SEGREGATION OF INDIVIDUAL COLOURS IN
The Project deals with an automated
material handling system.
It synchronizes the movement of punch
It aims in classifying the colored objects
which are coming on the conveyor by
punching and placing the objects in its
respective pre-programmed place.
Khojastehnazhand,et al., (2010)
Grading systems give many kinds of information such as size, colour,
shape, defect, and internal quality.
Among these colour and size are the most important features for
accurate classification and/or sorting of citrus such as oranges, lemons
Basically, two inspection stages of the system can be identified: external
fruit inspection and internal fruit inspection. The former task is
accomplished through processing of colour images, while internal
inspection requires special sensors for moisture, sugar and acid contents.
In this paper, an efficient algorithm for grading lemon fruits is developed
and implemented in visual basic environment. The system consists of two
CCD cameras, two capture cards, an appropriate lighting system, a
personal computer and other mechanical parts.
The algorithm initially extracts the fruit from the background. The
samples of different grades of lemon are situated in front of the cameras
and are calibrated off-line. Then information on the HSI colour values
and estimated volumes of fruits are extracted and saved in a database.
By comparing the information during sorting phase with the available
information inside the database, the final grade of the passing fruits is
determined. This algorithm can be easily adapted for grading and/or
inspection of other agricultural products such as cucumber and eggplant.
ZONECONVYER PLACE ZONE
Image processing is used because:
Colour Sensors are not sensitive to shades of
same colour. Here we can use image processing,
For example In metal processing plant, metal
grade ore processing can be done by using image
processing. This is because ore and metal are
almost of the same colour but if we process the
image we can separate ore and metal.
Sensors need calibration while there is no need
for calibration in image processing. Hence in
case certain parameters in a process change we
not only have to update the software but also
calibrate the hardware. But in image processing
only changes have to be made in the software of
Additional sensors are not required for safety
because image processing is real time hence
an integrated system can be developed.
In case if we are picking from a heap of
metal ore then we need an array of sensors
which is more costly compared to image
Certain processes which deal with high
temperature or pressure or any unfavorable
condition. Instead of designing specific
sensors we can simply use image processing.
Also in above processes mechanical wear-
tear takes place of sensors due to exposure
to such high temperatures etc.
The above mentioned image processing is done using Matlab in the following way:
The Image Processing Toolbox software is a collection of functions that extend the
capability of the MATLAB numeric computing environment.
The toolbox supports a wide range of image processing operations, including
1. Spatial image transformations
2. Morphological operations
3. Neighborhood and block operations
4. Linear filtering and filter design
6. Image analysis and enhancement
7. Image registration
9. Region of interest operations
Many of the toolbox functions are MATLAB M-files, a series of MATLAB statements
that implement specialized image processing algorithms.
Thus, colour segregation can be done by using the MATLAB image processing tool box
and we will use the highlighted operations extensively for it.
The resolution of the image should be found out. Generally is in terms
of:[640x480] or [320x240] etc.
Then, the colour is expressed as an RGB triplet (r,g,b), each component
of which can vary from zero to a defined maximum value. If all the
components are at zero the result is black; if all are at maximum, the
result is the brightest representable white.
SETTING THRESHOLD LEVELS : Since a RGB image model will contain
red, green & blue as the constituent colours. Hence, if we are
successfully able to distinguish between the three; rest are just shades of
these colours. Hence, we establish a condition for separate identification
of these colours. One condition per base colour(R or G or B) means three
conditions in all. Also these threshold values for condition are so set that
we are looking for pure base colour to avoid over lapping of base colours.
IDENTIFICATION AND SETTING UP OF MARKER : Now we define a 3-
dimentional matrix which will correspond to the pixel value of the
current image displayed. Once a pixel value corresponds to any of the
three conditions defined above, it should place a marker on it. And start
tracking it wherever it moves on the screen. In case multiple pixel values
satisfy the condition then multiple markers should appear. For continuous
tracking a loop should be used.
MULTIPLE color detection Filtering out different colors
We have found out that instead of treating image as a whole entity
it is sometimes better to segment & process.
Imagine a situation where we have to pick up objects from a heap.
For this we are acquiring a real tim image from a camera source
and if we divide the image, say into 9 cells [3x3] and process it one
We focus on one block at a time and pick up the required objects
and then move to next block.
This prevents the picking mechanism from getting confused and
also since the mechanism is sequential in order, process
automation is easier.
Also since, multiple objects are processed simultaneously faster
processing takes place.
Algorithm can be modified according to the domain of processing
Picking up object from heap: Image
segmentation reduces coding part for picking
mechanism as the image is processed
Color segregation: Objects of different colors
can be processed sequentially. A particular
color object can be separated from rest.
Most of the industrial products are colored
hence there is a large scope for segregation
of these products.
A programmable logic controller (PLC) or programmable
controller is a digital computer used for automation of
electromechanical processes, such as control of machinery
on factory assembly lines, amusement rides, or light
In our case PLC understands:
Logic 0 – 0 V
Logic 1- 24 V
Functions of a PLC:
1. Process synchronization between
Microcontroller, conveyer belt and robotic arm.
2. HMI based control of process.
3. Error report generation.
4. Inventory report.
5. Control via LAN using a remote PC.
6. Active process report. (Via HMI)
A relay is an electrically operated switch. Many relays
use an electromagnet to operate a switching
mechanism mechanically, but other operating
principles are also used.
Relays are used where it is necessary to control a
circuit by a low-power signal (with complete
electrical isolation between control and controlled
circuits), or where several circuits must be controlled
by one signal.
The first relays were used in long distance telegraph
circuits, repeating the signal coming in from one
circuit and re-transmitting it to another.
Relays were used extensively in telephone exchanges
and early computers to perform logical operations.
6V (Sensor output to PLC)
24V(PLC output to Motor)
24V(PLC output to Indicators)
6V(Process control to PLC)
24(timed/PWM) V(PLC to DC)
Data is transmitted serially in one direction
over a pair of wires. Data going out is labeled
Tx (indicating transmission) while data coming
in is labeled Rx (indicating reception). To
create a two way communication system a
minimum of three wires are needed Tx, Rx and
GND (ground). Crossing over Tx & Rx between
the two systems lets each unit talk to the
Punch mechanism: 5V, 20 rpm
Conveyer: 24V, 30 rpm
The DC motors are used to control the arm and turn table movement are
connected to controller circuit and receives signals from micro-
controller. There are IR sensors installed in order to accurately identify
ground and drop places
An electric motor converts electrical energy into mechanical energy. DC
motor design generates an oscillating current in a wound rotor, or
armature, with a split ring commutator, and either a wound or permanent
magnet stator. A rotor consists of one or more coils of wire wound around
a core on a shaft; an electrical power source is connected to the rotor
coil through the commutator and its brushes, causing current to flow in
it, producing electromagnetism. The commutator causes the current in
the coils to be switched as the rotor turns, keeping the magnetic poles of
the rotor from ever fully aligning with the magnetic poles of the stator
field, so that the rotor never stops (like a compass needle does) but
rather keeps rotating indefinitely (as long as power is applied and is
sufficient for the motor to overcome the shaft torque load and internal
losses due to friction, etc.).
Here, the conveyor motor receives power and signal from the
central supply through rectifier and control circuit. The control
circuit consisting of an potentiometer will allow the user to
manually control the speed of conveyor belt by the regulatory
knob. Polyester is used as a belt material.
A conveyor belt consists of two or more pulleys, with a
continuous loop of material - the conveyor belt - that rotates
One or both of the pulleys are powered, moving the belt and the
material on the belt forward. The powered pulley is called the
drive pulley while the unpowered pulley is called the idler.
There are two main industrial classes of belt conveyors; those in
general material handling such as those moving boxes along
inside a factory and bulk material handling such as those used to
transport industrial and agricultural materials, such as grain,
coal, ores, etc. generally in outdoor locations.
The project works successfully and separates
different coloured objects using colour sensor.
The camera based colour detection result was
converted chiefly to the command that drive the
handling systems which drive the pick and place
robot to pick up the object and place it into its
There are two main steps in colour sensing
part, objects detection and colour recognition.
The system has successfully performed handling
station task, namely pick and place mechanism
with help of colour sensor.
.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,
VOL. 45, NO. 8, AUGUST 2007 Walled LTSA Array for Rapid, High
Spatial Resolution, and Phase-Sensitive Imaging to Visualize Plastic
Landmines Soichi Masuyama and Akira Hirose, Member, IEEE.
 CAN bus based on ARM core and the gangue separation system
;Xian-Min Ma; Xiao-Ru Song Machine Learning and Cybernetics,
2005. Proceedings of 2005 International Conference on Volume: 2
Publication Year: 2005 , Page(s): 988 - 992 Vol. 2
 Blobworld: Image Segmentation Using Expectation-
Maximization and Its Application to Image Querying Chad Carson,
Member, IEEE, Serge Belongie, Member, IEEE Hayit Greenspan,
Member, IEEE, and Jitendra Malik, Member, IEEE : IEEE
TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE
. Khojastehnazhand, M., Omid, M., and Tabatabaeefar, A.,
“Development of a lemon sorting system based on colour and size”
Journal of Plant Science, Vol. 4, No. 4, pp. 122-127, 2010.