(Color Identification in Images) : Iot & Computer Vision

You might also like

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 17

IoT & COMPUTER VISION

(Color Identification In Images)


INTERNSHIP TRAINING REPORT

SUBMITTED BY
SHARATH CHANDRA PALLE (T190953051)

UNDER THE SUPERVISON OF


MR. PRANAV DUBEY
MANAGING DIRECTOR,
THE SPARKS FOUNDATION

TE (ELECTRONICS AND TELECOMMUNICATION)


DEPARTMENT OF ELECTRONICS AND TELECOMMUNICATION

HOPE FOUNDATION’s
INTERNATIONAL INSTITUTE OF INFORMATION TECHNOLOGY,
HINJAWADI, PUNE(MH)-411057

SAVITRIBAI PHULE PUNE UNIVERSITY


A.Y. 2021-22
2
CERTIFICATE
DEPARTMENT OF ELECTRONICS AND TELECOMMUNICATION
HOPE FOUNDATION’s
INTERNATIONAL INSTITUTE OF INFORMATION TECHNOLOGY,
HINJAWADI, PUNE-411057

This is to certify that Sharath Chandra Palle (T190953051), class of TE(E&TC) has satisfactorily
completed the internship as part of fulfilling the requirements of Internship (304199) course in the
Semester II of TE E&TC Engineering (A.Y. 2021-2022) of Savitribai Phule Pune University.

Dr. S.M.M. Naidu Dr. Risil Chhatrala


Internship Coordinator HoD(E&TC)

External Examiner

Place: Pune
Date:

3
Internship Certificate

4
Internship Place Details

Industry Name: The Sparks Foundation


Address: THE HANGAR, NUS ENTERPRISE
21 HENG MUI KENG TERRACE, SINGAPORE, 119613

Website: https://www.thesparksfoundationsingapore.org/

External Supervisor Name: Pranav Dubey


Designation: Managing Director
Email ID: info@thesparksfoundation.sg
Contact Number: +65-8402-8590,

A. Company background-organization and activities

The Sparks Foundation (TSF) is a non-profit organization registered in India and Singapore. We envision
a world of enabled and connected little minds, building the future. They aim to inspire students, help them
innovate, and let them integrate to build the next generation of humankind. The Sparks Foundation help
the students to integrate and help each other, learn from each other, and do well together.
The Graduate Rotational Internship Program (GRIP) is the flagship program of TSF in which students,
recent graduates, and professionals focus on technical skills development as well as professional profile
improvement on LinkedIn. The program gives young aspiring minds a learning platform to connect with
students and professionals from varied diversity, background, skills, and countries. During the Covid-19
pandemic, the format of GRIP is a 1-month, unpaid, and virtual internship .

B. Scope and object of the study

Internet of Things (IoT) conceptualizes the idea of remotely connecting and monitoring real world objects
(things) through the Internet. Computer vision is the science that means to give a comparative, if not
better, capacity to a machine or PC. Computer vision is worried about the programmed extraction,
investigation and comprehension of valuable data from a single picture or a grouping of pictures. Some of
the basic image processing capabilities include filtering, edge detection, corner detection, sampling and
interpolation, color conversion, morphological operations, histograms and many more. Color detection
using OpenCV has many advantages like, it allows the detection of a specific color in a livestream video
content. In this OpenCV color detection system there are four major modules, activated webcam, scan
object, match frame parts and system results.

C. Personal observation
The internship opportunity that I had with The Sparks Foundation was a great chance for learning and
professional development. I'm grateful for having a chance to meet so many wonderful people and
professionals through this internship period. I take this opportunity to express my heartfelt gratitude to
each one of them. OpenCV may be a library of programming functions mainly aimed toward real-time
computer vision. In simple language, it's a library used for Image Processing. It’s mainly wanted to do all
the operations associated with Images. I put in the library on the computer. I begin writing the code which
will make use of the various features in OpenCV. I build this code and run it to perform the task you
described. OpenCV may be a Computer Vision library with APIs that permit you found out a pipeline for
your Computer Vision project.

5
Table of Contents

1 Introduction 7

2 Objectives 7

3 Motivation & Scope of the Study 7

4 Methodological Details 7

5 Results / Analysis / Inferences and Conclusion 12

6 Suggestions / Recommendations for Improvement to Industry 14

7 Reference (Library books, magazines and other sources) 14

8 Appendix 15

6
1. Introduction
My project of Color detection System can work in any computer with minimum specification.
The detection process takes less than a moment and this is very beneficial for companies. The
first thing to start with is observation. With the help of Color Detection, it will be easy to identify
the color and give its name to the persons using it. This project is made to reach each and
everyone in the society suffering from color blindness so that everyone can get benefit from this.
Color Detection technology is very accurate and no one can doubt it. The project designed by us
can be used through basic camera also. No special cameras are required for its basic functioning,
but for using it as an assistant in self drive cars the camera should be good and more than one
should be used for getting an overall view around the car. And all the cameras should be
connected to each other.

2. Objectives
In this color detection Python project, the objective of this study is to build an application
through which you can automatically get the name of the color by clicking on them.

3. Motivation & Scope of the Study


A. Motivation:
The motivation for developing computer vision is the human vision system which is richest sense
that we have. To us vision seems easy, but in reality, we are processing around 60 images per
second with millions of points (pixels) in each image. In fact, over half the human brain is
involved in processing visual information, and this seems a good indication that this is a very
complex task.

B. Scope of the Study:


Colors are made up of 3 primary colors; red, green, and blue. In computers, we define each color
value within a range of 0 to 255. So in how many ways we can define a color? The answer is
256*256*256 = 16,581,375. There are approximately 16.5 million different ways to represent a
color. In our dataset, we need to map each color’s values with their corresponding names. But
don’t worry, we don’t need to map all the values. We will be using a dataset that contains RGB
values with their corresponding names.
In this work, we design and implement a color recognizer using Python. This process is also
known as “Color Detection”. We will create a basic application that will help us to detect the
colors in an image. The program will also return as the RGB values of the colors, which is really
helpful. Many graphic designers and web designers will understand how RGB values can be
helpful. Building a color recognizer is a great project to get started with Computer Vision.

4. Methodological Details
A. Capturing and Storing Image:
In this, the capturing of image takes place. The image stored in this process is later used for
detecting the color.
B. Image Processing:
• In this module, the programs run over gives the image for further operation.
• When all the images are perfectly processed and the program is ready to detect the color.
C. Color Detection:

7
• In this module, the programs has completed the Image Processing and is ready to take the input
of the user.
• The program which is already displaying the window can now be clicked anywhere and it will
display the color present there.
• The user Clicks on the image anywhere of whose color he wants to know.
• When the user double clicks anywhere he gets the color name along with their R, G, B values.

Figure 1. Block Diagram

Implementation:

Figure 2. Flow Chart

Step-1 :
Install Python-OpenCV To implement this project.
Step-2:

8
First import all the required modules.

Figure 3. Importing Module

Step-3:
Then we read the Image File.

Figure 4. Reading the Image File

Step-4:
We have colors.csv which has all the encodings of the color as shown below.

9
Figure 5. Encodings of the color

Step-5:
Then we initialize the variables, this part of the code converts them to R,G,B Values.

Figure 6. Conversion to R,G,B Values

This R,G,B values are then converted to the color using the data frame that was loaded
previously with the minimum deviation.

10
Figure 7. Conversion into color

This part prints color on the screen.

Figure 8. Printing color on the screen

11
5. Results / Analysis / Inferences and Conclusion
Results:

The RGB color model giving the accuracy that it is leads to believe that the other color models as well
may have a wing of accuracy. Further research has revealed a neat difference in the color models, which
have been discussed below. All work on how color is viewed by a computer and given the fact that
today’s world is filled with their desired data, none of the color models can be shunned. We can only
depend on accuracy of actual color / data viewed by human eyes since the constraints of computer vision
lie in the pixel quality of the hardware it is subject to.

Figure 9. Identifying the Color Green

Figure 10. Identifying the Color Gray

12
Figure 11. Identifying the color Orange

A. Analysis:

Color detection using OpenCV, allows detection of specific color in an image. In this
OpenCV detection system read the image, scan the object, match the color and give the
result. If the Color is matched with a defined color pattern by RGB color model then the
system gets the correct output as a result. This design can be used for various application
based upon vision through computer for the purpose of identifying, differentiating and
collection of various objects are done based upon color, shape and size which are the
primary factors. This can be done with help of an OpenCV.

B. Inferences:

We defined to get the required color field from an RGB image. In this various step are
implemented using OpenCV platform. The main positive point of this method is its color
differentiation of a mono color. The detection of the edge detection techniques has different other
applications like facial detection, color conversion for grey scale image etc. that can also be
implemented.

C. Conclusion:

Detecting colors with our physical eyes is always difficult in the sense that some colors
resemble one another. Also, Color vision deficiency is commonly known as color blind,
is a type of vision defect in our eyeball. The inability to recognize color has caused
several problems to the patient daily life and in conducting certain color oriented
activities. Color detecting system makes it easier and simple when detecting colors. This
system was design in a way that it will automatically get the name of the color by
clicking on them.

13
6. Suggestions / Recommendations for Improvement to Industry

A. Suggestions:
In existing system there is no exact color representation of colors with accuracy. In proposed
system, we are introducing the CV datasets and according to it the number of shades that can
be identified using 865 color names along with their RGB and hex values. Whenever the
cursor clicks the image, it automatically shows the RGB shades color values. Proposed
system uses OpenCV for sorting of primary colors.

B. Recommendations for Improvement to Industry:


Color Detection in real life is a blooming concept. But there is still much to uncover. With
changing technology in a fast paced and impatient world, we can look forward to heights that
now seem unattainable.

7. Reference
[1] Reetu Awasthiand Khushboo Khurana, “Techniques for Object Recognition in Images and Multi-
Object Detection”,(IJARCET), ISSN:2278-1323,4th , April 2013.
[2] Artificial Intelligence. https://en.wikipedia.org/wiki/Artificial_intelligence
[3] Computer Vision. (December 2017). https://en.wikipedia.org/wiki/Computer_vision
[4] Computer Vision’s Open Source. https://en.wikipedia.org/wiki/OpenCV
[5] Object Detection. http://en.m.wikipedia.org/wiki/Object_detection
[6] Numpy.org, 2017. http://www.numpy.org [7] https://www.invensis.net/blog/it/benefits-of-python
overother-programming-languages/

14
8. Appendix

A. Checklist for the internship file submission

Checklist
304199: Internship (TE E&Tc 2019 Course)

Sr. Checklist Name Available Remarks


No. & Attached
Yes/No
1 Student Request/Permission Letter for Internship (If
No
available include it in the Appendix of the Internship
Report)
2 Internship confirmation Letter/ Email (Mandatory to
Yes
include it in the Appendix of the Internship Report)
3 Joining Report/ Letter / Email. (Mandatory to include it
Yes
in the Appendix of the Internship Report)
4 Weekly Update Report Submitted to the Mentor by an
No
Email or Printed copy
5 No
Internship Workbook with timely entries
6 Internship Training Report After Completion of
Yes
Internship (Mandatory to Prepare and Bring it on the day
of Presentation/Oral Exam)
7 Internship Certificate (Mandatory to include it in the
Yes
internship training report)
8 Feedback on your availability & performance during
Yes
your internship, an email/letter from the external mentor
(Mandatory to include it in the Appendix of the
Internship Report)

Student Name:

Signature:

15
B. Student Request/Permission Letter for Internship (if available) scan copy [NA]

C. Internship confirmation letter/ email scan copy

Figure 12.Selection Certificate

D. Joining Report/ Letter / Email scan copy

E. Feedback from internship supervisor (External and Internal) with following recommended
parameters through a email or letter:[ ]
a. Technical knowledge
b. Discipline
c. Punctuality
d. Commitment
e. Willingness to do the work
f. Communication skill
g. Individual work
h. Team work
i. Leadership

16
Figure 13.Allotment Of Badge

Figure 14. Verification Of Badge

17

You might also like