object sorting with image processing

International Journal of Emerging Technology and Advanced Engineering

Website: www.ijetae.com (ISSN 2250-2459, ISO 9001:2008 Certified Journal, Volume 5, Issue 2, February 2015)

187

―Automation of Object Sorting Using an Industrial Roboarm

and MATLAB Based Image Processing‖ Prof. D. B. Rane

1, Gunjal Sagar S.

2, Nikam Devendra V.

3, Shaikh Jameer U.

4

Department of Electronic Engineering, P.R.E.C. Loni, Savitribai Phule Pune University, India

Abstract— In recent years the importance of process

automation has been increased as the growth of any industry

is directly depends on it. For precise output and accuracy of

industrial process robots with sophisticated sensors are used.

In modern era application of image processing in many

industrial processes has proven its prevalence and dominance.

This paper present color based object sorting system which

uses the machine vision and the operations in image

processing. The proposed work is to develop compact, easy

and accurate objects sorting machine using real time color

image processing method to continuously evaluate and inspect

the color deformity using camera based machine vision. After

the evaluation of quality the object is sorted into predefined

quality groups with the help of pick and place roboarm. If the

inspected object fails to follow quality norms it is rejected out

by the system. The proposed system will have broad areas of

applications in many fields where continuously evaluation of

the quality is required.

Keywords—Roboarm, image processing, machine vision,

webcam, MATLAB, servo motor.

I. INTRODUCTION

Colour based sorting is extensively used in many

industries for sorting purposes to ensure the quality of the

object is up to the mark e.g. Food processing industries,

pharmaceutical industries, automotive industries,

agriculture industries. Such sorting reduces the human

effort, labour cost and also time of operation. Most of

errors caused by humans due to their limited potential are

eliminated due to use of automated system supported by

colour based sorting using image processing.

The field of robotics is growing with a faster rate in

recent years and many advanced technologies are coming

up with their own advancements. Robots due to its ease of

operation used in domestic, industrial and military purposes

thus the horizons of this field are increasing day by day.

The roboarm used in this project work is used to sort the

objects moving on conveyor belt depending upon its colour

properties into the predetermined categories.

This robotic arm is controlled by the controller used i.e.

ARM 7 which is a 32 bit microcontroller having RISC

architecture. This controller is programmed to move the dc

and servo motors used in roboarm. The roboarm is

manufactured using aluminium brackets which are durable

and lightweight. The gripper is used to hold object which is

fitted at the tip of the roboarm.

The software development is the vital task in the

proposed project development. The software is entirely

coded in MATLAB to check the colour of the object used

for sorting purpose. The work in the paper is considered to

sort objects such as apple depending on its attributes such

as colour. Thus by using fully automated system the time

required for the sorting process is reduced to the great

extent, so proposed system is fast, accurate, economical,

robust and cost efficient.

Objectives of the project:

1. To sort objects depending upon the colour.

2. To provide automation to the process using robotic

arm.

3. To analyse the quality of the object.

4. To design easy and simplified operational system.

5. To count and display count of the object.



188

II. BLOCK DIAGRAM

Fig. Block Diagram at control room.

Block Diagram Description:

ARM processor is the heart of the entire system and used

for data analysis and storage. It will capture the all the

answers feed by users and will do the comparison with

standard answers enter by system operator. There various

modules are connected to the system are camera, two pair

of IR sensor, two DC motor, five servomotor, conveyor

belt, display module, power supply module. Camera is

input sensor which is connected to PC using USB cable.

Camera is used to capture real time image of object. There

is PC with MATLAB software is connected to ARM

processor by using RS232 cable. LCD display is connected

to ARM to display object count and message like object is

rejected or object is ok. Driver IC is driving servomotor.

There are two DC motors which are used to drive conveyor

belt. The conveyor motor receives power and signal from

the central supply through rectifier and control circuit. The

control circuit consisting of a 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

about them. Out of these two DC motors one is used as

driver pulley and other is used as idler pulley.

Two types of power supply are required to drive this

system. One is used to drive ARM processor and other is

used for driving DC motor.

ARM7 processor kit is interfaced with PC using RS232

cable. Two pair of IR sensor are used to detect of object at

two different position on the conveyor belt. Roboarm is

most and foremost requirement of the system. Here we are

using 4 axis roboarm. It moves up-down and right-left.

Roboarm is constructed using five servomotors. Out of

these five servomotors one is used at base, two at middle

and two at the arm of the roboarm. Camera is placed at

exactly centre of the conveyor belt.

III. FLOW CHART AND WORKING

B. Object Placement:

It is first part of the system in that all objects which we

have to be sort are placed on the conveyor belt. We have

taken object as fruit in that an apple. Hence we have to

place different size, shape and colour apples on the

conveyor belt. Object placement should be done as one

apple get sorted after that another apple is placed on the

conveyor belt. After placing an apple on the conveyor belt

then start conveyor belt for further processing.

C. Capture Image:

When an apple placed on conveyor belt is cuts first IR

sensor pair. Then conveyor belt is stop moving and takes

stable position. The camera used in this case will be

overhead and it will take the snapshot of the object for

Colour sensing purpose. With the help of camera real time

image of an apple is taken. This image should be good

quality and which is send to PC with MATLAB software.

D. Image Processing:

Important terms related to image processing

Pixel: Pixel is the building blocks of an image. In other

words, a pixel is the smallest possible image that can be

detected on your screen.

Binary Image: An image that consists of mainly black and

white pixels.

Grey scale Image: It contains intensity values ranging from

a minimum (absolute black) to a maximum (absolute

white) and in between varying shades of grey. Typically,

this range is between 0 and 255.

Colour Image: An image is composed of the three primary

colours, Red, Green and Blue. Hence is called as RGB

image.

Idler

Pulley

ARM 7

LCD

Camera

PC with

MATLAB

RS232

IR sensor

Conveyor Belt

Driver

Pulley

Rectifier Unit

Central Power

Supply Unit

Driver

Servo

Motor

Power

Supply



189

RGB value: All colours which we see around us can be

made by adding red, blue and green components in varying

proportions. Hence, any colour of the world can uniquely

be described by its RGB value.

A. Flowchart:

Which stands for Red, Blue and Green values. This

triple colour has each value ranging from 0 to 255, with 0

obviously meaning no component of that particular colour

and 255 meaning full component. For example, pure red

colour has RGB value [255 0 0], pure white has [255 255

255], pure black has [0 0 0] and has RGB value [55 162

170].

Representation of an Image in MATLAB: An image in

MATLAB is stored as a 2D matrix (of size m x n). Where

each element of the matrix represents the intensity of

light/colour of that particular pixel. Hence, for a binary

image, the value of each element of the matrix is either 0 or

1 and for a grey scale image each value lies between 0 and

255. A colour image is stored as an m x n x 3 matrix where

each element is the RGB value of that particular pixel. You

can consider it as three 2D matrices for red, green and blue

intensities. In this total processing we are finding the fruit

is good quality or not.

E. Roboarm:

It is basically 4 axis roboarm. This is used to send an

apple to different position. If apple is good quality then

fruits are get down at trolley at the end of the conveyor

belt. If apple is bad quality then second IR sensor pair is get

activated. When an apple cuts second IR pair then

conveyor belt gets stop and roboarm is get activated. Then

it keeps an apple at its desired location which we have set.

It is a type of mechanical arm, usually programmable, with

similar function to a human arm. The arm may be the sum

total of the mechanism or may be part of a more complex

robot. The links of such a manipulator are connected by

joints allowing either rotational motion or translational

displacement. There are five servomotors are used for

roboarm.

Fig. A four axis roboarm.

START

Initialize DC motors, Servo motors, IR sensor, Camera,

LCD.

Start conveyer belt

Stop conveyer belt

Run conveyer belt

Active second IR pair

Put OK object at trolley

STOP

Is IR

cut?

Capture real time image of object

Verify object using Image processing

Is object

OK?

Activate ROBOARM pick rejected object by ROBOARM

And placed at desired location

Run conveyer belt

When second IR cut then stop conveyer

No

Yes

No

Yes



190

F. Servomotors:

Servomotors are nothing but DC motors. Servomotors

have built in gearing system and feedback loop control

circuitry. These motors do not require any type of driver

circuitry. When the shaft of the motor is at the desired

position, power supplied to the motor is stopped. If not, the

motor is turned in the appropriate direction. The desired

position is sent via electrical pulses through the signal wire.

The motor's speed is proportional to the difference between

its actual position and desired position. So if the motor is

near the desired position, it will turn slowly, otherwise it

will turn fast. This is called proportional control. This

means motor will only run as hard as necessary to

accomplish the task at hand Servomotors have rotary

actuators that allow precise angular position. There are five

servomotors used for roboarm.

Fig. Servomotor

IV. ADVANTAGES

1. High efficiency

2. High speed of operation.

3. High precision: margin of error can be reduced to great

extent.

4. High degree of intelligence.

5. Low failure rate with long life.

6. Reliable operation and maintenance.

7. Fully automatic operation.

V. APPLICATIONS

The robots find numerous applications in industrial,

domestic, medical, pharmaceutical, and hazardous

environment where there are threats to human life. Some

major applications given as follow:

1. Industry: Object sorting roboarm can be used in food

processing industries to sort the fruits depending upon

their colour, dimensions and weight.

2. Medical: Robotic arms are used in telesurgery and

also helpful in precision surgeries.

3. Hazardous environments: roboarm can be used in

environments such as coal mines, radiation places

which is either hazardous or dangerous to access.

4. Defence: Roboarm can be used to defuse the bombs.

5. Roboarm can be used in space exploration programs.

VI. FUTURE SCOPE

The proposed system will be a demo version, so for a

large scale production the number of robotic arms, cameras

and length of conveyor system can be modified. Advance

design of robotic arm can be further used to pick large and

heavy objects and sort them effectively. Generally image

capture is a big challenge as there is a chance of high

uncertainty due to the external lighting conditions. Same

way while collecting object from conveyor system by a

roboarm there is variation in the weight and size of a object

so further design can be modified so fruits can be collected

stably. Speed and efficiency of a system can be further

improved by using ARM9 or ARM11 processor for the

same purpose. Automatic Trolley system can be designed

to guide the sorted objects to their desired locations.

VII. CONCLUSION

The sorting machine sorts the objects depending upon

the colours of the objects successfully with the help of the

roboarm and MATLAB program in image processing. The

USB webcam serves as an eye of the system which

captures the real time image of the objects. The roboarm

picks the faulty quality object and places it at predefined

place, while good quality object continues its motion on

conveyor belt and finally drops into object carrier system.

The LCD displays the object count with the status about the

quality of the object. The servomotors used in the roboarm

plays the vital role as control movement of the roboarm

wholly depends control signal given to servo motor. Hence

to operate the system accurately the synchronization

between IR sensors, dc motors of the conveyor belt and

roboarm is very essential.



191

REFERENCES

[1] Kyunghoon Kim, Soonil Bae, and Kwanghak Huh, ‖ Intelligent

Surveillance and Security Robot Systems,‖978-1-4244-9123-0/1 ©2010 IEEE.

[2] Sahu, S., Lenka, P.; Kumari, S.; Sahu, K.B.; Mallick, B.;―Design a colour sensor: Application to robot handling radiation work‖, Vol.

56, No. 10, pp. 365- 368, 2007, Industrial Engineering.

[3] Project on― Pick n Place Robot‖, made by Bharat Jain and Dinesh Rajput, under guidance of Prof.KaviArya, IIT Mumbai,2010.

[4] A. Collet, D. Berenson, S. S. Srinivasa, and D. Ferguson, ―Object recognition and full pose registration from a single image for robotic

manipulation,‖ International Conference on Robotics and

Automation (ICRA), pp. 48–55, May 2009.

[5] T. Gevers, A. Smeulders, ―Color based object recognition‖, in Proc.

of IEEE Int. Conference on Image Analysis and Processing, 1997, pp. 319 –326.

[6] 2. Rafael c. Gonzalez and Richard e. Woods, "Digital Image

Processing," 2nd Edi., Pearson Education,, pp. 166,191,443 - 458, 488-490, Fifth Reprint 2000.

[7] www.shortcourse.com/www.sensors.com/optical/imagesensors

[8] www.pdfgeni.com/www.indiamart.com/sorting machine

[9] www.google.com/arduino.cc/main/software

[10] www.pdfgeni.com/servo-tutorial

[11] www.pdfgeni.com/matlab- mathematical lab/pdf

object sorting with image processing

Documents