A circlip (circular-clip) is a semi-flexible metal ring used as a fastener in advanced industrial machinery. Faults or defects in the circlip can cause the entire machinery to fall off. Hence, sorting of circlips as "good" or "faulty" is imperative.
HARDNESS, FRACTURE TOUGHNESS AND STRENGTH OF CERAMICS
Defect detection in circlips using image processing in ni lab view
1. SHRI RAMDEOBABA COLLEGE OF ENGINEERING
AND MANAGEMENT, NAGPUR.
F I N A L Y E A R P R O J E C T
By:
• Sayali Bodhankar - 18
• Mayur Harisangam - 53
• Akash Kharde - 79
• Shubham Patwardhan - 81
Project Guide:
• Prof. B. Lad.
3. What is a circlip?
• A circlip (circular clip) is a type
of fastner or retaining ring consisting of a
semi-flexible metal ring with open ends
which can be snapped into place, into
a machined groove on a dowel pin or other
part to permit rotation but to prevent
lateral movement.
• Circlips are often used to secure pinned
connections.
4. Literature
Survey
• Mostly used for surface defect detection like sheet metal, fabric
textiles etc.
• Process: surface image is acquired by using a camera from top of
the surface from a distance adjusted so as to get the best possible
view of the surface.
• R-G-B image is converted into grey scale.
• Noise removing and filtering.
• Thresholding is done to get those pixels which represents an object.
• Histogram equalisation :
Histogram equalization is a method for stretching the contrast by
uniformly distributing the grey values enhances the quality of an image
useful when the image is intended for viewing.
• This method is applicable to differentiate textures , also the method
detects a variety of defects for a given texture.
1. Texture Defect Detection:
5. Literature
Survey
• This method is generally used for detection moving objects in videos from
static cameras.
• Generally an image’s regions of interest are objects (humans, cars, text
etc.) in its foreground.
• The rationale in the approach is that of detecting the moving objects
from the difference between the current frame and a reference frame,
often called “background image”, or “background model.
2.Foreground extraction and background
subtraction
6. Literature
Survey
• PCA is used to extract features of stored image and test
image.
• The Euclidian distance applied between the features of
standard images and the features of the test image, to
recognize the highest similarity image from the standard
image to the test image.
3.Principle Component Analysis:
9. Dilation :
This operation is used to restore boundaries of the particles eroded due to erosion
operation. A dilation eliminates tiny holes isolated in particles and expands the particle
contours according to the template defined by the structuring element. This function
has the opposite effect of an erosion because the dilation is equivalent to eroding the
background.
For any given pixel P0, the structuring element is centered on P0.The pixels masked by a
coefficient of the structuring element equal to 1 then are referred to as Pi.
If the value of one pixel Pi is equal to 1, then P0 is set to 1, else P0 is set to 0.
If OR(Pi) = 1, then P0 = 1, else P0 = 0.
Firstly an Erosion operation is performed to eliminate the pixels isolated in the
background.
For a given pixel P0, the structuring element is centered on P0. The pixels
masked by a coefficient of the structuring element equal to 1 are then referred
as Pi.If the value of one pixel Pi is equal to 0, then P0 is set to 0, else P0 is set to
1.If AND(Pi) = 1, then P0 = 1, else P0 = 0.
According to the erosion operation mentioned above a pixel is cleared if it is
equal to 1 and the three neighbours to its left are not equal to 1.
However this operation also erodes the contour of particles according to the
template defined by the structuring element.
Local Thresholding:
The average is referred to as local mean m(i,j) at pixel (i,j).
An image B(i, j) is calculated as
B(i, j) = I(i, j) – m(i, j)
where m(i, j) is the local mean at pixel (i, j).
An optimal threshold is determined by maximizing
the between-class variation with respect to the threshold.
The threshold value is the pixel value k at which the following expression is maximized
B2=[T(k)-(k)]2/(k) [1-(k)]
where
(k)=i=0kip(i) , T=i=0N-1ip(i)
● i represents the gray level value.
● k represents the gray level value chosen as the threshold.
● h(i) represents the number of pixels in the image at each gray level value.
● N represents the total number of gray levels in the image. (256 for an 8-bit image)
● n represents the total number of pixels in the image.
10. Thresholding
Thresholding sets each grey level that is less than or equal to
some prescribed value T‐called the threshold value‐to 0, and
each grey level greater than T is changed to K ‐ 1.
Thresholding is useful when one wants to separate bright
objects of interest from a darker background or vice versa.
The thresholding transformation is defined by:
T(i,j) = k-1 ; I(I.j)>T
T(I,j)= 0 ; I(I,j)<T
For Entire Circlip
Inverse Transformation
Inverse Transformation is applied to greyscale
image.
Given greyscale image has 256 grey levels.
K=256
Inverse image: N(I,j)
Greyscale Image: I(I.j)
N(I,j)=(k-1)-I(I,j)
14. Basler Industrial Camera
• Model Name -daA2500-14uc - Basler dart
• Sensor Type -CMOS
• Sensor Size -5.7 mm x 4.3 mm
• Resolution (H x V) -2592 px x 1944 px
• Resolution -5 MP
• Pixel Size (H x V) -2.2 µm x 2.2 µm
• Frame Rate -14 fps
• Power Requirements -Via USB 3.0 interface
• Power Consumption
• (typical) -1.3 W
• Basler dart can be interfaced using USB 3.0.
16. Proximity Sensor
Components Required:
1. LM 358 IC
2. 1 InfraRed LED PhotoDiode pair
3. Resistors: 2 x 270R, 10K
4. Potentiometer: 10K
5. Breadboard
6. Power Supply: (3-12)V
7. Few Breadboard connectors
The sensing component
in this circuit is IR
photo-diode.
More the amount of
Infrared light falling on
the IR photodiode, more
is the current flowing
through it.
(Energy from IR waves is
absorbed by electrons at
p-n junction of IR
photodiode, which
causes current to flow)
This current when flows
through the 10k resistor,
causes potential
difference (voltage) to
develop.
As the value of resistor is
constant, the voltage
across the resistor is
directly proportional to
the magnitude of current
flowing, which in turn is
directly proportional to
the amount of Infra-Red
waves incident on the IR
photodiode.
So, when any object is
brought nearer to the
IR LED, Photo-Diode
pair, the amount of IR
rays from IR LED
which reflects and falls
on the IR photodiode
increases and therefore
voltage at the resistor
increases.
We compare this voltage change
(nearer the object, more is the
voltage at 10K resistor / IR
photodiode) with a fixed
reference voltage (Created using
a potentiometer).
Here, LM358 IC (A
comparator/OpAmp) is used for
comparing the sensor and
reference voltages.
The OpAmp functions in a way
that whenever the voltage at
non-inverting input is more than
the voltage at inverting input, the
output turns ON.
The positive terminal of
photodiode (This is the point
where the voltage changes
proportion to object distance)
is connected to non-inverting
input of OpAmp and the
reference voltage is
connected to inverting input
of OpAmp.
When no object is near the IR
proximity sensor, we need
LED to be turned off. So we
adjust the potentiometer so as
to make the voltage at
inverting input more than
non-inverting.
When any object approaches
the IR proximity sensor, the
voltage at photodiode
increases and at some point
the voltage at non-inverting
input becomes more than
inverting input, which causes
OpAmp to turn on the LED.
In the same manner, when the
object moves farther from the
IR proximity sensor, the
voltage at non-inverting input
reduces and at some point
becomes less than inverting
input, which causes OpAmp to
turn off the LED.
17. Serial Communication by ARDUINO
• Baud Rate = 115200.
• Both sidesof the serial connection(i.e. the
Arduino and your computer) need to be set to
use the same speed serial connectionin order
to get any sort of intelligibledata. If there's a
mismatch between what the two systems think
the speed is then the data will be garbled.
• :Serial.begin(115200) would set the Arduino
to transmit at 115200 bits per second.You'd
need to set whatever software you're using on
your computer (like the Arduino IDE's serial
monitor) to the same speed in order to see the
data being sent.
18. Microcontroller ATmega328
Operating Voltage(logic level): 5V
Input Voltage (recommended): 7-
12 V
Input Voltage(limits): 6-20 V
Digital I/O Pins : 14 (of which6
provide PWM output)
Analog Input Pins: 8
DC Current per I/O Pin: 40 mA
Flash Memory 32KB (ATmega328)
of which2KB used bybootloader
SRAM: 2KB(ATmega328) EEPROM:
1KB (ATmega328) Clock Speed: 16
MHz Dimensions: 0.73" x 1.70"
19. Besler D2500 camera
acrylic circular sheet
15x15 rectangular
plastic container
LED
Proximity Sensor and
Arduino Nano Board
20. Pixel to real world
measurements.
• Image used for calibration.Whatever length
measurement are shown after
image processing are in terms
of pixels. To convert these
measurements to real world
standard units such as
centimetre or metre, we have
to calibrate the program
accordingly. To calibrate the
program, we need to see how
many pixel lengths
correspond to what length in
centimetres. For this purpose
we have taken an image of a
scale and measured its length
in pixels.
27. • Rafael C. Gonzalez, Richard E. Woods, “Digital Image Processing”, 2nd ed.,
Prenticece Hall, Upper Saddle River, New Jersey 07458 .
• Su-Ling Lee and Chien-Cheng Tseng,Senior Member, IEEE, “Color Image
Enhancement Using Histogram Equalization Method without Changing Hue
and Saturation”,2017 IEEE International Conference on Consumer Electronics
- Taiwan (ICCE-TW)
• Mao Xiaobo, Yang Jing ,”Research on Object-background Segmentation of
Color Image Based on LabVIEW”,Proceedings of the 2011 IEEE International
Conference on Cyber Technology in Automation, Control, and Intelligent
Systems, March 20-23, 2011, Kunming, China
• Suresh Babu Changalasetty, Ahmed Said Badawy, Wade Ghribi and Lalitha
Saroja Thota ,”Identification and Extraction of Moving Vehicles in
LabVIEW”,International Conference on Communication and Signal
Processing, April 3-5, 2014, India .
• Abahan Sarkar Graduate Student Member IEEE, Tamal Dutta, and B K Roy
Member, IEEE,”Fault Identification on Cigarette Packets - An Image
Processing Approach ”,2014 Annual IEEE India Conference (INDICON).