- This event has passed.
ONLINE COURSE – Machine Vision using Python (MVUP01) This course will be delivered live
3rd February 2025 - 7th February 2025
£480.00
Event Date
Monday, February 3rd, 2025
Course Format
This is a ‘LIVE COURSE’ – the instructor will be delivering lectures and coaching attendees through the accompanying computer practical’s via video link, a good internet connection is essential.
Course Program
TIME ZONE – Ireland local time – however all sessions will be recorded and made available allowing attendees from different time zones to follow.
Please email oliverhooker@prstatistics.com for full details or to discuss how we can accommodate you.
Course Details
Machine vision has produced many helpful image-processing techniques in several fields, such as object detection, classification, and segmentation. Machine vision is an interdisciplinary discipline combining computer vision and machine learning methods, mainly deep learning, to solve vision problems. Common problems, such as classification and localisation, are typical examples that combine these research fields. These techniques have applications in many areas. Deep learning methods are commonly applied for image classification, focusing on deep neural networks and Convolutional Neural Networks (CNNs), including concepts of transfer learning applied to image classification. This course introduces basic concepts of deep learning and machine vision applied to image classification using CNNs. To illustrate these methods, a dataset of medically and forensically important flies is used. Other examples will also be used during the course to illustrate the applications of machine vision in ecology.
By the end of the course, participants should:
- Understand the basic concepts behind the machine vision ecosystem in Python;
- Understand the machine vision pipeline workflow;
- Understand the application of standard Python packages such as OpenCV and Tensorflow;
- Understand the basic concepts behind Deep Neural Networks;
- Understand the basic concepts behind Convolutional Deep Neural Networks;
- Understand basic concepts behind Transfer learning;
- Have the confidence to implement basic Machine vision methods using Python;
- Have the confidence to combine basic computer vision and machine learning methods to perform vision tasks;
Intended Audiences
- Academics and post-graduate students working on projects related to machine vision
- Applied researchers and analysts in public, private or third-sector organisations who need the reproducibility, speed and flexibility of a programming language such as Python for machine vision;
- Ecologists utilise Python to solve vision-related problems and look to update their knowledge in the machine vision area.
Venue
Delivered remotely
Course Information
Time zone – Central Time Zone
Availability – TBC
Duration – 5 days
Contact hours – Approx. 35 hours
ECT’s – Equal to 3 ECT’s
Language – English
Teaching Format
Introductory and Intermediate-level lectures interspersed with hands-on projects. The instructors will provide datasets, but participants are welcome to bring their data. Any code that the instructor produces during these sessions will be uploaded to a publicly available GitHub site after each session.
All sessions will be video recorded and made available to all attendees as soon as possible. If some sessions are not at a convenient time due to different time zones, attendees are encouraged to join as many of the live broadcasts as possible.
At the start of the first day, we will ensure that everyone is comfortable with how Zoom works, and we’ll discuss the procedure for asking questions and raising comments.
Assumed quantitative knowledge
A basic understanding of statistical and mathematical concepts. Also, a basic understanding of supervised learning.
Assumed computer background
Day one will cover the basics of Python for the module. However, some familiarity with any other programming language is welcome
Equipment and software requirements
Although not absolutely necessary, a large monitor and a second screen could improve the learning experience. Participants are also encouraged to keep their webcams active to increase their interaction with the instructor and other students.
Cancellations are accepted up to 28 days before the course start date subject to a 25% cancellation fee. Cancellations later than this may be considered, contact oliverhooker@prstatistics.com. Failure to attend will result in the full cost of the course being charged. In the unfortunate event that a course is cancelled due to unforeseen circumstances a full refund of the course fees will be credited.
COURSE PROGRAMME
Monday 3rd
Day 1: A Short Course in Python Basics (9:30 – 17:30)
This day provides participants with the foundational Python skills required for machine vision tasks. This day is designed for beginners or those needing a refresher in Python programming.
- Section 1 (Python Essentials for Machine Vision): This section focuses on Python syntax, variables, data types, conditionals (`if`, `else`, `elif`), loops (`for`, `while`), and writing reusable code using functions.
- Section 2 (Data Structures and File Handling in Python): Focuses on lists, dictionaries, tuples, sets, and reading/writing files (e.g., CSVs) for data manipulation.
Tuesday 4th
Day 2: Fundamentals of Computer Vision (9:30 – 17:30)
This day focuses on the theoretical foundations of computer vision, detailing the main aspects.
- Section 3 (Introduction to Computer Vision and Image Processing): This section covers the fundamental structure of an image, basic image handling techniques, and an introduction to computer graphics.
- Section 4 (Local Image Descriptors and Feature Mapping): This section explores local image descriptors, such as the Harris Corner Detector, and techniques for image-to-image mapping.
Wednesday 5th
Day 3: Fundamentals of Deep Learning (9:30 – 17:30)
This day focuses on the theoretical foundations of deep learning from Neural Networks to Convolutional Neural Networks (CNNs).
- Section 5 (Neural Networks: From Basics to Backpropagation): Introduces artificial neurons and explains how neural networks learn through backpropagation.
- Section 6 (Convolutional Neural Networks (CNNs) for Image Classification): Provides a detailed explanation of CNN architecture, including convolution layers, pooling layers, and fully connected layers.
Thursday 6th
Day 4: Understanding the Machine Vision Ecosystem in Python (OpenCV & TensorFlow) (9:30 – 17:30)
This day introduces participants to the core libraries used in machine vision tasks. OpenCV is used for image processing, and TensorFlow is used for building deep learning models.
- Section 7 (Building Deep Learning Models with TensorFlow/Keras): Offers a step-by-step guide to building CNN models for image classification using TensorFlow/Keras.
- Section 8 (Image Processing with OpenCV: Filters, Edge Detection & Contours): Covers basic image manipulation techniques using OpenCV, including resizing, cropping, applying filters (blurring/sharpening), edge detection (Canny), and contour detection.
Friday 7th
Day 5: The Machine Vision Pipeline (9:30 – 17:30)
Participants will learn about the end-to-end workflow of a typical machine vision project.
Section 9 (Preprocessing Images for Deep Learning with OpenCV & TensorFlow): This section focuses on preprocessing techniques in OpenCV before feeding images into TensorFlow models for training. An entomological example illustrating the Machine Vision Pipeline will be used.
Section 10 (The Complete Machine Vision Pipeline: From Image Capture to Classification): Covers the end-to-end machine vision workflow, including image capture, enhancement through preprocessing, segmentation, feature extraction, and classification using machine learning classifiers.
Course Instructor
Dr. Gabriel Palma
Gabriel R. Palma obtained a B.Sc. in Biology from the University of São Paulo, Brazil in 2021. He is currently a PhD researcher at the Hamilton Institute at Maynooth University, Ireland, funded by the Science Foundation Ireland’s Centre for Research Training in Foundations of Data Science. His research interests include statistical and mathematical modelling, machine vision, machine learning, and applications to ecology and entomology. His personal webpage can be found here