Basic Image Processing with OpenCV and Python Workshop is a hands-on course in OpenCV 5 and Python, from enhancing images and finding edges and contours to measure and count objects, to tracking objects in video and detecting faces and objects with AI models. It suits Python developers, engineers and anyone who wants to build computer vision systems.
Inspecting parts, counting products, reading values from images and detecting people or vehicles from a camera all start with sound image processing. OpenCV is the leading open source library for computer vision and works with Python straight away, and OpenCV 5 has reworked its DNN module to support far more of the ONNX format, so modern AI models and classic image processing techniques can now sit in the same program.
This workshop takes learners through OpenCV 5 with Python, from the basics of digital images, transformations, thresholding, filters and histograms to finding contours to measure and count objects, matching features, and detecting motion and tracking objects in video. It then moves into deep learning with face detection and recognition, object detection with YOLO26 and acceleration with OpenVINO, and closes with a project that builds a vision system working with a real camera. (3 days, 6 hours per day, 18 hours in total, Beginner level.)
Course Details
This course is the 2026 edition of Basic Image with OpenCV and Python Workshop, updated for OpenCV 5. It runs for 3 days, 6 hours per day (18 hours in total, 09:00-16:00), as a workshop in which learners write code against real images, video and cameras in every topic. Beginner level, for learners with basic Python. Day one covers image processing fundamentals, day two covers measuring, counting and tracking objects, and day three covers deep learning for images with ONNX models, face detection and recognition, YOLO26 and OpenVINO, with a capstone that builds a vision system from a real camera. Every lab runs on an ordinary laptop without a GPU. Learners take home a lab guide, source code and sample images and video for every lab.
Section 1: Lab: Getting Started with OpenCV 5 and Python
Section 2: Lab: Drawing and Geometric Transformations
Section 3: Image Arithmetic and Thresholding
Section 4: Filters, Morphology and Edge Detection
Section 5: Lab: Histograms and Image Enhancement
Section 6: Contours and Shape Analysis
Section 7: Lab: Measuring and Counting Parts
Section 8: Feature Detection and Matching
Section 9: Lab: Video and Motion Detection
Section 10: Lab: Object Tracking in Video
Section 11: The DNN Module in OpenCV 5
Section 12: Lab: Face Detection and Recognition
Section 13: Object Detection with YOLO26
Section 14: Lab: Speeding Up with OpenVINO
Section 15: Workshop: A Vision System from a Real Camera
No public rounds are open right now. Join the waiting list and we will contact you first when the next round opens, or ask us on LINE. Or call 02-570-8449 or 088-807-9770
Image processing transforms or adjusts images, for example reducing noise, adjusting contrast, finding edges or separating objects from the background, and the result is usually still an image. Computer vision makes the computer understand what is in the image, such as counting parts, measuring sizes, recognising faces or detecting objects, and it usually relies on image processing to prepare the image first. This course starts with image processing and builds up to computer vision and AI models.
Convert the image to grayscale, reduce noise with a Gaussian blur, then separate objects from the background with a threshold or find edges with Canny. Use morphology to close small gaps, then call findContours to get a list of contours, one per object. From each contour you can calculate area, perimeter and bounding boxes to measure or count objects. For real-world units, compare against a reference object of known size.
OpenVINO is Intel's open source toolkit for optimising and running AI models faster on CPUs and integrated GPUs, without a separate graphics card. In the course, OpenCV prepares the images and displays the results, while models such as YOLO26 are converted to OpenVINO IR and run with OpenVINO Runtime. You also try shrinking models to FP16 or INT8 and compare FPS on your own laptop.
It suits anyone building computer vision systems that read, measure or count objects, production engineers and technicians, Python developers, and students who want a foundation before deep learning. You should be able to write basic Python and install packages with pip; familiarity with NumPy helps. Please bring a laptop with 8 GB of RAM or more and a webcam. No GPU is needed.
You will be able to process images and video fluently with OpenCV 5, separate objects by threshold and colour, measure and count parts from contours, match features between images, detect motion and track objects in video, run ONNX models to detect faces and objects, and speed them up with OpenVINO. You also take home prototype code for a vision system that works with a real camera.
Yes. IT Genius Institute runs in-house training for organisations. Workshop examples and problems can be adapted to your team's work, such as checking part sizes on a production line, counting products or analysing CCTV video, and the emphasis can lean towards classic image processing or AI models as needed. Contact the institute to request a quotation.
Articles are published in Thai.
Internet of Things work is not only about programming small boards. It also needs software on a computer, Raspberry Pi or gateway that receives sensor data, transforms it, stores it in a database and passes it on to other systems. Python is the most popular…
Blazor lets C# developers build interactive web pages using the same language on the front end and the back end, and Blazor WebAssembly runs .NET code directly in the browser. Paired with MongoDB, which stores flexible documents, it makes web applications…
Rust delivers performance on a par with C and C++ while preventing memory errors at compile time, without a garbage collector. That is why it is increasingly used for systems work, command-line tools and backends that need both speed and stability. Beginners,…
