Executive Programs

Workshops

Projects

Blogs

Careers

Find Jobs

For Business / Universities

Corporate Training

Hire from US

Academic Up-skilling

All Courses

Choose a category

All Courses

Basics of Computer Vision using Python

A comprehensive course on Computer Vision using Python. This course is highly suited for beginners

Approved Training Partner

RELATED RECENT PLACEMENTS

Shubham Nashirkar

UPR Engineering Pvt Ltd

Rajiv Gandhi College Of Engineering & Research | Top Engineering College in Nagpur

Ritik Rathi

Cyient

Prof.Ram Meghe Institute of Technology & Research

Meghraj Patil

Tech Mahindra

Sinhgad College of Engineering, Pune

Akshay Pawar

Equilibrium Solutions

MET's Institute Of Engineering, Nashik, Maharashtra, India

Akash Dhathombe

DGS Technical Services Pvt. Ltd.

Sant Gajanan Maharaj College of Engineering

Samiksha Kadu

DGS Technical Services Pvt. Ltd.

P. R. Pote Patil College of Engineering and Management

Prasad Chandrakant Paithane

DGS Technical Services Pvt. Ltd.

Dr. Babasaheb Ambedkar Marathwada University

MAYUR KOKANI

DGS Technical Services Pvt. Ltd.

Gharda Institute Of Technology

& 1200+ more

Syllabus

This course is full of best-in-class content by leading faculty and industry experts in the form of videos and projects

Course Overview

This course provides the parameters and processes that define computer vision and delve into details like image processing, edge detection and image segmentation.
This course provides the basics of classical computer vision, 2d and 3d processing, camera projections, use of machine learning in vision systems

Course Syllabus

On a daily basis we talk to companies in the likes of Tata Elxsi and Mahindra to fine tune our curriculum.

Week - 01 Introduction to Computer Vision

General introduction,

History of CV
Formulating the field, why is it a hard topic?

Definition of computer vision

Required components
What qualifies as a vision system

Humans as a vision system: how good do we “see”?
Useful applications
Image acquisition using a camera
Different types of cameras for different domain

Stills, Video, DSLR, Bodycam, Drone
Infrared, Ultrasonography, Magnetic resonance

Physics of Color: color spectrum
Human encoding of color: Rods and cons of eyes
Color spaces:

RGB, CMYK, HSV
Color balance

Camera specifications:

Pinhole
CMOS
CCD

Image specifications:

Pixel (Picture element)
Aspect ratio, HD, Interlacing
Conversions

Type of digital images:

Binary, Grayscale, Color
Conversion techniques

Week - 02 Image processing

Noise Removal

Pixel Neighborhood
Salt and pepper noise
Morphing to hide cracks in the image

Applying filters to images

Convolution of matrices

Types of Filter:

Mean or Box filtering
Median Filter
Mode, Mean, Pass
Generic properties of smoothing
Anisotropic filtering

Gaussian: Isotropy condition, formulation, figure

Weight influence of pixels by their distance to the center pixel
Spread parameter
Motivating examples

Filter Separability

Computation and Maths
Gaussian Separability

Week - 03 Edge Detection

Introduction to edges and gradients

Intensity difference
1D versus 2D edge detection

Edge detection in mammals
1D signals and 2D signals

Difference and derivative mask
Examples

Image Gradient
Image noise: Gaussian noise
Smoothing + Edge detection

Gaussian Derivative Signals

2D gradient operators

Prewitt Masks
Sobel Masks

Steerable filters
Laplacian filters

Laplacian of Gaussian
Zero Crossings

Canny edge detection

Hysteresis thresholding
Non-maximal Suppression

Week - 04 Image Segmentation and features

Thresholding based on histogram
Otsu, Adaptive Otsu

Formulation, Advancements, and effectiveness
Examples

Distance Metric: Norm functions
Thresholding based on different metrics, covariance-based
Different types of background subtraction

Mean, Euclidean, Mahalanobis
Covariance matrix, multidimensional mahalanobis

Shadow modeling

Transform to color spaces

Multimodal background distribution

Gaussian Mixture Model
Foreground Assignment

Clustering to Image Segmentation

Agglomerative Clustering
K Means, K Means ++
Mean Shift Clustering
Hierarchical Clustering

Week - 05 Binary Image Operation

Morphology:

Erosion, Dilation
Open, Close

Connected component

Counting objects: Sequential count etc
Recursive count
Remove Small Features

Hough Transformation Algorithm
Radon Transformation Algorithm
Image Pyramids: Gaussian Laplacian Coding Compression

Week - 06 Shape of Objects

Largest component
Medial axis
Boundary coding
Chain Coding
Shape Numbering
Quadtree Representation
Bounding box
Perimeter, Compactness, Circularity
Centroid
Spatial Moments

Central
Second third order

Similitude Moment
Dimensionality Reduction
Linear basis set
Principal Component Analysis

Eigen Values and Vectors
Finding Eigen sets
Test on synthetic and real data

Face Recognition using PCA: kernel trick

Week - 07 Motion

Definition, simple motion

Image differentiation
Single constant threshold

Weber's Law
Optical flow

Formulas, geometry, example

Normal optic flow
Weighted aggregate,
Hierarchical Motion Estimation
Motion: Use of linear Algebra
3D motion of a point

Matrix operations for different motion in objects
Pinhole Camera Model

2D matrix motion

Translation Motion
Similarity Motion
Affine Motion

Motion History Image

Spatial Pattern of where motion occurred
Progression of motion

Motion Energy Image
Silhouette Difference

Week - 08 Matching & Tracking

Motivation, Example
Feature-based tracking
How to find good features to track
Find Interest Points (General)

Panoramic stitching

Features from Accelerated Segment (FAST)
Harris Detector

Gradients
Window weighing function
Harris Corner Response Function

Week - 09 Interest Point

SURF algorithm
SIFT algorithm for automated feature selection
Free alternative to SIFT and SURF in OpenCV
Laplacian Of Gaussian

Automated Feature selection

Diff Of Gaussian
Covariance tracking

Descriptor Matrix
Finding best match
Rotation Invariance

Kanade-Lucas-Tomasi (KLT) Tracker

Tracking Features
Formulations
Reduction Pyramid
Select “good” feature based on Eigen Value

Mean shift tracking
Weighted histograms using spatial kernels

Evaluating similarity between distributions using Bhattacharyya coefficient

Object tracking by target localization (in each frame) by maximizing the similarity function using mean shift

Template Matching

Sum-of-Absolute Differences
Sum-of-Squared Differences
Normalized Cross-Correlation

Week - 10 Image Registration

Lens

Thin Lens Model
Focus, DoF, Aperture,

Projective Camera Model

Pinhole Camera
Intrinsic and Extrinsic Camera Parameters

Homogeneous Coordinate
Projection

Camera Projection

Camera Matrices

Estimating camera matrices
Extracting parameter P

Calibration
Projection

Perspective Effective
Affine
Orthographic
Weak

Transformation: Translation, Rotation, Skew, Reflection
Planar homography/ Projective Transformation

Solving homography matrix
Normalized Direct Linear Transformation
Example on real 3D data

RANSAC Algorithm
Gold Standard Algorithm

Week - 11 Lens & Camera projection

3D intro

Motivation
Ambiguity in single View

Geometry for simple stereo system
Depth and Calibration
Epipolar Geometry

Baseline, Epipole, Epipolar Line, Epipolar Plane
Epipolar Constraint
Converging camera
Parallel Camera

Camera Motion
Fundamental Matrix

Computation
8 point algorithm

Depth Matrix
Stereo Matching Algorithm

Correspondence Search
Estimate disparity by finding corresponding points
Depth is inversely related to disparity

Stereo Matching as Energy Minimization
Graph cut algorithm

Week - 12 SOTA ML based CV Techniques

LeNet
AlexNet
General detection techniques
YOLO
GAN
Autonomous Vehicle Specific Networks
Gaussian Neural Network
Confidence in classification output: decide object confidence for autonomous vehicle

Our courses have been designed by industry experts to help students achieve their dream careers

Industry Projects

Our projects are designed by experts in the industry to reflect industry standards. By working through our projects, Learners will gain a practical understanding of what they will take on at a larger-scale in the industry. In total, there are 2 Projects that are available in this program.

Real time traffic tracking using matching algorithms

In this project, the students are expected to perform the "matching algorithms" to capture moving pedestrians and vehicles traffic and compare them quantitatively.

Real time video segmentation using machine learning and feature extraction

In this project, students will have to download public road video dataset and design a machine learning based technique to segment and identify specific tasks related to autonomous systems and vehicles using open source and data competitions (can choose between kaggle competitions)

Our courses have been designed by industry experts to help students achieve their dream careers

Ratings & Reviews by Learners

Skill-Lync has received honest feedback from our learners around the globe.

4.6

Basics of Computer Vision using Python

The computer vision online course is quite comprehensive as it covers an array of functions and techniques. Once students enrol in the course, they can easily learn computer vision with Python. The programme begins with some basic concepts and then progresses to the nitty-gritty of the language. Students get a chance to work on a live project where they will get hands-on experience on how computer vision will work with the help of Python.

The computer vision course includes two projects on which the students will be working. The project will consist of fundamentals of Python along with background segmentation and designing of basic techniques that build autonomous systems and vehicles. The computer vision online course will also cover the following aspects:

Introduction to Computer Vision.
Image Processing.
Image Segmentation.
Stereo Vision.
Camera Models.

The computer vision online course will also include 2D shapes and stereo vision. The computer vision course is very comprehensive and will help in understanding Python and then using it practically in real-life based situations. Skill Lync provides the best computer vision course where you can easily learn computer vision with Python and learn the basics of Python, a multipurpose language.

Who Should Take the Computer Vision Online Course?

The computer vision course is ideally designed for students who have prior experience handling Algebra and Statistics. Also, students should opt-in for this course and learn computer vision with Python if they have some basic programming skills or have used platforms like Python, Matlab, etc., before. Also, this course will require them to design a lot of functions. Therefore, students should have decent mathematical skills to join this course. Maximising a function, taking derivatives, etc., will be an important part of the computer vision course.

However, the language is a little difficult, and the course has a few prerequisites. An ideal student is expected to understand Statistics, Algebra, etc., before enrolling on the course. Also, an idea of basic programming is a must-have as Python can get tricky. We offer the best computer vision course to help professionals make a career out of the language.

What Will you Learn?

While students learn computer vision with Python, they will touch upon several other aspects once they get enrolled in the computer vision course. The course gives students two projects to work on, which will help them understand how the industry works on computer vision and how Python can be integrated to use computer vision. Some aspects that students will learn are listed below:

Introduction to Computer Vision and the history.
Image processing and understanding the Pixel neighbourhood.
An introduction to edges and gradients and edge detection in 1D and 2D images.
Segmenting of images and their features.
Morphology and its elements.
Object shapes and sizes and the element of the Medial axis.
Feature-based and matching and tracking and spotting good and trackable features.
Understanding the SURF algorithm and the SIFT algorithm and their alternatives can be brought to use.
Registration of Images.
Projection of the lens and the camera.

Skills You Will Gain?

Here are some of the skills you will acquire once students start working on Python and implementing it to computer vision:

Programming Skills
Statistics
Linear Algebra
Deriving functions
Using Computer Vision and working with all kinds of images
Plotting of data
A sense of how machine learning works
Tools like TensorFlow, Kera’s, etc
Image Processing

Key Highlights of the Programme

The resources shared with the candidates align with the standard industry practices. Students will get an idea as to how things work practically.
Skill-Lync provides certificates to anyone who completes the course. Additionally, a merit certificate will be provided to the top 5% of the course participants.
It is a 3-month course, and access to the course material will depend on the amount you pay.
Several technical engineers will support the students throughout the course.

Career Opportunities after taking the course

There are several career opportunities for people who opt-in for the computer vision course. Engineer, researcher, developer, programmer, and scientist are just a few computer vision occupations available. Opportunities abound, and the pay for these positions is quite competitive.

A computer vision online course will make students abreast with the latest technologies and trends driving computer vision. Not only that, but the course also offers a live project where students can learn computer vision with Python and bring the literature to use. With the help of the live project, students will get a real-time experience using Computer Vision. Students can then take up any job that involves Computer Vision or its application like Image Processing, Object Detection, etc.

FAQs on Basics of Computer Vision using Python

Is Machine Learning an important part of Computer Vision?
Computer vision involves various algorithms, and hence Machine Learning has become an important part of it.
Will we be provided with some reading material for the computer vision course?
Yes, a lot of reading material is provided for you to read from and practice.
Will Cloud Services be a part of the computer vision course?
Yes, but you are not required to be a specialist in the same. An introductory knowledge would be more than enough.
Will I get a certificate post the completion of the course?
You will get a certificate of completion once you finish the course.
Is the course relevant for engineers?
Students who come from a mechanical and computer science background can enrol in this course.
Will the project involve the elements of Image Processing?
Yes, image processing forms a very important part of the live project.
Can I take a trial session before paying for the course?
Yes, you can book a one-on-one demo before making the payment for the course.
Can Computer Vision be used in Autonomous Vehicles?
Computer Vision is very actively used in Autonomous Vehicles, and you can take up the course if you are developing new-age vehicles.