Computer Vision

principles and practice

A math-first approach to learning computer vision in a classroom setting

Computer Vision

principles and practice

A math-first approach to learning computer vision in a classroom setting

Venue: JustCo at Samyan Mitrtown - Bangkok
24 - 25 February 2020
18.30 - 21.30
3 hours x 2 days
Difficulty: Beginner
Delivered in English
Investment: THB 9.000

Quality Classroom
We pay meticulous attention to the logistical details of our workshops: quality audio and visual setups, comfortable sitting arrangements, small group size, large displays and extra monitors. Dinners are included for evening workshops and lunch for afternoon workshops.
Workshop Lecturer’s Notes
Including Course Book (PDF), HTML files, course transcripts (if any).
Highly-accelerated Learning
Learn under the assistance of our lead instructor and a band of qualified teaching assistants throughout the 2 – day course.
Certification of Completion
Show current and prospective employers that you’ve completed the course with a signed certificate of completion.

Testimonials from previous workshop

The intended audience for this course and accompanying workshop are absolute beginners who have an interest in computer vision and the application of artificial intelligence in modern day CV libraries. Some familiarity in Python and / or geometry will be helpful but is not required as the instructor assumes no prior math / programming knowledge for all workshops in the Classroom series.

The lecture is carried out by a Lead Instructor, and adopts a learn-by-building approach. Participants are required to bring their personal laptop to follow each section and write code to solve small challenges procedurally.

Syllabus

CHAPTER 1: Image Transformation

Affine Transformation
- Definition
  - Mathematical Definitions
- Practical Examples
- Motivation
- Getting Affine Transformation
  - Trigonometry Proof
- Code Illustrations
- Summary and Key Points
- Optional video
  - Rotation Matrix Explained Visually
- References and learn-by-building modules

CHAPTER 2: Kernel Convolutions

Kernel Convolutions
Definition
- Optional video
  - Kernel Convolutions Explained Visually
- Mathematical Definitions
- Padding
Smoothing and Blurring
A Note on Terminology
- Kernels or Filters?
- Correlations vs Convolutions?
Code Illustrations: Mean Filtering
Role in Convolution Neural Networks
Handy Kernels for Image Processing
- Gaussian Filtering
- Sharpening Kernels
- Gaussian Kernels for Sharpening
- Unsharp Masking
Summary and Key Points
References and learn-by-building modules

CHAPTER 3: Edge Detection

Edge Detection
Definition
Gradient-based Edge Detection
- Sobel Operator
  - Discrete Derivative
  - Code Illustrations: Sobel Operator
- Gradient Orientation & Magnitude
Image Segmentation
- Intensity-based Segmentation
  - Simple Thresholding
  - Adaptive Thresholding
- Edge-based Contour Estimation
  - Contour Retrieval and Approximation
- Canny Edge Detector
  - Edge Thinning
  - Hysteresis Thresholding
References and learn-by-building modules

Quiz and Certification

Attempt a 7-question quiz in class
Attempt all learn-by-building modules in the coursework
Successful attempts are rewarded with a badge
All participants are given a certificate of completion

The workshop will be delivered in English. Participants will learn in a classroom setting by following the lecture with a personal laptop.

Course Material Preview

Course Preview

Frequently Asked Questions

Is this program open to person with non IT background?

Yes! This program is open for those who does not have technical background previously.

What is the output I can expect to receive out of this program?

Using image transformation to restore a skewed map
Build an object counter (count number of penguins in a picture, count number of LEGO bricks in a picture) by applying edge detection principles

How the learnings will be able to be implemented in real life business cases?

A couple of examples in each industry :

Agricultural : Count the number of crops
Warehousing : Count very quickly the number of carton boxes, packages in each area of warehouse, Identify odd shapes, Identify outliers
Logistics : Quickly scanning the number of vessels / ships etc for defense / border control
Medical : X-ray imagery
Surveillance : Count number of people walking into the store, Attendance system

And many other industries and application.

Instructor

Samuel Chan

Samuel Chan

An RStudio-certified instructor and machine learning practitioner in the field of marketing automation, fraud detection, finance and e-commerce. Samuel is Indonesia’s top-ranked Stack Overflow user in R (top 5% worldwide) for three years running, and boasts certifications from RStudio, Microsoft, MongoDB, Neo4J Database, Stanford University, John Hopkins University, among others.

Prior to Algoritma, he has 8 years of working experience, including a stint as in-house consultant to several public-trading companies from his time staying in China, Japan and Singapore. He is today an active trainer and consultant for various companies in the financial industry. He has guest lectured in various campuses: Binus, NUS (National University of Singapore)’s The Logistics Institute, University of Indonesia, Universitas Gadjah Mada (UGM), Binus, Institute of Technology Bandung (ITB), Telkom University etc. Courses he authored are offered also in Singapore through Ngee Ann Polytechnic.

Samuel is also among the first recipients of Microsoft Professional Program Certificate in Data Science in Southeast Asia, having demonstrated proficiency in R, Python, Microsoft Azure, SQL / T-SQL, PowerBI and a list of other technologies, and among the first to be certified in RStudio’s program. Technical committee member and competition judge on Finhacks 2018, the largest Machine Learning competition of the year organized by PT. Bank Central Asia (BCA) and DailySocial.