COMPUTER VISION AND PATTERN RECOGNITION (ONLINE) - 2025/6

Module Overview

The purpose of this module is to provide students with a comprehensive understanding of image application. It aims to equip students with the skills to detect and classify features within an image, represent scenes in varying levels of detail, and apply machine learning and deep learning techniques for advanced image analysis tasks. The module covers a spectrum from foundational image processing methods to sophisticated algorithms for object tracking and 3D reconstruction. Students will also gain hands-on experience with MATLAB to implement concepts learned and explore the intricacies of neural network architectures for image classification processing, scene representation, and analysis through a blend of theoretical knowledge and practical.

Module provider

SOL - Computer Science and Elec Eng

Module Leader

BOBER Miroslaw (CS & EE)

Number of Credits: 15

ECTS Credits: 7.5

Framework: FHEQ Level 7

Module cap (Maximum number of students): N/A

Module Availability

Semester 2

Prerequisites / Co-requisites

None

Module content

This module begins with an introduction to low-level image processing techniques, which include methods for edge detection and the use of simple colour classifiers to identify regions of interest. It then progresses to mid-level scene representation, where it discusses global shape descriptors and local feature descriptors. Following this, the basics of Deep Learning for image analysis are covered, emphasizing neural network (NN) architectures for image classification tasks. These concepts are integrated with machine learning principles, using basic classifiers to delve into supervised classification problems, such as shape and object recognition. Additionally, the module covers unsupervised clustering applications, such as codebook-based image retrieval, which students will investigate further in their coursework assignments.
Dynamic models are introduced in the context of object tracking, accompanied by examples of both classical and contemporary tracking algorithms. The course also provides a brief overview of high-level scene description using statistical shape models. Towards the end, it presents theories of camera geometry and image formation, with a focus on their use in 3D reconstruction.
To reinforce the taught material, students will engage in formative self-guided lab-based exercises using MATLAB. These exercises will not only solidify the students' understanding of traditional image processing techniques but also give them practical experience with the foundational elements of Deep Learning relevant to image analysis.
COMPUTER VISION
Introduction to Computer Vision and its Applications.
Image Processing: Convolution and Linear filters. Edge detection. Image Interpolation.
Pattern classification: Supervised clustering; K-NN; Thresholding and decision boundaries; Eigenmodels and Mahalanobis distance; PCA.
Features and Matching: Image Descriptors (EHD, SIFT). Concept of a feature space. Unsupervised clustering (K-Means). Visual codebooks. Bag of Visual Words framework. Applications to object classification and visual search.
Shape Description: Shape Factors, Image Moments, Fourier descriptors, Chain Code, Hough Transform.
Deep Learning: NN architectures for deep learning – design, training, and evaluation,
Tracking: Templates and cross-correlation. Blob trackers. Kalman filter. Bayes Law. Particle filters.
Markov Processes.
Contour models: Piecewise cubic splines, Active contours; PDMs; ASMs.
Multiview Geometry: Linear Perspective, Homography, RANSAC and Mosaicing. Epipolar Geometry.
Fundamental and Essential Matrix; Estimating scene geometry; Stereo matching and triangulation; Visual Hull.

Assessment pattern

Alternative Assessment

None

Assessment Strategy

The assessment strategy for this module is designed to provide students with the opportunity to demonstrate the following. 
The examination assesses all learning outcomes through use of broad range of questions covering worked calculations and problem solving “scenario” based questions that require recommendation of appropriate algorithms and solutions. All taught material is covered in the examination covering low- mid- and high- level vision so following the captured content and guided-learning plan. The coursework focuses on the design, implementation and evaluation of a Computer Vision system e.g. a visual search system being one of the topics covered in the early lectures. This particularly focuses upon the first 3 learning outcomes, on the selection of appropriate vision and pattern recognition techniques, and their implementation and their evaluation.
Thus, the summative assessment for this module consists of the following: 

• Coursework assignment (20% weighting).


• Examination (80% weighting).

Any deadline given here is indicative. For confirmation of exact date and time, please check the Departmental assessment calendar issued to you.
Formative assessment and feedback:
For the module, students will receive formative assessment/feedback in the following ways:

• Q&A during tutorials.


• By means of unassessed guided-learning problem sheets .


• Via feedback comments on assessed coursework.

Module aims

• To introduce the fundamental concepts of low-level image processing, including edge detection and color classification, to identify regions of interest in images.
• To familiarize students with mid-level scene representation techniques, such as global shape descriptors and local feature descriptors, and their role in understanding image content.
• To provide a foundational understanding of Deep Learning, specifically neural network architectures, and their application in image analysis and classification tasks.
• To explore the integration of machine learning algorithms with image processing for supervised classification problems like shape and object recognition, as well as unsupervised clustering applications like image retrieval.
• To teach dynamic models for object tracking and to present a variety of classical and contemporary tracking algorithms.
• To offer a concise introduction to high-level scene description using statistical models and to discuss the applications of camera geometry and image formation in 3D reconstruction.
• To reinforce theoretical knowledge through practical, self-guided lab exercises using MATLAB, enabling students to implement and experiment with the algorithms discussed in the module.
• To prepare students to apply the acquired knowledge and skills to solve practical problems in computer vision, robotics, artificial intelligence, and other fields that require image analysis competencies.

Learning outcomes

Methods of Teaching / Learning

The learning and teaching strategy is designed to achieve the following aims:
The strategy is to deliver core theory through captured content and guided learning activities and enable the practical application of that theory through self-guided lab activities. The latter also provides an opportunity for formative feedback. 
The coursework exposes students to the full development cycle of a vision system – design, implementation, evaluation and reporting of a computer vision system. Both summative and formative feedback are delivered via the coursework.
The learning and teaching methods include the following:

• Captured content.


• Guided learning activities .


• Tutorials.

Indicated Lecture Hours (which may also include seminars, tutorials, workshops and other contact time) are approximate and may include in-class tests where one or more of these are an assessment on the module. In-class tests are scheduled/organised separately to taught content and will be published on to student personal timetables, where they apply to taken modules, as soon as they are finalised by central administration. This will usually be after the initial publication of the teaching timetable for the relevant semester.

Reading list

https://readinglists.surrey.ac.uk
Upon accessing the reading list, please search for the module using the module code: EEEM078

Other information

We are committed to developing graduates with strengths in Employability, Digital Capabilities, Global and Cultural Capabilities, Sustainability, and Resourcefulness and Resilience. This module is designed to allow students to develop knowledge, skills, and capabilities in the following areas:
Digital capabilities: Digital capabilities and employability are further strengthened by providing a fundamental grounding in computer programming and problem modelling and prototyping in MATLAB, which is commonly used in industry and academia. Students solve technical challenges during the guided-learning and assessed coursework.
Employability: This module will enhance employability skills by developing demanded skills & customer-driven approach to practical problem-solving during guided learning and the coursework assignment. 
Resourcefulness and resilience: These are promoted by encouraging students to reach their full potential via planning and optimal use of resources offered, including the captured content, guided learning, and the challenges in the assignment.

Programmes this module appears in

Please note that the information detailed within this record is accurate at the time of publishing and may be subject to change. This record contains information for the most up to date version of the programme / module for the 2025/6 academic year.