IMAGE PROCESSING AND DEEP LEARNING - 2018/9

Module code: EEEM063

Module provider

Electrical and Electronic Engineering

Module Leader

COLLOMOSSE JP Prof (Elec Elec En)

Number of Credits

15

ECTS Credits

7.5

Framework

FHEQ Level 7

JACs code

I113

Module cap (Maximum number of students)

N/A

Module Availability

Semester 2

Overall student workload

Independent Study Hours: 117

Lecture Hours: 22

Laboratory Hours: 11

Assessment pattern

Assessment type Unit of assessment Weighting
Examination 2 HOUR CLOSED-BOOK WRITTEN EXAMINATION 75
Coursework MATLAB-BASED EXERCISE AND REPORT 25

Alternative Assessment

Not applicable: students failing a unit of assessment resit the assessment in its original format.

Prerequisites / Co-requisites

None.

Module overview

Module purpose:  This course offers an introduction to image processing and computer vision for those interested in the science and technology of machine vision. It provides background and the theory for building artificial systems that manipulate videos and images and alter or analyse their information content. This is done by various computer algorithms that are discussed, implemented and demonstrated.

Module aims

The aim of this module is to offer an in depth course on the principles of Image Processing and Computer Vision which form the foundation for a variety of disciplines like Robotics, Machine Vision, Remote Sensing, Surveillance, Medical Imaging, Multimedia Technologies etc. In particular the course focuses upon Deep Learning - a form of AI/Machine Learning that has emerged in recent years with broad applicability across these domains.

Learning outcomes

Attributes Developed
1 Be able to demonstrate an understanding of a number of principles in image processing and computer vision and the theory behind those K
2 Be able to choose an appropriate method to an image processing or computer vision problem at hand and predict the outcome of the applied processing KCP
3 Be able to formulate problems in Image Processing and Computer VisionĀ  in a Mathematical way and solve them to achieve optimality in performance KCT
4 Be able to analyse some non-trivial problems in image processing and computer vision, understand the concepts behind them and come up with possible algorithmic solutions. CP

Attributes Developed

C - Cognitive/analytical

K - Subject knowledge

T - Transferable skills

P - Professional/Practical skills

Module content

Indicative content includes the following. 

[1-2] Introduction. Image Representation and Colour. Geometric Image Transformations.  Homogeneous Coordinates.
[3-4] Image Warping.  Interpolation.  Image Quality metrics.
[5-7] Image Filtering.  Aliasing.  Blurring, Sharping and Edge Detection.  Gaussian kernel and its derivatives.  Scale-space pyramids.  Thresholding.
[8-10] Image Completion and Enhancement.  Brightness and Contrast.  Poisson Image Editing. Patch based in-painting.  Super-resolution.
[11-12] Classical object recognition.  Interest points, Gradient domain features and Bag of Words.
[13-15] Convolutional Neural Networks (CNNs).  Siamese Networks. CNN Interpretatability.
[16-18] Fully convolutional networks. Up-convolution. Optical flow.  FCNs for Stylization.  Segmentation.
[19-20] Genereative Adversarial Networks (GANs).  Image transformation networks.  Super-resolution.
[21-22] Revision lectures

Methods of Teaching / Learning

The learning and teaching strategy is designed to achieve the following aims.


To introduce image processing and computer vision to promote deep understanding of the engineering methodologies for design and implementation of software algorithms. The topics include: algebraic manipulation;  probability & statistical analysis;  discrete probability;  Fourier analysis;  vector algebra;  differential & integral calculus.
To introduces engineering principles for software design in signal processing, which involves integration of software components related to verification and validation.
Students learn to identify, classify and describe the performance of software systems and components through the use of analytical methods and modelling techniques. These allow them to employ performance trade-offs and the use of appropriate metrics, to predict and evaluate performance of computer vision algorithms.
Students learn skills of applying quantitative methods, mathematical and computer-based models, and use computer software (Matlab) to solve image-processing problems. Skills involve identifying and analyse problems in images, and develop software solutions to remove problems, for example noise.
Students learn basic programming skills and understanding of software tools, development environments, libraries and reusable components such as matlab or open-CV libraries. They use these to perform filtering, image geometry, and other computer vision tasks such as matching and clustering.


 

Learning and teaching methods include the following.


Lectures: 11 weeks, 11x 2h
Labs: Matlab exercises to consolidate the lecture material, 11 x 1h


 

Assessment Strategy

The assessment strategy for this module is designed to provide students with the opportunity to demonstrate the following.

Problem Classes, assignments, examination:

Knowledge of image processing and computer vision, understanding of the engineering methodologies for design and implementation of software algorithms.

Knowledge of state-of-the art solutions to image processing and computer vision problems, their limitations and requirements for better solutions.

Skills of identifying, classifying and describing the performance of software systems and components through the use of analytical methods and modelling techniques.

Laboratory based assessment: Practical knowledge of designing and assessment of the performance of image processing and computer vision algorithms, such as filtering, clustering, motion estimation, matching, recognition, image enhancement. Assessed by laboratory exercises.

Knowledge of engineering principles for software design in signal processing. This involves integration of software components related to verification and validation.

Skills of applying quantitative methods, mathematical and computer-based models, and use computer software (Matlab) to solve image-processing problems.

Skills of identifying and analyse problems in images, and develop software solutions to remove problems, for example noise. Assessed by laboratory exercises.

Programming skills and understanding of software tools, development environments, libraries and reusable components such as matlab or open-CV libraries. They use these to perform filtering, image geometry, and other computer vision tasks such as matching and clustering.
 

Thus, the summative assessment for this module consists of the following.

· Examination 75%

· Matlab exercise and report 25% (weeks 5-10)

The examination consists of 2h closed-book written examination. There are 4 questions each from different area of the course. Each question consists of several subquestions testing knowledge, analytical, and design skills.

The coursework assessments consists of using the Caffe framework (e.g. via DIGITS) to perform an experiment e.g. image recognition, with a report summarizing theoutcomes. The purpose of the coursework is for students to practically apply the theoretical knowledge gained from the lectures on a topic from each of the core themes of this module: image processing, and computer vision.

Formative assessment and feedback

For the module, students will receive formative assessment/feedback in the following ways.

· During lectures, by question and answer sessions

· During tutorials/tutorial classes

· During supervised computer laboratory sessions

 

 

 

 

Reading list

Reading list for IMAGE PROCESSING AND DEEP LEARNING : http://aspire.surrey.ac.uk/modules/eeem063

Programmes this module appears in

Programme Semester Classification Qualifying conditions
Computer and Internet Engineering MEng 2 Optional A weighted aggregate mark of 50% is required to pass the module
Electronic Engineering with Computer Systems MEng 2 Compulsory A weighted aggregate mark of 50% is required to pass the module
Electronic Engineering MEng 2 Optional A weighted aggregate mark of 50% is required to pass the module
Medical Imaging MSc 2 Compulsory A weighted aggregate mark of 50% is required to pass the module
Mobile Media Communications MSc 2 Optional A weighted aggregate mark of 50% is required to pass the module
Electronic Engineering MSc 2 Optional A weighted aggregate mark of 50% is required to pass the module
Computer Vision, Robotics and Machine Learning MSc 2 Compulsory A weighted aggregate mark of 50% is required to pass the module
Electronic Engineering with Communications MEng 2 Optional A weighted aggregate mark of 50% is required to pass the module
Electronic Engineering with Audio-Visual Systems MEng 2 Optional A weighted aggregate mark of 50% is required to pass the module

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 2018/9 academic year.