Skip to main content Skip to navigation

Module Catalogue

WM3F7-30 Computer Vision and Data Science

Department
WMG
Level
Undergraduate Level 3
Module leader
Manoj Babu
Credit value
30
Module duration
42 weeks
Assessment
100% coursework
Study locations
  • University of Warwick main campus, Coventry Primary
  • Distance or Online Delivery

Download as PDF

Introductory description

This module provides an introduction to the essential aspects image processing, data science and machine learning. This module will enable apprentices to perform basic image processing tasks, exploratory analysis of data and implement Deep Neural Networks (DNN) to perform a range of Computer Vision and Machine Learning Tasks.

Module web page

Module aims

This module aims to provide the fundamentals of image processing, data science and machine learning.
The module will cover the principles of image formation, sampling and quantization, which will allow apprentices to investigate image-processing techniques. Apprentices will be equipped with the knowledge related to image intensity transformations and spatial filtering.
The module also aims to enable the apprentices to perform critical tasks such as, data collection, extraction, and analysis to provide insights. It will also introduce apprentices to a typical data analysis pipeline together with the necessary programming and theoretical background.

Outline syllabus

This is an indicative module outline only to give an indication of the sort of topics that may be covered. Actual sessions held may differ.

This is an indicative module outline only to give an indication of the sort of topics that may be covered. Actual sessions held may differ.

  1. Digital image fundamentals
  2. Intensity transformation and spatial filtering
  3. Extraction, Transformation and Loading of datasets
  4. Advanced Regression, classification and clustering techniques
  5. Introduction to ANN and CNN architectures.

Learning outcomes

By the end of the module, students should be able to:

  • Obtain, clean and perform exploratory analysis of data [CITP, 2.1.1, 2.2.5, 2.3.2] [AHEP:4, C3]
  • Appraise methods and techniques to analyse large datasets. [CITP. 2.2.5][AHEP:4,C3]
  • Critically analyse how data analysis may exhibit biases and prejudice. [CITP, 2.1.13]
  • Evalaute limits and assumptions of machine learning algorithms [CITP, 2.1.1, 2.1.9][AHEP:4, C1, C17]
  • Design and assess applicabilty of advanced Machine Learning models for a range of computer vision and machine learning tasks [CITP, 2.1.1, 2.1.2, 2.1.9, 2.1.12] [AHEP:4, C1, C17]
  • Assess and apply algorithms for image processing tasks [CITP, 2.1.1, 2.1.9] [AHEP:4, C1, C17]

Indicative reading list

View reading list on Talis Aspire

Subject specific skills

This module contributes to the following Knowledge (K) and Skills (s) in the ST0119 occupational standard:
K13: Principles of data analysis for digital and technology solutions.
K54: How to critically analyse, interpret and evaluate complex information from diverse datasets.
K56: Sources of data such as files, databases, web services, open data, government data, news and social media.
K59: How Data Analytics can be applied to improve an organisation’s processes, operations and outputs.
K60: How data and analysis may exhibit biases and prejudice. How ethics and compliance affect Data Analytics work, and the impact of international regulations. For example, General Data Protection Regulation, Data Protection Act 2018.
S11: Determine and use appropriate data analysis techniques. For example, Text, Statistical, Diagnostic or Predictive Analysis to assess a digital and technology solutions.
S48: Define Data Requirements and perform Data Collection, Data Processing and Data Cleansing.
Apply different types of Data Analysis, as appropriate.
S50: Find, present, communicate and disseminate data analysis outputs effectively and with high impact through creative storytelling, tailoring the message for the audience. Visualise data to tell compelling and actionable narratives by using the best medium for each audience, such as charts, graphs and dashboards.
S51: Identify barriers to effective analysis encountered both by analysts and their stakeholders within data analysis projects.
Apply a range of techniques for analysing quantitative data such as data mining, modelling techniques to identify and predict trends and patterns in data.
S53: Apply exploratory or confirmatory approaches to analysing data. Validate and and test stability of the results.
S54: Extract data from a range of sources. For example, databases, web services, open data.
S55: Analyse in detail large data sets, using a range of industry standard tools and data analysis methods.

Transferable skills

Python programming; Data analysis; Data visualisation.

Study time

Type Required
Lectures 15 sessions of 1 hour (5%)
Tutorials 7 sessions of 1 hour (2%)
Practical classes 8 sessions of 1 hour (3%)
Work-based learning 15 sessions of 1 hour (5%)
Online learning (scheduled sessions) 15 sessions of 1 hour (5%)
Other activity 50 hours (17%)
Private study 70 hours (23%)
Assessment 120 hours (40%)
Total 300 hours

Private study description

  • Explore various open source frameworks for Machine Learning software
  • Exploring various methods for data visualization and exploratory analysis.
Other activity description

Student independent study including time to

  • Practice python programming.

WBL hours are utilsed to explore the workspace/business and identify the tasks where available process data can be used improve efficiency, gain insights or automate tasks. Followed by application of machine learning algorithms to demonstrate them.

Costs

No further costs have been identified for this module.

You must pass all assessment components to pass the module.

Assessment group A
Weighting Study time Eligible for self-certification
Assessment component
In-class test 25% 30 hours No

This test will be a combination of multiple choice and short answer questions delivered via Moodle or QMP to test the understanding of the fundamentals of image processing, data analysis, machine learning algorithms
Reassessment component is the same
Assessment component
Exploratory data analysis project 25% 30 hours Yes (extension)

A programming project where the apprentices submit code and a final report detailing the exploratory data analysis of a chosen dataset.
Reassessment component is the same
Assessment component
Post Module Project 50% 60 hours Yes (extension)

Apprentices will utilise a dataset obtained form work or recommended online sources to further analyse and apply appropriate machine learning algorithms. A summary of the performed analysis and results along with code has to be submitted in the form of report for assessment.
Reassessment component is the same
Feedback on assessment

Feedback given as appropriate to the assessment type:

  • verbal feedback given during seminar/tutorial sessions.
  • written individual feedback on the assignment report and code.
  • Cohort level feedback for in-class test.

Courses

This module is Core for:

  • Year 3 of UWMS-H65B Undergraduate Digital and Technology Solutions (Data Analytics)
  • Year 3 of DWMS-H652 Undergraduate Digital and Technology Solutions (Data Analytics) (Degree Apprenticeship)

This module is Optional for:

  • Year 3 of UWMS-H65E Undergraduate Digital and Technology Solutions (Cyber)
  • Year 3 of DWMS-H655 Undergraduate Digital and Technology Solutions (Cyber) (Degree Apprenticeship)
  • Year 3 of UWMS-H65C Undergraduate Digital and Technology Solutions (Network Engineering)
  • Year 3 of DWMS-H653 Undergraduate Digital and Technology Solutions (Network Engineering) (Degree Apprenticeship)
  • Year 3 of UWMS-H65D Undergraduate Digital and Technology Solutions (Software Engineering)
  • Year 3 of DWMS-H654 Undergraduate Digital and Technology Solutions (Software Engineering) (Degree Apprenticeship)