SRM INSTITUTE OF SCIENCE AND TECHNOLOGY

COLLEGE OF SCIENCE AND HUMANITIES

DEPARTMENT OF COMPUTER APPLICATIONS

PRACTICAL RECORD NOTE

STUDENT NAME :
REGISTER
:
NUMBER

CLASS :
YEAR &
:
SEMESTER

SUBJECT CODE :

SUBJECT TITLE :

April 2023
 1

SRM INSTITUTE OF SCIENCE AND TECHNOLOGY

COLLEGE OF SCIENCE AND HUMANITIES
DEPARTMENT OF COMPUTER APPLICATIONS
SRM Nagar, Kattankulathur – 603 203

CERTIFICATE

Certified to be the bonafide record of practical work done

by_____________________________Register No______________________of
Degree course for UDS21402J-Introduction to Computer Vision in the
Computer lab in SRM Institute of Science and Technology during the academic
year 2022-2023.

Staff In-charge Head of the Department

Submitted for Semester Practical Examination held on __________________.

Internal Examiner External Examiner

 2

INDEX

Ex.No. Date Title of the experiment Page no Staff sign

1 2/1/23 Read, Write and Show Images

2 9/1/23 Color Space

3 18/1/23 Thresholding Techniques

4 25/1/23 Contour Detection

5 2/2/23 Image Scaling, Rotation and

Translation

6 9/2/23 Edge detection

7 16/2/23 Image filtering,Box Blur

8 23/2/23 Gaussian Blur, Median blur &

Bilateral

9 2/3/23 Sift Invariant Feature Transform

10 9/3/23 Binary Robust Independent

Elementary Transform

11 16/3/23 Face Detection

12 16/3/23 Harris Corner Detection

13 24/3/23 Features from accelerated segment

test

14 31/3/23 Morphological operations

Errosion &Dilation
15 31/3/23 Morphological operations
Open/Close
 3

Date: 2/1/23
Ex.no: Read, Write and Show Images

Aim:

Algorithm:
 4

Source Code:
!pip install opencv-python

from google.colab import drive

drive.mount('/content/drive')

from google.colab.patches import cv2_imshow

import cv2
import numpy as np
image1 = cv2.imread('/content/drive/MyDrive/Human.png')
cv2.imwrite('/content/drive/MyDrive/Human.png',image1)
cv2_imshow(image1)

Output :
Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-
wheels/public/simple/
Requirement already satisfied: opencv-python in /usr/local/lib/python3.9/dist-packages
(4.7.0.72)
Requirement already satisfied: numpy>=1.19.3 in /usr/local/lib/python3.9/dist-packages
(from opencv-python) (1.22.4)

Mounted at /content/drive
 5

Date: 9/1/23
Ex. No: Color Space

Aim:

Algorithm:
 6

Source Code:
import cv2
image1 = cv2.imread('/content/drive/MyDrive/Human.png')
img = cv2.cvtColor(image1, cv2.COLOR_BGR2GRAY)
cv2_imshow(img)
img = cv2.cvtColor(image1, cv2.COLOR_BGR2HSV)
cv2_imshow(img)
img = cv2.cvtColor(image1, cv2.COLOR_BGR2Lab)
cv2_imshow(img)
img = cv2.cvtColor(image1, cv2.COLOR_BGR2RGB)
cv2_imshow(img)

Output:
 7

Date:18/1/23
Ex. No: Thresholding Techniques

Aim:

Algorithm:
 8

Source Code:
import cv2
image1 = cv2.imread('/content/drive/MyDrive/Human.png')
ret, thresh1 = cv2.threshold(img, 140, 234, 246, cv2.THRESH_BINARY )
ret, thresh2 = cv2.threshold(img, 45, 247, 234, cv2.THRESH_BINARY_INV)
ret, thresh3 = cv2.threshold(img, 34, 254, 231, cv2.THRESH_TRUNC)
ret, thresh4 = cv2.threshold(img, 249, 248, 123, cv2.THRESH_TOZERO)
ret, thresh5 = cv2.threshold(img, 237, 167, 189, cv2.THRESH_TOZERO_INV)

cv2_imshow(thresh1)
cv2_imshow(thresh2)
cv2_imshow(thresh3)
cv2_imshow(thresh4)
cv2_imshow(thresh5)

Output:
 9

Date: 25/1/23
Ex. No: Contour Detection

Aim:

Algorithm:
 10

Source Code:
import numpy as np
img=cv2.imread('/content/drive/MyDrive/Human.png')
gray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
ret,thresh=cv2.threshold(gray,160,235,0)
contours,hirearchy
=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
print("Number of contours found=",len(contours))
cv2.drawContours(img,contours,100,(150,150,0),3)
cv2_imshow(img)

import cv2
img=cv2.imread('/content/drive/MyDrive/Eagle.png')
gray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
ret,thresh=cv2.threshold(gray,110,234,0)
contours,hirearchy=
cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
cv2.drawContours(img,contours,100,(149,170,0),2)
cv2_imshow(img)

Output:
No of contours found = 157
 11

Date: 2/2/23
Ex. No: Image Scaling,Rotation and Translation

Aim:

Algorithm:
 12

Source Code:
import cv2
import numpy as np
import matplotlib.pyplot as plt
image=cv2.imread('/content/drive/MyDrive/Human.png')
half=cv2.resize(image,(4743,3166),fx=0.1,fy=0.1)
bigger=cv2.resize(image,(1050,1610))
stretch_near=cv2.resize(image,(780,540),interpolation=cv2.INTER_LINEAR)
titles=["Original","Half","Bigger","Interpolation Nearest"]
images=[image,half,bigger,stretch_near]
count=4

for i in range (count):

plt.subplot(2,2,i+1)
plt.title(titles[i])
plt.imshow(images[i])
plt.show()
Image rotation
import cv2
from google.colab.patches import cv2_imshow
img=cv2.imread('/content/drive/MyDrive/Human.png')
window_name='Image'
image =cv2.rotate(img,cv2.ROTATE_90_COUNTERCLOCKWISE)
image1 =cv2.rotate(img,cv2.ROTATE_180)
image2 =cv2.rotate(img,cv2.ROTATE_90_CLOCKWISE)
cv2_imshow(image)
cv2_imshow(image1)
cv2_imshow(image2)
Image Translation
image=cv2.imread('/content/drive/MyDrive/Human.png')
height,width=image.shape[:2]
T=np.float32([[1,0,height/4],[0,1,width/4]])
print('Original image')
cv2_imshow(image)
print('Translated image')
cv2_imshow(cv2.warpAffine(image,T,(width,height)))
 13

Output:
Scaling

Rotation

Translation
 14

Date: 09/02/23
Ex. No: Edge Detection

Aim:

Algorithm:
 15

Source Code :
import cv2
from google.colab.patches import cv2_imshow
img=cv2.imread('/content/drive/MyDrive/Human.png')
low=100
upper=250
edge=cv2.Canny(img,low,upper)
cv2_imshow(edge)

Output:
 16

Date:16/2/23 Image Filtering , Box Blurring

Ex. No:

Aim:

Algorithm:
 17

Source Code :
#Image Filtering :
import cv2
import numpy as np
img = cv2.imread('/content/drive/MyDrive/Human.png')
id_kernel = np.array([[0,0,0],[0,1,0],[0,0,0]])
flt_img = cv2.filter2D(src=img,ddepth=-1,kernel=id_kernel)
cv2_imshow(flt_img)

#Box Blurring:
import cv2
import numpy as np
import matplotlib.pyplot as plt
img = cv2.imread('/content/drive/MyDrive/Human.png')
Rgb=cv2.cvtColor(img,cv2.COLOR_BGR2RGB)
plt.imshow(img)
plt.show()
# It is a unity matrix which is divided by 9
array=np.array([[1, 1, 1], [1,1,1],[1,1,1]])
box_blur_ker =array/9.0
Box_blur = cv2.filter2D(src=img, ddepth=-1, kernel=box_blur_ker)
# Showing the box blur image using matplotlib library function plt.imshow()
plt.imshow(Box_blur)
plt.show()

Output :
Image Filtering:

Box Blurring :
 18

Date:23/2/23
Ex.No: Gaussian Blur, Median Blur & Bilateral

Aim:

Algorithm:
 19

Source Code:
#Gaussian Blur
import cv2
import numpy as np
import matplotlib.pyplot as plt

img = cv2.imread('/content/drive/MyDrive/Human.png')
plt.imshow(img)
plt.show()
#size of kernel
gaussian_blur = cv2.GaussianBlur(src=img, ksize=(3,3),sigmaX=0, sigmaY=0)
#function plt.imshow()
plt.imshow(gaussian_blur)
plt.show()

#Median Blur
import cv2
import numpy as np
import matplotlib.pyplot as plt

img = cv2.imread('/content/drive/MyDrive/Human.png')
plt.imshow(img)
plt.show()
value
median_blur = cv2.medianBlur(src=img, ksize=9)
#Showing the Median blur image using matplotlib library #function plt.imshow()
plt.imshow(median_blur)
plt.show()

# Bilateral Blur
bilateral = cv2.bilateralFilter(image, 9, 75, 75)
cv2_imshow(bilateral)
cv2.waitKey(0)
cv2.destroyAllWindows()
 20

Output:
Gaussian Blur
input image output imge

Median Blur
input image output image

Bilateral Blur
 21

Date:2/3/23
Ex.No: Shift Invariant Feature Transformation

Aim:

Algorithm:
 22

Source Code:
#import required libraries
import cv2
#read input image
img = cv2.imread('/content/drive/MyDrive/Human.png')
#convert the image to grayscale
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
#Initiate SIFT object with default value
sift = cv2.SIFT_create()
#find the keypoints on image(grayscale)
kp=sift.detect(gray,None)
#draw keypoints in image
img2 = cv2.drawKeypoints(gray,kp,None,flags=0)
#display the image with keypoints drawn on it
cv2_imshow(img2)
cv2.waitKey(0)
cv2.destroyAllWindows()
Output:
 23

Date:9/3/23
Ex.No: Binary Robust Independent Elementary Features

Aim:

Algorithm:
 24

Source Code:
import numpy as np
import cv2 as cv
from matplotlib import pyplot as plt
from google.colab.patches import cv2_imshow
img = cv.imread('/content/drive/MyDrive/Human.png', cv.IMREAD_GRAYSCALE)
# Initiate FAST detector
star = cv.xfeatures2d.StarDetector_create()
# Initiate BRIEF extractor
brief = cv.xfeatures2d.BriefDescriptorExtractor_create()
# find the keypoints with STAR
kp = star.detect(img,None)
# compute the descriptors with BRIEF
kp, des = brief.compute(img, kp)
print( brief.descriptorSize() )
print( des.shape )

cv2_imshow(img)

Output:
 25

Date:16/3/23
Ex.No: Face Detection

Aim:

Algorithm:
 26

Source Code:
import cv2
from google.colab.patches import cv2_imshow

img=cv2.imread("/content/drive/MyDrive/Human.png")
classifier=cv2.CascadeClassifier("/content/drive/MyDrive/haarcascade_frontalface_default.x
ml")

gray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)

face=classifier.detectMultiScale(gray)

for x,y,w,h in face:

cv2.rectangle(img,(x,y),(x+w,y+h),(234,45,66),2)

cv2_imshow(img)

Output:
 27

Date:16/3/23
Ex.No: Harris Corner Detection

Aim:

Algorithm:
 28

Source Code:
import cv2
from google.colab.patches import cv2_imshow
import numpy as np
image =cv2.imread('/content/drive/MyDrive/Human.png')
#convert the input image into grayscale color space
operatedImage = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
#modify the datatype #setting to 32-bit floating point
operatedImage = np .float32(operatedImage)
#apply the cv2.cornerHarris method # to detect the corners with appropriate
#values as input parameters
dest = cv2.cornerHarris(operatedImage,2,5,0.07)
#Results are marked though the dilated corners
dest=cv2.dilate(dest,None)
#Reverting back to the original image,
#with optimal threshold value
image[dest>0.01*dest.max()]=[0,0,255]
#the window showing output image with corners
cv2_imshow(image)
Output:
 29

Date:24/3/23
Ex.No: Feature From Accelerated Segment Test

Aim:

Algorithm:
 30

Source Code:
import cv2
#read input image
img = cv2.imread('/content/drive/MyDrive/Human.png')
#convert the image to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
#Initiate FAST object with default values
fast = cv2.FastFeatureDetector_create()
#find the keypoints on image(grayscale)
kp = fast.detect(gray,None)
#draw keypoints in image
img2 = cv2.drawKeypoints(img,kp,None)
#Print all default params
print("Threshold: ",fast.getThreshold())
print("nonmaxSuppression: ", fast.getNonmaxSuppression())
print("neighborhood:", fast.getType())
print("Total Keypoints with nonmaxSuppression:", len(kp))
#display the image with keypoints drawn on it
cv2_imshow(img2)
cv2.waitKey(0)
cv2.destroyAllWindows()
Output:
 31

Date:31/3/23
Ex.No: Morphological Erosion & Dilation

Aim:

Algorithm:
 32

Source Code:
#importing the required modules
import cv2
import numpy as np
#reading the image which is to be eroded using imread() function
img = cv2.imread("/content/drive/MyDrive/Human.png")
#defining the kernel matrix
kernel = np.ones((5,5),np.uint8)
#using erode function on the input image to be eroded
erodedimage = cv2.erode(img,kernel,iterations = 1)
img_dilation = cv2.dilate(img, kernel, iterations=1)
#displaying the eroded image as the output on the screen
cv2_imshow(erodedimage)
cv2_imshow(img_dilation)
cv2.waitKey(0)
Output:

-1
 33

Date:31/3/23
Ex.No: Morphological open & close

Aim :

Algorithm :
 34

Source Code :
#Open
import cv2
import numpy as np
#reading the image which is to be eroded using imread() function
img = cv2.imread("/content/drive/MyDrive/Human.png")
#defining the kernel matrix
kernel = np.ones((5,5),np.uint8)
opening = cv.morphologyEx(img, cv.MORPH_OPEN, kernel)
closing = cv.morphologyEx(img, cv.MORPH_CLOSE, kernel)
#displaying the eroded image as the output on the screen
cv2_imshow(opening)
cv2_imshow(closing)
cv2.waitKey(0)

#CLOSE
#importing the required modules
import cv2
import numpy as np
#reading the image which is to be eroded using imread() function
img = cv2.imread("/content/drive/MyDrive/Human.png")
#defining the kernel matrix
kernel = np.ones((5,5),np.uint8)

close = cv.morphologyEx(img, cv.MORPH_CLOSE, kernel)

#displaying the eroded image as the output on the screen
cv2_imshow(close)
cv2_imshow(img_dilation)
Output:
Open

-1
 35

Close