Module Database Search



MODULE DESCRIPTOR
Module Title
Computer Vision
Reference CM4709 Version 1
Created April 2022 SCQF Level SCQF 10
Approved June 2022 SCQF Points 30
Amended ECTS Points 15

Aims of Module
To enable students to develop computational solutions to understand the content of images and video in a way similar to human perception.

Learning Outcomes for Module
On completion of this module, students are expected to be able to:
1 Critically analyse a range of image processing and image manipulation techniques.
2 Critically evaluate a range of image features extraction and features representation methods.
3 Critically analyse different machine learning and deep learning methods for image classification and object detection and recognition tasks.
4 Create an end-to-end intelligent computer vision solution by applying underlying concepts and theories of modern computer vision.

Indicative Module Content
This module will cover image and video analysis, including image processing methods, classification, object recognition and detection, and object tracking. Core image processing tasks such as image enhancement, sampling, noise removal, filtering and morphological operations. Modern computer vision methods such as Convolutional Neural Networks, deep learning methods for handling images and videos. Object Detection, Localisation and Recognition. Object tracking and motion estimation. Deploying computer-vision solutions for real world problems. Working with relevant tools and technologies such as Python, OpenCV, and Tensorflow.

Module Delivery
The module is delivered in Blended Learning mode using structured online learning materials/activities and directed study, facilitated by regular online tutor support. Workplace Mentor support and work-based learning activities will allow students to contextualise this learning to their own workplace. Face-to-face engagement occurs through annual induction sessions, employer work-site visits, and modular on-campus workshops.

Indicative Student Workload Full Time Part Time
Contact Hours 30 N/A
Non-Contact Hours 30 N/A
Placement/Work-Based Learning Experience [Notional] Hours 240 N/A
TOTAL 300 N/A
Actual Placement hours for professional, statutory or regulatory body 240  

ASSESSMENT PLAN
If a major/minor model is used and box is ticked, % weightings below are indicative only.
Component 1
Type: Coursework Weighting: 100% Outcomes Assessed: 1, 2, 3, 4
Description: A report based on applying computer vision techniques to a case study from the public domain.

MODULE PERFORMANCE DESCRIPTOR
Explanatory Text
The calculation of the overall grade for this module is based on 100% weighing of C1. An overall minimum grade D is required to pass the module.
Module Grade Minimum Requirements to achieve Module Grade:
A The student needs to achieve an A in C1
B The student needs to achieve a B in C1
C The student needs to achieve a C in C1
D The student needs to achieve a D in C1
E The student needs to achieve an E in C1
F The student needs to achieve an F in C1
NS Non-submission of work by published deadline or non-attendance for examination

Module Requirements
Prerequisites for Module None.
Corequisites for module None.
Precluded Modules None.

INDICATIVE BIBLIOGRAPHY
1 J Howse and J Minichino, 2020, “Learning OpenCV 4 Computer Vision with Python 3: Get to grips with tools, techniques, and algorithms for computer vision and machine learning”, 3rd Edition.
2 Krishnendu Kar, 2020, “Mastering Computer Vision with TensorFlow 2.x: Build Advanced Computer Vision Applications Using Machine Learning and Deep Learning Techniques.
3 Aurelien Geron 2019, Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems.

Robert Gordon University, Garthdee House, Aberdeen, AB10 7QB, Scotland, UK: a Scottish charity, registration No. SC013781