A Project Report
On
Colour Detection using Python
Registration Admission Degree /
Roll number Student Name Sem
No Number Branch
38 2020gu0263@ Nill Hasnain Abbas BSIT(evng) VI
Under the Supervision of
MAM SAIMA
GHAZI UNIVERISTY DERA GHZI KHAN
CANDIDATE’S DECLARATION
We hereby certify that the work which is being presented in the project,
entitled “COLOR DETECTION USING OPENCV” in partial
fulfilment of the requirements for the award of the BSIT submitted in
the Ghazi university dera ghazi khan is an original work carried out
during the period of 2020-24, under the supervision of Mam saima
Department of Computer Science and Engineering, Ghazi university
Dera Ghazi khan
The matter presented in the project has not been submitted by us for the
award of any other degree of this or any other places.
Hasnain Abbas 2020gu0263
Supervisor Name
CERTIFICATE
The Final Project Viva-Voice examination of Hasnain abbas
Evening and their work is recommended for the award of BSIT in
Computer Science Engineering.
Signature of Examiner(s) Signature of Supervisor(s)
Signature of Project Coordinator Signature of Dean
Date : Jun 17, 2023
Place : Dera Ghazi Khan
TABLE OF CONTENTS
S.No Particulars Page No
1 Abstract 3
2 Literature Reviews/Comparative study 4
3 Problem Formulation 5
4 Dataset of Colors 6
5 Calculating Distance 7
6 Required tools 8
7 Output 9
8 Feasibility Analysis 14
9 References 15
Abstract
Color detection is necessary to recognize objects, it is also used as a tool
in various image editing and drawing apps. It is the process of detecting
the name of any color. Well, for humans this is an extremely easy task
but for computers, it is not straightforward. Human eyes and brains work
together to translate light into color. Light receptors that are present in
our eyes transmit the signal to the brain. Our brain then recognizes the
color. Hence the problem that arises in front of us is how to make a
computer understand or recognize colors , so we are going to solve this
problem. So basically in this project using python we need 3 different
parts to be used. Python code which will be recognizing color, Image
that will be used for testing the color recognition, a .csv file that will be
containing the colors
as dataset. Hence the above 3 modules will help us in achieving our aim
that is detecting the colors in an image using python.
Literature Review
[1] Color can be identified from the sensory optic nerves of the eyes.
Color can only be seen or identified when a source of light is applied to
an object. Color blindness can be termed as inability of the
differentiation between colors. It is incurable disease that can be termed
as lifelong disease. Edges can be very helpful in color differentiation
boundary.
[2] Color detection model can be used in mixing of colors especially in
paints, dyes and color pigments. It can be also very helpful in to
differentiating colors that are used in robotics and in other medical
fields. It can also be used in Graphic Arts Industry. Other
implementations can
also be used in agricultural industry like especially detection of quality
of soil.
[3] Color Detection can be used in agriculture industry to find the weeds
the along with the crops. Via color detection weeds can be identified and
destroyed and the crops can be saved. It can be also used in medical
industries to detect the disease and other disorders especially in face and
other internal diseases like cancers.
[4] The main aim of computer vision is to analyze the behavior of
human eye and the reduction of human effort. Through computer vision
various task can be done that is done by human eye, whether to detect
the object or identify its color. By this method it is very helpful to detect
the symptoms of the disease and the other applications in other
industries like agriculture.
Due to its powerful learning ability and advantages in dealing with
occlusion, scale transformation and background switches, deep learning
based object detection has been a research hotspot in recent years. This
paper provides a detailed review on deep learning based object detection
frameworks which handle different subproblems, such as occlusion,
clutter and low resolution, with different degrees of modifications on R-
CNN. The review starts on generic object detection pipelines which
provide base architectures for other related tasks.
Then, three other common tasks, namely salient object detection, face
detection and pedestrian detection, are also briefly reviewed. Finally, we
propose several promising future directions to gain a thorough
understanding of the object detection landscape.
This review is also meaningful for the developments in neural networks
and related learning systems, which provides valuable insights and
guidelines for future progress.
colour detection is the process of detecting the name of any color.
Simple isn’t it? Well, for humans this is an extremely easy task but
for computers, it is not straightforward.
Human eyes and brains work together to translate light into color.
Light receptors that are present in our eyes transmit the signal to
the brain. Our brain then recognizes the color.
Since childhood, we have mapped certain lights with their color
names. We will be using the somewhat same strategy to detect
color names.
Problem Formulation
“It is said that a problem well defined is a problem half solved.”
So here we are talking about a very common disease we come across
nowadays “Color Blindness”.
This is a genetic disease and cannot be easily cured. In this disease the
person suffering with it cannot differentiate between colors. So with the
help of technology .
we can help the person suffering from Color Blindness without
physically operating or doing anything to the person’s eyes.
Now let us formulate it.
Import the modules necessary in solving the problem.
Take the image path of which you want to find the colors in.
Read the csv file in the hex code of colors is stored.
Now calculate the minimum distance from all the color and get the
most matching color using the get_color_name function.
Make a function to get the x, y coordinates of the click point of
mouse.
Display image on the window with a pointer to select any point on
image.
Display the color name of the point along with the R, G, B values
Dataset of colors
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. The CSV file for our dataset has been taken
from this link:
The above dataset contains 865 colors along with their R, G, B values
we will be using this dataset only to get the colors for the mouse clicks.
Calculating Distance
Now as we have already shown in the screenshot that we have the R, G,
B values of the colors that we have attached in the dataset.
Explanation of Code:
Camera Settings: In order to perform runtime operations, the
device’s web-camera is used. To capture a video, we need to
create a VideoCapture object. Its argument can be either the
device index or the name of a video file. The device index is
just the number to specify which camera. Normally one camera
will be connected, so we simply pass 0. You can select the
second camera by passing 1 and so on. After that, you can
capture frame-by-frame. But in the end, don’t forget to release
the capture. Moreover, if anyone wants to apply this colour
detection technique on any image it can be done with little
modifications in the code which I’ll discuss later.
Capturing frames: The infinite loop is used so that the web
camera captures the frames in every instance and is open
during the entire course of the program.
After capturing the live stream frame by frame we are
converting each frame in BGR color space(the default one) to
HSV color space. There are more than 150 color-space
conversion methods available in OpenCV. But we will look
into only two which are most widely used ones, BGR to Gray
and BGR to HSV. For color conversion, we use the function
cv2.cvtColor(input_image, flag) where flag determines the
type of conversion. For BGR to HSV, we use the flag
cv2.COLOR_BGR2HSV. Now we know how to convert BGR
images to HSV, we can use this to extract a colored object. In
HSV, it is more easier to represent a color than RGB color-
space.
In specifying the range , we have specified the range of blue
color. Whereas you can enter the range of any colour you wish.
Masking technique: The mask is basically creating some
specific region of the image following certain rules. Here we
are creating a mask that comprises of an object in blue color.
After that, I have used a bitwise_and on the input image and
the threshold image so that only the blue coloured objects are
highlighted and stored in res.
We then display the frame, res, and mask on 3 separate
windows using imshow function.
Display the frame: As imshow() is a function of HighGui it is
required to call waitKey regularly, in order to process its event
loop.
The function waitKey() waits for key event for a “delay” (here,
5 milliseconds). If you don’t call waitKey, HighGui cannot
process windows events like redraw, resizing, input event etc.
So just call it, even with a 1ms delay .
Summarizing the process:
1. Take each frame of the video.
2. Convert each frame from BGR to HSV color-space.
3. Threshold the HSV image for a range of blue color.
We need a function in the program that is going to return the color of the
point where the mouse is clicked. And as we know for getting the color
we need to get the distance and then compare it with the dataset.
Calculating the distance is done by the formulae given below :-
D= abs (Red-ithRedColor) + abs (Green-ithGreenColor) + abs (Blue-
ithBlueColor)
( ithRedColor, ithGreenColor, ithBlueColor are the colors R,G,B
values from the dataset )
Required tools
OpenCV:
OpenCV (Open Source Computer Vision) library aims at real time
Computer Vision. It is mainly used to do all the operations related
to images.
Pandas:
Pandas is Python Package which stands for Python and data
analysis. This library helps in data manipulation and analysis.
Image Processing:
Image Processing technique is used to perform some certain
operations on an image, in order to get an enhanced image as an
output or to extract some useful information from the image.
It acts as a type signal processing in which input is an image and
output may be an image or characteristics/features associated with
that image (we have used it for resizing the image) .
Output
Feasibility Analysis
Technical Feasibility:
The software is offline and totally based on python so it doesn’t requires
any kind of internet and there can’t be any issue regarding component
not working correctly.
It is compatible for Windows, Linux and Mac.
Resource and Time feasibility:
Resources that are required for the project,
Programming Device
Programming Tool (freely available)
Programming individuals
So this project has the following required resource.
References
Color Blindness
https://www.sciencedirect.com/science/article/abs/pii/S003335069
8005903
Pandas documentation
https://pandas.pydata.org/docs/
OpenCv Documentation
https://opencv.org/
