IMAGE PROCESSING AND DEEP LEARNING - 2017/8
Module code: EEEM063
Electrical and Electronic Engineering
COLLOMOSSE JP Dr (Elec Elec En)
Number of Credits
FHEQ Level 7
Module cap (Maximum number of students)
Overall student workload
Lecture Hours: 33
Laboratory Hours: 15
|Assessment type||Unit of assessment||Weighting|
|Examination||2 HOUR CLOSED-BOOK WRITTEN EXAMINATION||75%|
|Coursework||MATLAB-BASED EXERCISE AND REPORT||10%|
|Coursework||MATLAB-BASED EXERCISE AND REPORT||15%|
Not applicable: students failing a unit of assessment resit the assessment in its original format.
Prerequisites / Co-requisites
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.
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.
|Be able to demonstrate an understanding of a number of principles in image processing and computer vision and the theory behind those||K|
|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|
|Be able to formulate problems in Image Processing and Computer Vision in a Mathematical way and solve them to achieve optimality in performance||KCT|
|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|
C - Cognitive/analytical
K - Subject knowledge
T - Transferable skills
P - Professional/Practical skills
Indicative content includes the following.
 Introduction. Geometric Image Transformations. Homogeneous Coordinates.
[2-3] Image Warping. Interpolation. Image Quality metrics.
[4-6] Image Filtering. Aliasing. Blurring, Sharping and Edge Detection. Gaussian kernel and its derivatives. Scale-space pyramids. Thresholding.
[7-9] Colour Images. Human Vision System - Physiology of the human vision system. Tri-stimulus experiment. Colour spaces. High Dynamic Range and tone mapping. Histogram modification and colour transfer.
[10-12] Image Completion and Enhancement. Poisson Image Editing. Patch based in-painting. Image Analogies. Super-resolution.
[13-15] Object Recognition. Sliding window detectors. Viola Jones. Gradient domain features. SVM varieties. Vector quantization. CNNs.
[16-18] Video Processing and Recognition. Optical Flow. Activity Recognition. Motion segmentation. Anomaly detection.
[19-21] Visual Localisation. Camera model and Calibration. Stereo Vision. Monte Carlo localization. Occupancy Grids.
[22-24] Active Vision. Particle Filter and SLAM. Large-scale mapping and loop closure.
[25-27] 3D Reconstruction from images. Shape from Shading. Pose estimation from consumer depth cameras. Dense scene reconstruction.
[28-30] 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: 10 weeks, 10x 3h
Labs: Matlab exercises to consolidate the lecture material, 2 weeks, 3 x 2h
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 10% (weeks 2-4)
· Matlab exercise and report 15% (weeks 6-9)
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 writing a short Matlab program to a provided specification, and writing a brief (max 10 page) report on the results of the program. The first assignment will focus on image processing through a worked example of image warping and the relative advantages of different interpolation and sampling schemes. The second assignment will focus on computer vision through a worked example of object recognition, with a report summarizing the relative advantages of different descriptors and classifier configurations. The lab sesisons running in weeks 2-4 and 7-9 will support the two pieces of coursework respectively. 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 for IMAGE PROCESSING AND DEEP LEARNING : http://aspire.surrey.ac.uk/modules/eeem063
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 2017/8 academic year.