Digital Image Processing and Computer Vision

Course aim

To introduce basic principles of Digital Image Processing techniques and to lay the theoretical foundation of image processing theory for developing applications involving digital image processing.
The course will provide an overview of the theory for restoring images from noisy conditions, reducing the image size for optimizing storage and transmission bandwidth using transform methods and will enhance the student’s knowledge in colour image representation. Pre-processing of digital images for object recognition through image segmentation process in the context of Computer Vision applications will also be introduced. The main aim of the course is to apply the theory in developing models to analyse the digital images and integrate the theory with processing techniques to develop computer vision applications.

Course content

Introduction to Digital Image Processing: Background; What is Digital Image processing?; Digital Image representation; Images as Matrices; Image types; Array Indexing; Few important Standard Arrays; Colour Image Representation;
Intensity transformations: Intensity transformation functions; Histogram processing; Spatial Filtering (Linear & Non- Linear);
Frequency Domain Processing: 2D Discrete Fourier Transform; Filtering in Frequency domain, Sharpening Frequency Domain Filters (High pass Filtering);
Image Restoration: Model of Image Degradation/Restoration process; Noise models;
Image Compression: Background; Coding redundancy (Huffman encoding & Decoding); Transformation methods in Image processing such as applications of Discrete Cosine Transform (DCT). Fast Wavelet Transform; Inverse Wavelet Transform: JPEG;
Image Segmentation: Point, Line and Edge detection; Line detection using Hough Transforms; Region-Based Segmentation; Segmentation using Watershed Transform;
Image Perception: Laminar Architecture of Visual Cortex for image processing and understanding; Adaptive Neural Networks for modelling biological vision.
A Review of Computer Vision applications; Fuzzy-Neural algorithms for computer vision applications;

NOTE: Conceded and Terminating passes will be available to undergraduates taking this course but not to postgraduates.

Textbook(s)

Gonzalez, Woods, and Eddins 2011, Digital Image Processing Using MATLAB, 2, McGraw Hill Education (Asia)

Prerequisite(s)

Corequisite(s)

Nil

Teaching method

Note: These components may or may not be scheduled in every study period. Please refer to the timetable for further details.

Assessment

Assignment on AI applications for modelling biological vision, Practicals (Ongoing laboratory assessment), Test (closed book)

Fees

EFTSL*: 0.125
Commonwealth Supported program (Band 2)
To determine the fee for this course as part of a Commonwealth Supported program, go to:
How to determine your Commonwealth Supported course fee. (Opens new window)

Fee-paying program for domestic and international students
International students and students undertaking this course as part of a postgraduate fee paying program must refer to the relevant program home page to determine the cost for undertaking this course.

Non-award enrolment
Non-award tuition fees are set by the university. To determine the cost of this course, go to:
How to determine the relevant non award tuition fee. (Opens new window)

Not all courses are available on all of the above bases, and students must check to ensure that they are permitted to enrol in a particular course.

* Equivalent Full Time Study Load. Please note: all EFTSL values are published and calculated at ten decimal places. Values are displayed to three decimal places for ease of interpretation.