You have no items in your shopping cart.
Course Details
Course Details
What You'll Learn
Topic 1: Overview of Computer Vision with Deep Learning
Topic 2: Basic Computer Vision Techniques
Topic 3: Image Classification
Topic 4: Object Detection
Topic 5: Computer Vision Systems
Course Info
Minimum Entry Requirement
Knowledge and Skills
- Able to operate using computer functions
- Minimum 3 GCE ‘O’ Levels Passes including English or WPL Level 5 (Average of Reading, Listening, Speaking & Writing Scores)
Attitude
- Positive Learning Attitude
- Enthusiastic Learner
Experience
- Minimum of 1 year of working experience.
Target Age Group: 21-65 years old
Minimum Software/Hardware Requirement
Software:
You will need the following for this course:
- Python 3 – free
- Visual Studio Code – free
- Google Colab – free, runs in the browser with a Google account
- An AI coding assistant with a free tier, e.g. GitHub Copilot Free in Visual Studio Code
Hardware: Windows PC or Mac laptop
Job Roles
Job Roles
- Computer Vision Engineer
- Machine Learning Engineer
- Robotics Developer
- Augmented Reality Developer
- Video Analytics Specialist
- Multimedia Developer
- Image Processing Engineer
- Visual Effects Artist
- Software Developer (with a focus on visual applications)
- Drone Technology Developer
- Biometrics Systems Engineer
- Autonomous Vehicle Systems Developer
- Medical Imaging Specialist
- CCTV and Surveillance Systems Designer
- Game Developer.
Trainers
Trainers
Dr. Alfred Ang brings both academic depth and shipped products to computer vision. He holds a PhD in Electrical Engineering from NUS, an MSc in Electrical and Electronic Engineering from NTU, a B.Sc (Hons) in Physics from NUS and a Graduate Diploma in Intelligent Robotics Systems from NUS-ISS, and he has worked in the defence, electronics and semiconductor industries, published more than 20 peer-reviewed papers and co-invented more than 20 US patents. Today he is a full-stack AI developer, Agentic AI solution architect and corporate trainer, and the founder of Tertiary Courses, where he serves as Managing Director, CIO, CTO and Chief Instructional Designer of Tertiary Infotech Academy Pte Ltd; he also founded Tertiary Robotics in 2015. His certifications include Microsoft Certified AI Engineer Associate (AI-102) and Data Scientist (DP-100) and AWS Certified AI Practitioner, and he is an IBM certified instructor for the AI Practitioners course. Computer vision appears throughout his GitHub portfolio: scannerapp and its Android counterpart perform edge detection, on-device OCR and image enhancement; passportphotoapp uses on-device background removal and face-aware cropping to official photo sizes; tapcardapp combines live edge detection with Vision OCR to read business cards; and lipsyncdemo animates a portrait into a talking avatar. Several of these are live on the App Store, so he teaches computer vision as something that must work reliably on real images from real cameras, not just in a notebook.
AI Vibe Coding for Computer Vision shows developers, engineers and technical learners how to build vision applications in Python by directing AI coding assistants such as Cursor, GitHub Copilot and Claude. The course begins with an overview of computer vision with deep learning, then moves to basic techniques, where learners use OpenCV to load, resize, filter and transform images and detect edges and contours. They go on to image classification with deep learning models and to object detection, locating and labelling multiple objects in images and video, before combining these skills into complete computer vision systems such as inspection, counting or monitoring applications. Dr. Ang's approach is to let the AI write the code while learners stay in control of the design: describing the problem precisely, checking results visually, measuring accuracy and asking the assistant to explain and fix what goes wrong. He brings practical lessons from his own vision apps, such as why lighting and camera angle matter, how to handle awkward edge cases, and when on-device processing is better for privacy and speed than sending images to the cloud. Each topic ends with a working program, so by the end of the course learners have built a small portfolio of computer vision projects they can extend at work. He also shows learners how to package a model into a simple application that colleagues can actually use. To see his computer vision and AI projects, view his GitHub portfolio at https://github.com/alfredang and connect with him on LinkedIn at https://www.linkedin.com/in/angchewhoe/
Richard Wan is an ACLP-certified lecturer and software consultant specialising in computer vision, with decades of software and hardware development experience across AI and machine learning. He holds an M.Sc. in Electrical Engineering (Computer Vision) from the University of Wisconsin-Madison and has worked extensively with OpenCV, C, C++ and Visual Studio on Windows and Linux, as well as embedded platforms such as Arduino, Raspberry Pi and BeagleBone. He has co-founded multiple high-tech companies, led AI-driven software development in healthcare, defence and manufacturing, and taught deep learning with TensorFlow and PyTorch.
In AI Vibe Coding for Computer Vision, Richard applies this computer vision background to building Python applications with AI coding assistants such as Cursor, GitHub Copilot and Claude. Learners get an overview of computer vision with deep learning, practise basic computer vision techniques, and then build image classification and object detection solutions before bringing them together as complete computer vision systems. His experience helps participants judge whether AI-generated code is sound, not just whether it runs. Through structured, beginner-friendly instruction, learners leave able to create practical applications such as quality inspection, people counting and document scanning.
Tan Woei Ming is an accomplished data scientist and AI engineer with over 15 years of experience in artificial intelligence, machine learning and data-driven innovation. He has led AI initiatives in predictive analytics, automation and process optimisation across the semiconductor and manufacturing industries, where reliable AI must work under real production conditions. He holds a Master's in Intelligent Systems from the National University of Singapore and a First-Class Honours degree in Electrical and Electronic Engineering from NTU. His expertise lies in translating complex AI technologies into practical business applications, enabling organisations to innovate through data insights and intelligent automation.
AI Vibe Coding for Computer Vision applies that engineering background to visual AI. Woei Ming guides learners through an overview of computer vision with deep learning, basic computer vision techniques, image classification, object detection and complete computer vision systems, using AI-assisted coding to speed up development. His intelligent systems training and industrial automation experience help participants understand what the generated code is doing and why a model behaves as it does, rather than simply running it. Learners leave able to prototype working vision applications quickly and to judge which approach suits a given business or operational problem.
Ken Yuen is an ACTA-certified adult educator specialising in STEM education, IoT systems and programming, with Python among the languages he teaches. He has conducted WSQ and SkillsFuture courses in Python, Jetson Nano, Raspberry Pi, Arduino and micro:bit, and in his technical courses he focuses on hands-on experimentation with sensors, microcontrollers and automation systems. He holds a Bachelor of Electrical and Electronics Engineering from Nanyang Technological University and a Diploma in Electronic Engineering from Singapore Polytechnic, and has worked as an Application Development Engineer, Technical Consultant and Project Manager. He is also a certified PMP and an MOE-registered instructor.
In AI Vibe Coding for Computer Vision, Ken brings his Python teaching and hardware background to learners who want to build image and video applications without writing every line themselves. He guides participants as they direct AI coding assistants such as Cursor, GitHub Copilot and Claude through the course topics: an overview of computer vision with deep learning, basic techniques, image classification, object detection and complete computer vision systems. His hands-on, experiment-first style helps learners test what the AI produces, understand why a model behaves as it does and assemble working prototypes for uses such as inspection, counting and monitoring.
Dr Alvin Ang is an ACTA-certified trainer with a long-standing interest in real-world data science. His PhD, Masters and Bachelors degrees are all from NTU, Singapore. He was previously a Principal Consultant (Data Science) and an Assistant Professor, and taught as an adjunct lecturer at SUSS for eight years. Though trained as an operational researcher, he is driven by practical applications more than academic theory, and he owns a startup.
AI Vibe Coding for Computer Vision puts that practical outlook to work on images and video. Learners use AI coding assistants such as Cursor, GitHub Copilot and Claude to build Python applications, beginning with an overview of computer vision with deep learning and basic computer vision techniques, then progressing to image classification, object detection and complete computer vision systems. Dr Ang draws on his data science and teaching background to help learners structure each problem, prepare their data sensibly and evaluate results critically rather than relying on whatever the assistant produces. By the end, participants can describe a vision task in plain English, steer an assistant to implement it, and judge whether the resulting model is good enough for real use.
Review
Customer Reviews (4)
- Excellent Course and Trainer Review by Course Participant/Trainee
-
Course materials and knowledge of trainer is very adequate.1. Do you find the course meet your expectation? 2. Do you find the trainer knowledgeable in this subject? 3. How do you find the training environment
Saw some reviews on initial set up taking half a day and splitting the no. of course days..
Personally feel 1.5 days will be the best duration but I do prefer to keep it to 1 day.
Most of my set up was done prior to the class, if you know you are attending a programming course and bringing your own laptop, the best way to prepare is to look for an IDE, download the latest patches, etc. before the actual course date.
Not professional to pin the blame on others if it is something we ourselves can prevent in the first place. However, it goes the same for the training provider, if the laptop is being provided, then it should be made ready-to-use.
Would recommend this course! The trainer could adapt and structure the learning according to what I shared I would be using it for, and after learning about my level of coding competency. (Posted on 8/22/2023) - will recommend Review by Course Participant/Trainee
-
. (Posted on 8/12/2020)1. Do you find the course meet your expectation? 2. Do you find the trainer knowledgeable in this subject? 3. How do you find the training environment - will recommend Review by Course Participant/Trainee
-
The initial setup took almost half a day. (Posted on 2/25/2020)1. Do you find the course meet your expectation? 2. Do you find the trainer knowledgeable in this subject? 3. How do you find the training environment - Will Recommend Review by Course Participant/Trainee
-
Better split the course to two day.Is quite complicated programming course. Lucky you have a outstanding and professional Lecturer and I am attend alone. Else will be not enough time to complete the entire lesson1. Do you find the course meet your expectation? 2. Do you find the trainer knowledgeable in this subject? 3. How do you find the training environment
I don't mind course fee increase if can split it to two days. Can provide a basic camera module to participant to apply in the course.
(Posted on 8/27/2018)
Write Your Own Review
- Recommended Courses
IBF - AI Assisted Python Programming for Finance
$2,000.00 (GST-exclusive)
$2,180.00
(GST-inclusive)
CASL - Python Text Mining and Analytics: Transforming Text into Insights
$720.00 (GST-exclusive)
$784.80
(GST-inclusive)
