provide the necessary
resistance required for the internal oscillator of the HT12D.

Department of Page
16
Plant Disease Detection using in Image Processing

RF Module

Features

 Input voltage range: 3.3V~5.0V

 Low power consumption: 5V @433.92M, 3.8mA~6mA

 Working frequency: 433.92M（can customize to 315M,390M,418M, etc.）

 Modulation: ASK
 Output mode: L mode(input valid signal , output corresponding signal. Valid signal
disappear, it auto stop output)
 Support multiple controller, such as controller with chip

PT2260，PT2262，PT2264，EV1527, etc.

 Good local oscillator radiation suppression, no interfering when single transmit and
multiple receive

Department of Page
17
Plant Disease Detection using in Image Processing

Water pump
The pumping of water is a basic and practical technique, far more practical than scooping it up
with one's hands or lifting it in a hand-held bucket. This is true whether the water is drawn from
a fresh source, moved to a needed location, purified, or used for irrigation, washing, or sewage
treatment, or for evacuating water from an undesirable location. Regardless of the outcome,
the energy required to pump water is an extremely demanding component of water
consumption. All other processes depend or benefit either from water descending from a higher
elevation or some pressurized plumbing system.

Water Pump

Features

 Operating Voltage : 3-9v

 Nominal Voltage : 7.2v
 Current Consumption : 1.8 A
 We recommebd you to use 2.5 A supply.at 7.2 volt,you can also use 5v/6v or 9v
supply.

Department of Page
18
Plant Disease Detection using in Image Processing

Relay:

A relay is an electrical switch that opens and closes under the control of another
electrical circuit. In the original form, the switch is operated by an electromagnet to open
or close one or many sets of contacts. A relay is able to control an output circuit of higher
power than the input circuit, it can be considered in a broad sense to be a form of electrical
amplifier. These contacts can be either Normally Open (NO), Normally Closed (NC), or
change-over contacts.

Normally open contacts connect to the circuit when the relay is activated, the
circuit is disconnected when the relay is inactive. It is also called as Form ‘A’ Contact or
Make Contact. Form A contact is ideal for applications that require to switch a high
current power source from a remote device.

Normally closed contacts disconnect the circuit when the relay is activated, the
circuit is connected when the relay is inactive. It is also called Form B Contact or Break
Contact. Form B contact is ideal for applications that require the circuit to remain closed
until the relay is activated.

Change over contacts control two circuits, one normally-open contact and other
normally-closed contact with a common terminal. It is also called Form C Contact.

Operation:

Fig 4.2: Relay

Department of Page
19
Plant Disease Detection using in Image Processing

Relay unit:
When a current flows through the coil, the resulting field attracts an armature that is
mechanically linked to a moving contact. The movement either makes or breaks a connection
with a fixed contact. When the current to the coil is switched off, the armature is returned by a
force that is half as strong as the magnetic force to its relaxed position. The magnetic flux in the
armature induces a current in opposition to the current provided to the coil called “back EMF”.
There is a rush of current to operate the coil and move the contacts, but once the armature is
closed, the current required to hold the armature is no longer available.

If the coil is energized with AC current, a small copper ring is crimped to the end of the
solenoid. Alternating current is at zero volts 120 times a second. At zero volts, there’s no
magnetic force holding the contacts closed. The small copper ring provides a small out of phase
current called a shadow pole. The sum of the AC current and the shadow pole keeps the
armature engaged at all times.
Relays are used:
1. To control a high-voltage circuit with a low-voltage signal, as in some types of modems.
2. To control a high-current circuit with a low-current signals, as in the starter solenoid of
an automobile.
3. To detect and isolate faults on transmission and distribution lines by opening and
closing circuit breakers (protection relays).
To isolate the controlling circuit from the controlled circuit when the two are at
different potentials, for example when controlling a mains-powered device from a low
voltage switch.

Department of Page
20
Plant Disease Detection using in Image Processing

A relay is a switch that is operated electrically. Most relays utilize electromagnet power to
operate a mechanism that makes the switch. However, there are also other systems used in these
devices. Basically, a relay figures out where the power needs to go, and where it needs to come
from. It then switches the channel flow as needed to make it work.

Telephone exchanges are a huge source where relays are used every single day. But, they are
also found in many other applications. As a general rule, computer programs are beginning to
play a huge part in actual relay actions, but a lot of physical relays are still in use.

Department of Page
21
Plant Disease Detection using in Image Processing

Power supply:
In this project 5V and 12V power supply units are designed to power controlling unit and
processing unit. The block diagram of power supply is as shown in Figure 3.6 and circuit
diagram shown in Figure 3.7

Department of Page
22
Plant Disease Detection using in Image Processing

Figure 3.6Block diagram of power supply

Figure 3.7: Circuit diagram of Power supply

Voltage Step down Unit

The conventional supply, which is generally available, is 230V, 50Hz ac main. It is necessary to
step down this main supply to the desired level. This is achieved by using suitably rated
step-down transformer. While designing the power supply, it is necessary to go for a little
higher rating transformer than the required one. The transformer rating is 230V ac at primary
and 0-12 V, 1 A across the secondary winding. This transformer has a capability to deliver a
current of 1 A. Due to electronic induction, voltage is induced at the secondary transformer.
The induced voltage is reduced in magnitude by a ratio. This ratio is called transformation ratio
or turns ratio.
The design for turn ratio is as follows.
For a transformer following relation holds well,
N1/N2=V1/V2

Department of Page
23
Plant Disease Detection using in Image Processing
Where, N1-Number of turns in primary coil
N2-Number of turns in secondary coil
V1-AC voltage at primary coil
V2-AC voltage at secondary coil
N1/N2-Turns Ratio

Rectifier
The step-down ac is converted into DC. The rectification is achieved by using diodes. If the
power supply is designed for low voltage (+5 V), it is sufficient to employ bridge rectifier. A
bridge rectifier is made using four individual diodes, but it is also available in special packages
containing the four diodes required. It is called a full-wave rectifier because it uses the entire
AC wave (both positive and negative sections). 1.4 V is used up in the bridge rectifier because
each diode uses 0.7 V when conducting and there are always two diodes conducting, as shown
in the. Bridge rectifiers are rated by the maximum current they can pass and the maximum
reverse voltage they can withstand.

The diodes D1 and D2 will be forward biased, while D3 and D4 reverse biased. The two diodes
D1 and D2 conduct in series with the load and the current flows as shown in the next half cycle
, when the polarity voltage reverse hence diode D3 and D4 are forward biased, while D1 and
D2 reverse biased. Note the diodes D3 and D4 conduct in series with the load and the current
flows as shown.
Filter
The output of a rectifier stage contains small percentage of super imposed ac ripples. So, to
remove these ac components, filtering is done. The cheap, reliable, simple and effective
filtering for low current drawing loads is done by using shunt capacitors. This electronic
capacitor has polarities: care has to be taken while connecting to the circuit.

The capacitor C1 is used for filtering purpose and connected across the rectifier output. It filters
the ac components present in the rectified dc and gives steady dc voltage. As the rectifier
voltage increases, it charges the capacitor and also supplies current to the load. Capacitor gets
charged till the peak value of the rectifier voltage and when the rectifier starts to decrease, it
discharges slowly so that output remains almost constant till the next voltage peak immediately
recharges it. Due to this continuous charge-discharge-recharge cycle very little ripples is
observed in the filtered output. The phenomenon is also explained in other form as the shunt
capacitor offers a low reactance path to the ac components of the current and open circuit to dc
Department of Page
24
Plant Disease Detection using in Image Processing
components.

The design of filter capacitor is as follows.

In the below design only rectifier circuit is considered.
Ripple Factor (γ) is given by expression,
γ=1/ (4√3RfC) ------------- (1)
f- Frequency of ac voltage applied at primary coil of transformer
C-Filtering capacitance
R- Resistance to be calculated
Rf- Resistance of diode when forward bias
Rf=12Ω
F=50Hz
V=18*2^1/2=25v
Vr=Vmax-Vmin
=15.75-14.25
Vr=1.5--------------------- (2)
Vac-rms=Vr(283^1/2)=0.433v
Vdc=15.75=(1.5/2)=15v

Voltage Regulator

A DC power supply which maintains the output voltage constant irrespective of ac mains
fluctuations or load variations are known as ‘regulated DC power supply’.

The variation in dc voltage may cause inaccurate or erratic operation or even malfunctioning of
many electronic circuits. Hence the stabilization of dc voltage is achieved by using the three
terminal voltage regulators IC. This regulator IC comes in two flavors: 78xx for positive
voltage output and 79xx for negative output. For ex, 7805 gives +5v output and 7905 gives -5v
stabilized output. These regulator ICs have in-built short-circuit protection and auto-thermal cut
out provisions. If the load current is very high, the IC needs ‘heat sink’ to dissipate the

Department of Page
25
Plant Disease Detection using in Image Processing
internally generated power.

In this circuit 7805 voltage regulator IC is used to get +5 volt regulated DC output, which is
needed for IR sensor module. In the three terminals, pin1 is input i.e., the dc supply is
connected to this pin. Pin2 is common pin and is grounded. The pin3 gives the stabilized dc
output to the load.

Specifications of 7805 and 7812 voltage regulators are both the regulators could source a
current of 1A and a maximum of 40V input voltage could be regulated.

Webcam

A webcam is a video camera that feeds or streams its image in real time to or through
a computer to a computer network. When "captured" by the computer, the video stream may
be saved, viewed or sent on to other networks via systems such as the internet, and emailed
as an attachment. When sent to a remote location, the video stream may be saved, viewed or
on sent there. Unlike an IP camera (which connects using Ethernet or Wi-Fi), a webcam is
generally connected by a USB cable, or similar cable, or built into computer hardware, such
as laptops.
The term "webcam" (a clipped compound) may also be used in its original sense of a
video camera connected to the Web continuously for an indefinite time, rather than for a
particular session, generally supplying a view for anyone who visits its web page over the
Internet. Some of them, for example, those used as online traffic cameras, are expensive, rugged
professional video cameras. Webcams typically include a lens , an image senso, and supporting
circuit.

Department of Page
26
Plant Disease Detection using in Image Processing

Fig 5.6 Webcam

CHAPTER 5: SOFTWARE DETAILS

This chapter has detailed description of the software’s used for the project.
This project is implemented using the following software
 MATLAB
 Keil µvision4


SOFTWARE DESCRIPTION
MATLAB and keil micro vision software are used in this project.

MATLAB
MATLAB[5] (matrix laboratory) is a multi-paradigm numerical computing environment and
fourth generation programming language. Developed by math works, Matlab allows matrix
manipulations, plotting of functions and data, implementation of algorithms, creation of user
interfaces and interfacing with programs written in other languages C, C++ java and Forton.
Various toolboxes are present in MATLAB. In this project image processing toolbox is used to
perform various image processing techniques.

Webcam Support
One can use MATLAB Webcam support to bring live images from any USBVideo Class
(UVC) compliant into MATLAB. This includes Webcams that may be built into laptops or
other devices, as well as Webcams that plug into your computer via a USB port.
Department of Page
27
Plant Disease Detection using in Image Processing

Using simple MATLAB functions, can detect connected Webcams, acquire individual
snapshots from a Webcam, and optionally set up a loop for acquiring images. The webcam list
function allows detecting the connected Webcams. The webcam function creates the Webcam
object that is used to acquire images. And the snapshot function returns a single image from the
camera.

Table 5.1 Supported functions of webcam

Function Purpose
Webcamlist Returns list of Webcams that are connected to the system.
Creates webcam object and connects to the single camera on your
Webcam system. If you have multiple cameras and you use the webcam
function with no input argument, it creates the object and connects it
to the first camera it finds.
Preview Preview the images from the Webcam. Use name of object as input
argument, which is cam in this example: preview(cam)
Acquire a single image from the Webcam. Use name of object as
Snapshot input argument, which is cam in this example.
img = snapshot(cam);

closePreview Close the preview window.

close Preview(cam)

Keil micro vision:

Keil development tools for the 8051 Microcontroller Architecture support every level of
software developer from the professional applications engineer to the student just learning
about embedded software development. The Keil 8051 Development Tools are designed to
solve the complex problems facing embedded software developers.

The Keil µVision Debugger accurately simulates on-chip peripherals of the 8051 device.
Simulation helps us to understand hardware configurations and avoids time wasted on setup
problems. Additionally, with simulation, write and test applications before target hardware is
available.

Department of Page
28
Plant Disease Detection using in Image Processing

KEIL SOFTWARE:

The KEIL 8051 Development Tools are designed to solve the complex problems facing
embedded software developers.In this project we select the KEIL software of version8.08
.Because it provides Device Database and the µVision IDE sets all compiler, assembler, linker,
and memory options for these. Numerous example programs are included in this software, and
also the KEIL µVision Debugger accurately simulates on-chip peripherals (I²C, CAN, UART,
SPI, Interrupts, I/O Ports, A/D Converter, D/A Converter, and PWM Modules) of the 8051
device.

Simulation helps to understand the hardware configurations and avoids time wasted on setup
problems. When testing the software application with target hardware, use the MON51,
MON390, MONADI, or FlashMON51 Target Monitors, the ISD51 In-System Debugger, or the
ULINK USB-JTAG Adapter to download and test program code on the target system.

CONCEPT OF COMPILER:

Compilers are programs used to convert a High Level Language to object code. Desktop
compilers produce an output object code for the underlying microprocessor, but not for other
microprocessors. I.E the programs written in one of the HLL like ‘C’ will compile the code to
run on the system for a particular processor like x86 (underlying microprocessor in the
computer). For example compilers for Dos platform is different from the Compilers for Unix
platform

So if one wants to define a compiler then compiler is a program that translates source
code into object code. The compiler derives its name from the way it works, looking at the
entire piece of source code and collecting and reorganizing the instruction. See there is a bit
little difference between compiler and an interpreter. Interpreter just interprets whole program
at a time while compiler analyzes and execute each line of source code in succession, without
looking at the entire program.

The advantage of interpreters is that they can execute a program immediately. Secondly
programs produced by compilers run much faster than the same programs executed by an
interpreter. However compilers require some time before an executable program emerges. Now
ascompilers translate source code into object code, which is unique for each type of computer,
Department of Page
29
Plant Disease Detection using in Image Processing
many compilers are available for the same language.

KEIL C CROSS COMPILER:

Keil is a German based Software development company. It provides several development tools
like
1. IDE (Integrated Development environment)
2. Project Manager
3. Simulator

4. Debugger
5. C Cross Compiler , Cross Assembler, Locator/Linker

Keil Software provides you with software development tools for the 8051 family of
microcontrollers. With these tools, you can generate embedded applications for the multitude of
8051 derivatives. Keil provides following tools for 8051 development

1. C51 Optimizing C Cross Compiler,

2. A51 Macro Assembler,
3. 8051 Utilities (linker, object file converter, library manager),
4. Source-Level Debugger/Simulator,
5. µVision for Windows Integrated Development Environment.

The keil 8051 tool kit includes three main tools, assembler, compiler and linker. An
assembler is used to assemble your 8051 assembly program A compiler is used to compile your
C source code into an object file A linker is used to create an absolute object module suitable
for your in-circuit emulator.

8051 project development cycle: - these are the steps to develop 8051 project using keil
1. Create source files in C or assembly.
2. Compile or assemble source files.
3. Correct errors in source files.
4. Link object files from compiler and assembler.
5. Test linked application.

Department of Page
30
Plant Disease Detection using in Image Processing
now let us start how to work with keil.
Keil is a cross compiler. So first we have to understand the concept of compilers and cross
compilers. After then we shall learn how to work with keil.

WORKING WITH KEIL:

To open keil software click on start menu then program and then select keil2 (or any
other version keil3 etc. here the discussion is on keil2 only). Following window will appear on
your screen

Fig 6.7
We can see three different windows in this screen. 1) project work space window 2) editing
window 3) output window.
Project workspace window is for showing all the related files connected with your
project.
Editing window is the place where you will edit the code
Output window will show the output when you compile or build or run your project.
Now to start with new project follow the steps
Department of Page
31
Plant Disease Detection using in Image Processing
1. click on project menu and select new project
2. you will be asked to create new project in specific directory

3. give the name of project as "test". By default it will be saved as *.v2 extension.

4. just move to your desired directory and there create a new folder for your project named
"first". Here I am creating new project in d:\keil2\myprojects\first as shown in figure

Fig 6.8

6.4 MATLAB:
MATLAB (matrix laboratory) is a multi-paradigm numerical computing environment. A
proprietary programming language developed by MathWorks, MATLAB allows matrix
manipulations, plotting of functions and data, implementation of algorithms, creation of user
interfaces, and interfacing with programs written in other languages, including C, C++, C#,
Java, Fortran and Python.

Although MATLAB is intended primarily for numerical computing, an optional toolbox uses
the MuPAD symbolic engine, allowing access to symbolic computing abilities. An additional
package, Simulink, adds graphical multi-domain simulation and model-based design for
dynamic and embedded systems.

Department of Page
32
Plant Disease Detection using in Image Processing

6.5 IMAGE PROCESSING:

An image is an array, or a matrix, of square pixels (picture elements) arranged in columns and
rows. In a (8-bit) grey scale image each picture element has an assigned Voice controlled
Humanoid Robot with artificial vision intensity that ranges from 0 to 255. A grey scale image is
what people normally call a black and white image, but the name emphasizes that such an
image will also include many shades of grey.

Figure 6.9 pixel

Each pixel has a value from 0 (black) to 255 (white). The possible range of the pixel
value depends on the colour depth of the image, here 8 bit = 256 tones or grey scales.

A normal grey scale image has 8 bit color depth = 256 grey scales. A ―true color‖
image has 24 bit color depth = 8 x 8 x 8 bits = 256 x 256 x 256 colors = ~16 million colors.

Department of Page
33
Plant Disease Detection using in Image Processing

Figure 6.10: A true-colour image.

A true-colour image assembled from three greyscale images coloured red, green and
blue. Such an image may contain up to 16 million different colors. Some grey scale images
have more grey scales, for instance 16 bit = 65536 grey scales. In principle three grey scale
images can be combined to form an image with 281,474,976,710,656 grey scales.

There are two general groups of ‗images‘: vector graphics (or line art) and bitmaps
(pixel-based or ‗images‘). Some of the most common file formats are:
1. GIF — an 8-bit (256 colour), non-destructively compressed bitmap format. Mostly
usedfor web. Has several sub-standards one of which is the animated GIF.Voice
controlled Humanoid
2. JPEG — a very efficient (i.e. much information per byte) destructively compressed 24
bit (16 million colours) bitmap format. Widely used, especially for web and Internet
(bandwidth-limited).
3. TIFF — the standard 24 bit publication bitmap format. Compresses non-destructively
with, for instance, Lempel-Ziv-Welch (LZW) compression.
4. PS — Postscript, a standard vector format. Has numerous sub-standards and can be
difficult to transport across platforms and operating systems.
5. PSD – a dedicated Photoshop format that keeps all the information in an image
including all the layers.

6.6 Embedded C

Embedded C is a set of language extensions for the C programming language by the C

Department of Page
34
Plant Disease Detection using in Image Processing
Standards Committee to address commonality issues that exist between C extensions for
different embedded systems. Historically, embedded C programming requires nonstandard
extensions to the C language in order to support exotic features such as fixed-point arithmetic,
multiple distinct memory banks, and basic I/O operations.

In 2008, the C Standards Committee extended the C language to address these issues
by providing a common standard for all implementations to adhere to. It includes a number
of features not available in normal C, such as, fixed-point arithmetic, named address spaces,
and basic I/O hardware addressing. Voice controlled Humanoid Robot with artificial vision
Embedded C uses most of the syntax and semantics of standard C, e.g., main() function,
variable definition, data type declaration, conditional statements (if, switch case), loops (while,
for), functions, arrays and strings, structures and union, bit operations, macros, etc.

CHAPTER 6: ADVANTAGES AND DISADVANTAGES

Advantages
 More accurate results can be obtained by image processing.
 The machine vision or the digital image processing is a non-destructive method.
 Digital image processing method which is fast and cheap.
 Image processing has a efficient recognizing capability.
 Unrecognizable features can be made prominent.

Disadvantages
 Accuracy is less if the system is trained for less number of training datasets.

Applications
1. Food processing Industry
2. It can be used in Agriculture Fields
Department of Page
35
Plant Disease Detection using in Image Processing

CHAPTER 7: CONCLUSION AND FUTURE SCOPE

Here we propose a method based on image processing and embedded system to automatically
to detect plant disease using a simple cheap webcam instead of costly multiple sensors. The
overall operation is initialized with image acquisition. It is implemented by capturing images of
infected plant leafs. Features are extracted from image and stored. In classification image is
compared with trained features from database. The activity detected is displayed and voice is
enabled for the same. Hence this system is assistance to farmers for knowing the disease
infected to the plants in early stage and to take appropriate measures. The setup used is also
very common and easily available. This is also more accurate than the human visual inspection.
All this leads to better quality.

FUTURE SCOPE:

In future the proposed system can be made fully automatic with increased accuracy of detection
by using high definition camera and it can be implemented in DSP processor for real time
processing.

Department of Page
36
Plant Disease Detection using in Image Processing

Images of Plant Disease

Department of Page
37
Plant Disease Detection using in Image Processing

REFERENCES

[1] of Advanced Research in Electrical, Electronics and Instrumentation Engineering(An ISO

3297: 2007 Certified Organization)Vol. 5, Issue 3, March 2016 Sanjay B. Patil, Dr. Shrikant K.
Bodhe, Leaf Disease Severity Measurement Using Image Processing” International Journal of
Engineering and Technology Vol.3 (5), 2011, 297-301

[2] Jundare Manisha, Jundare Pallavi, Jundare Pragati, Prof. C.S.Aryan, “Plant Disease
Detection and its Treatment using Image Processing” International Journal

[3] Prakash M. Mainkar, Shreekant Ghorpade, Mayur Adawadkar, ”Plant Leaf Disease
Detection and Classification Using Image Processing Techniques” International Journal of
Innovative and Emerging Research in Engineering e-ISSN: 2394 – 3343 p-ISSN: 2394 – 5494

[4] Vaibhavi S. Bharwad , Kruti J. Dangarwala,” Recent Research Trends of Plant Disease
Detection” International Journal of Science and Research (IJSR) ISSN (Online): 2319-7064
Index Copernicus Value (2013): 6.14 | Impact Factor (2014): 5.611

Department of Page
38
Plant Disease Detection using in Image Processing

[5] Prof. Sanjay B. Dhaygude, Mr.Nitin P.Kumbhar, “Agricultural plant Leaf Disease
Detection Using Image Processing” International Journal of Advanced Research in Electrical,
Electronics and Instrumentation Engineering Vol. 2, ISSN: 2278 – 8875, Issue 1, January 2013

[6] Surender Kumar , Rupinder Kaur ,” Plant Disease Detection using Image Processing A
Review” International Journal of Computer Applications (0975 – 8887) Volume 124 – No.16,
August 2015

[7] Sushil R. Kamlapurkar. “Detection of Plant Leaf Disease Using Image Processing
Approach” International Journal of Scientific and Research Publications, Volume 6, Issue 2,
February 2016 ISSN 2250-3153

[8] Y.Sanjana , Ashwath Sivasamy , SriJayanth,” Plant Disease Detection Using Image
Processing Techniques” International Journal of Innovative Research in Science, Engineering
and Technology (An ISO 3297: 2007 Certified Organization) Vol. 4, Special Issue 6, May 2015

[9] Jayamala K. Patil , Raj Kumar, “Advances In Image Processing For Detection Of Plant
Diseases” Journal of Advanced Bioinformatics Applications and Research ISSN 0976-2604 Vol
2, Issue 2, June2011, pp 135-141

[10] M.Malathi , K.Aruli , S.Mohamed Nizar , A.Sagaya Selvaraj, “A Survey on Plant Leaf
Disease Detection Using Image Processing Techniques” International Research Journal of
Engineering and Technology (IRJET) e-ISSN: 2395-0056 p-ISSN: 2395-0072 Volume: 02
Issue: 09 | Dec-2015

Department of Page
39