Deep Learning for Applied Computer Vision (Online)


Designing computer vision applications in healthcare, robotics, manufacturing, retail, automotive, and security.

Deep Learning for Applied Computer Vision is a brand new, online course which is designed for practitioners already applying or considering computer vision techniques.

It is an industry-led professional development course rather than a purely academic course.

This course will help you learn more about, and how to implement, computer vision in:

  • Healthcare
  • Robotics
  • Manufacturing
  • Retail
  • Automotive
  • Security

Level and Demands/Intended Audience

While a knowledge of coding would be advantageous, it is not essential. This course course is accessible for those who may, for example, be domain experts who may not have (much) hands-on coding.

The course is suited to industry practitioners who want to implement computer vision solutions in their domains.

This course would be particularly beneficial to those who are developers, designers, or industry experts with domain knowledge in the application areas (Healthcare, Robotics, Manufacturing, Retail, Automotive, and Security).

Most of this course (about two-thirds of the time) will be spent on the computer vision fundamentals, with the other third dedicated to looking at case studies.

The computer vision case studies provided to each group are organized by industry verticals (Healthcare, Robotics, Manufacturing, Retail, Automotive, and Security).

By working in a group of your peers on a case study, and mentored by industry and academic experts, you will learn about problems in your industry that can be addressed with computer vision.

This ‘hands-on’ approach also allows you to learn computer applications even if you are domain expert with relatively less knowledge of coding.

Programme details

Led by Dr. Lars Kunze (Oxford Robotics Institute – University of Oxford) and Ajit Jaokar (Course Director – Artificial Intelligence - Cloud and Edge Implementations at the University of Oxford)

Computer vision fundamentals

Introduction to computer vision

History and evolution of computer vision

Image fundamentals

  • Image Fundamentals
  • Image Classification
  • Basics Datasets

Computer vision components and functions

  • Object classification
  • Object and instance segmentation
  • Pose estimation
  • Video analysis
  • Instance tracking
  • Action recognition
  • Motion estimation
  • Scene reconstruction
  • Deep Learning approaches for computer vision like YOLO (You Only Look Once)

Introduction to Object Detection

  • Object detection scenarios
  • R-CNN Models
  • YOLO Models 

Introduction to TensorFlow and Keras

  • Python machine learning libraries
  • The flow of a TensorFlow and Keras program
  • TensorFlow for Computer Vision

Your first image classifier

  • Understanding the image classification scenario

Machine learning and Deep Learning

  • Neural network fundamentals
  • Introduction to convolutional neural networks

Understanding CNN architectures

  • VGG GoogLeNet and the inception module
  • ResNet
  • ImageNet GANs
  • Leveraging transfer learning

Improving the performance of the model

In this module, you will be taken through the various strategies to improve the performance of the baseline model:

  • Understanding model performance
  • Parameter tuning, normalisation, optimisers, regularisation
  • Training on complex and scarce datasets
  • How to deal with data scarcity
  • Augmenting datasets
  • Video and recurrent neural networks

Implementing computer vision in the cloud and edge

This section of the course will take you through the various techniques to implement computer vision in the cloud, and on edge devices

Computer vision Applications

In this session, we explore how deep learning methods can be applied apply to real-world problems.


  • Diagnostics (radiology, etc.)
  • Monitoring elderly and vulnerable patients


  • Mobile robots in open-ended environments (Sensors, ImageNet, CNNs for object detection)
  • Novelty detection in unknown environments (Space, Industrial settings) [Variational Autoencoders— outlook to unsupervised learning]

Manufacturing and Supply Chain

  • Inspection
  • Event detection (for example, on an assembly line)


  • Food inspection
  • Fashion Industry (dresses based on customer body type and preference)


  • Intelligent vehicles
  • Scene understanding (Object detection, Semantic Segmentation, Data Augmentation) [U-NET, GANs]


  • Proof of identity
  • Biometrics
  • Security at ATMs etc
  • Emotion detection


The course will close with each group presenting the case studies that they have been working on with their mentors, before the wrap up and course summary.

Course Delivery

This course will run over six live online sessions on Tuesdays, Wednesdays and Thursdays.

Session dates: Tues 13, Weds 14, Thurs 15, Tues 20, Weds 21 and Thurs 22 April 2021

Sessions will be 15:00 to 18:30 UK time (with a half-hour break) and delivered online via Microsoft Teams.

A world clock, and time zone converter can be found here:

No attendance at Oxford is required and you do not need to purchase any software.


Participants who attend the full course will receive a University of Oxford electronic certificate of attendance. 

The certificate will show your name, the course title and the dates of the course you attended.

You will be required to attend all of the live sessions on the course in order to be considered for an attendance certificate. 


Description Costs
Course fee £995.00


All courses are VAT exempt.

Register immediately online 

Click the “book now” button on this webpage. Payment by credit or debit card is required.

Request an invoice

If you require an invoice for your company or personal records, please complete an online application form. The Course Administrator will then email you an invoice. Payment is accepted online, by credit/debit card, or by bank transfer. Please do not send card or bank details via email.


Dr Lars Kunze

Course Director

Lars Kunze is a Departmental Lecturer in Robotics in the Oxford Robotics Institute (ORI) and the Department of Engineering Science at the University of Oxford. At ORI, he leads the Cognitive Robotics Group (CRG).

Lars is also a Stipendiary Lecturer in Computer Science at Christ Church, a Programme Fellow of the Assuring Autonomy International Programme (AAIP), and an Editor of the German Journal of Artificial Intelligence (KI Journal, Springer).

His areas of expertise lie in the fields of robotics and artificial intelligence (AI). His goal is to enable robots to understand their surroundings, to act autonomously, and to explain their own behaviour in meaningful human terms. To this end, his research concerns the design and development of fundamental AI techniques for autonomous robot systems. He focusses on the combination of knowledge representation, reasoning, machine learning, and robot perception; motivated by applications in complex, real-world environments.


Lars studied Cognitive Science (BSc, 2006) and Computer Science (MSc, 2008) at the University of Osnabrück, Germany, and partly at the University of Edinburgh, UK.


He received his PhD (Dr. rer. nat.) from the Technical University of Munich, Germany, in 2014. During his PhD, Lars worked on methods for naive physics and common sense reasoning in the context of everyday robot manipulation. He contributed to several national, European and international projects including RoboHow, RoboEarth, and the PR2 Beta program.


In May 2013, Lars was appointed as a Research Fellow in the Intelligent Robotics Lab at the School of Computer Science at Birmingham University.  Here he worked on qualitative spatio-temporal models for perception planning and knowledge-enabled perception, contributing to the European research projects STRANDS and ALOOF.


He was a visiting researcher in the JSK Lab at the University of Tokyo, Japan (Summer 2011) and the Human-Robot Interaction Laboratory at Tufts University, US (Spring 2015).

Ajit Jaokar

Course Director

Based in London, Ajit's work work spans research, entrepreneurship and academia relating to artificial intelligence (AI) and the internet of things (IoT). 

He is the course director of the course: Artificial Intelligence: Cloud and Edge Implementations. Besides this, he also conducts the University of Oxford courses: Developing AI Applications and Computer Vision.

Ajit works as a data scientist through his company feynlabs - focusing on building innovative early stage AI prototypes for domains such as cybersecurity, robotics and healthcare.

Besides the University of Oxford, Ajit has also conducted AI courses in the London School of Economics (LSE), Universidad Politécnica de Madrid (UPM) and as part of the The Future Society at the Harvard Kennedy School of Government.

He is also currently working on a book to teach AI using mathematical foundations at high school level. 

Ajit was listed in the top 30 influencers for IoT for 2017 along with Amazon, Bosch, Cisco, Forrester and Gartner by the German insurance company Munich Re.

Ajit publishes extensively on KDnuggets and Data Science Central.

He was recently included in top 16 influencers (Data Science Central), Top 100 blogs (KDnuggets), Top 50 (IoT central), and 19th among the top 50 twitter IoT influencers (IoT Institute). 

His PhD research is based on AI and Affective Computing (how AI interprets emotion).

Ms Ayşe Mutlu


Ayşe Mutlu is a data scientist working on Azure AI and devops technologies. Based in London, Ayşe’s work involves building and deploying Machine Learning and Deep Learning models using the Microsoft Azure framework (Azure DevOps and Azure Pipelines).

She enjoys coding in Python and contributing to Open Source Initiatives in Python.

Bojan Komazec


Bojan Komazec has been working in IT industry for over 15 years. He currently holds the position of Senior Software Engineer in Avast Software where he develops various security and privacy products.

Bojan's interests span from code craftsmanship and cyber security to Artificial Intelligence and Internet of Things. He is an active blogger and speaker at several IT Meetup groups where he enjoys sharing experience and knowledge.

Bojan studied Electrical Engineering and Telecommunications and in 2004 received master's degree from University of Novi Sad, Serbia.

Marina Fernandez


Marina is a CTRM Analyst Developer at Anglo American Plc. She has over 15 years experience in  Software Engineering, Business Analysis,  Agile, project management and full software life cycle in a variety of business domains including Commodity trading and Finance, Machine Learning and AI, e-commerce, e-learning, web-development.

Marina holds an MSc in Software Engineering from University of Oxford and Applied Mathematics degree from Lomonosov Moscow State University. 

In February 2020, Marina completed the course "Data science for internet of things" from the University of Oxford.

Anjali Jain


Anjali is a Digital Solutions Architect at Metrobank, where she helps to deliver advanced technology driven business solutions around diverse themes of Internet Banking, Mobile App, Business banking, and Open banking/PSD2, using agile methodology.

She has over 16 years of IT experience and worked across Banking, Telecom and logistics domains, from inception to the delivery of complex projects.

Anjali is passionate about AI and Machine learning and completed the course "Data science for internet of things" in February 2019 from the University of Oxford.


If you would like to discuss your application or any part of the application process before applying, please click Contact Us at the top of this page.

IT requirements

To participate you must be familiar with using a computer for purposes such as sending email and searching the Internet. You will also need regular access to the Internet and a computer meeting our recommended minimum computer specification.
It is advised to use headphones with working speakers and microphone.