Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                

AI Master Class Series - Day 3: Introductions To Computer Vision & Its Libraries

Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 25

AI Master Class series – Day 3

Introductions to Computer Vision & its Libraries


Announcement
Attendance link will be available around
8:30 PM.
Day-3 Agenda.

01. 02. 03.


Libraries of
Introduction to Computer Application of
Computer Vision Computer vision
Vision
CV & Image processing vs CV Available libraries and
Evolution & applications
Installing OpenCV

04. 05.
Computer Vision examples Q & A Session
Basic OpenCV functions
What is Computer Vision?.
● Early experiments in computer vision took place in
the 1950s, using some of the first neural networks to
detect the edges of an object and to sort simple objects
into categories like circles and squares.

● Computer vision is an interdisciplinary scientific field


that deals with how computers can gain high-level
understanding from digital images or videos.
Image Processsing vs Computer vision.
Image processing, an image is "processed", transformations are
applied to an input image to get output image.

Computer vision, an image or a video is taken as input, and the


goal is to understand the image and its contents which uses image
processing algorithms to solve some of its tasks like human brain
Evolution. Applications.
● Image Segmentation ● Object recognition
● Edge Detection ● Face recognition
● Watermarking ● Autonomous vehicle
● Steganography ● Disease detection
● Cryptography ● Emotion recognition
● Moving object Detection ● Agriculture
● Object recognition ● Satellite image analysis
● Autonomous Vehicle ● Robot vision
● Satellite image analysis ● Search engines
● Medical image analysis ● Mobile & camera
● OCR ● Pattern recognition
Practical session
Not all Libraries are supporting
Python 3.9
Installing
OpenCV
OpenCV: pip install opencv-python
or
Installing it from the source
Microsoft C++ Build Tools: https://visualstudio.microsoft.com/visual-cpp-build-tools/
or from
Visual Studio
Microsoft Visual studio 2017: https://
my.visualstudio.com/Downloads?q=visual%20studio%202017&wt.mc_id=o~msft
~vscom~older-downloads
Successfully Installed
OpenCV in Python 3.9. But
not all library
Alternate way of Installing
OpenCV & Its libraries without
any error
Installing Python from Visual Studio
Or Install stable version of Python
CMAKE: https://cmake.org/download/
Installing
OpenCV
OpenCV: pip install opencv-python
or
Installing it from the source
Numerical Python Librarie
Scikit-image
NumPy is a library for the Python
programming language, adding support for
s. It includes algorithms for segmentation,
geometric transformations, color space
large, multi-dimensional arrays and matrices,
manipulation, analysis, filtering, morphology,
along with a large collection of high-level
feature detection, and more.
mathematical functions to operate on these
arrays.

Scientific Python PIL


SciPy contains modules for It adds support for opening,
optimization, linear algebra, manipulating, and saving many
integration, interpolation, special different image file formats.
functions, FFT, signal and image
processing

Mahotas Open CV
Mahotas is a includes many algorithms OpenCV is a library of
implemented in C++ for speed while operating programming functions mainly
in numpy arrays and with a very clean Python aimed at real-time computer vision.
interface.
Installing
Libraries

Wheel: pip install wheel


Matplotlib: pip install matplotlib
Imutils: pip install imutils
Scipy: pip install scipy
Successfully Installed
OpenCVand other libraries in
Python 3.7
Basic programs
on Computer
Vision
Read, Show & Write an Image.
import numpy as np
import cv2
img = cv2.imread(‘sample2.jpg')
cv2.imshow(‘show',img)
cv2.imwrite(‘photo.jpg',img)
cv2.waitKey(0)
cv2.destroyAllWindows()
Converting Color Image to Greyscale
Image.
import cv2
image = cv2.imread(‘sample1.png')
greyImage = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
cv2.imwrite('gray_image.png', greyImage)
cv2.imshow(‘Color_image',image)
cv2.imshow(‘Grey_image', greyImage)
cv2.waitKey(0)                
cv2.destroyAllWindows()       
Image Properties.
Import cv2
img = cv2.imread(‘sample2.jpg')
print (img.shape) #(342, 548, 3)
print (img.size) #562248
print (img.dtype) #uint8
Q & A session
AI News – Day 3.
OCT-2020

Speaking at the Responsible AI for Social


Empowerment (RAISE) 2020 summit, PM
Modi said that while he wants India to
become a global hub for AI, it is also a
collective responsibility of the nation to
protect the world from misuse of AI by non-
state actors such as cyber criminals,
terrorists, among others.
Tomorrow
Thanks! session
Do you have any questions? Moving Object Detection and
sanjay@pantechmail.com Tracking using OpenCV

www.pantechsolutions.net

You might also like