| Effective Term: | 2024/05 |
| Institute / School : | Institute of Innovation, Science & Sustainability |
| Unit Title: | Digital Imaging and Artificial Intelligence |
| Unit ID: | ENGIN3405 |
| Credit Points: | 15.00 |
| Prerequisite(s): | (MATHS3001 or MATHS3040) |
| Co-requisite(s): | Nil |
| Exclusion(s): | (ENMTX3030) |
| ASCED: | 030101 |
| Other Change: | |
| Brief description of the Unit |
The course introduces students to the advanced level knowledge and understanding of digital imaging and artificial intelligence. The students will learn about the historical development of artificial intelligence and image processing technologies and appreciate their use in current industrial environments. Students will further learn about the diversity of artificial intelligence, image processing and their applications. Through such learning, students will gain practical skills in developing various algorithms and building software based models to be implemented in physical mechatronic systems. |
| Grade Scheme: | Graded (HD, D, C, P, MF, F, XF) |
| Work Experience Indicator: |
| No work experience |
| Placement Component: | |
| Supplementary Assessment:Yes |
| Where supplementary assessment is available a student must have failed overall in the Unit but gained a final mark of 45 per cent or above, has completed all major assessment tasks (including all sub-components where a task has multiple parts) as specified in the Unit Description and is not eligible for any other form of supplementary assessment |
| Course Level: |
| Level of Unit in Course | AQF Level(s) of Course | | 5 | 6 | 7 | 8 | 9 | 10 | | Introductory | | | | | | | | Intermediate | | | | | | | | Advanced | | |  | | | |
|
| Learning Outcomes: |
| Knowledge: |
| K1. | Demonstrate understanding of image processing, image representation, image segmentation, feature extraction and low-level image analysis techniques. |
|
| K2. | Demonstrate understanding of spatial and frequency filtering. |
|
| K3. | Interpret and analyse image analysis algorithms in edge and shape detection, colour based segmentation and image thresholding. |
|
| K4. | Demonstrate understanding of pattern recognition and classification process. |
|
| K5. | Explain and outline the advanced concepts and historical development of artificial intelligence. |
|
| K6. | Interpret and discriminate the development of various optimization and machine learning algorithms / techniques. |
|
| K7. | Demonstrate advanced understanding of expert systems and neural networks. |
|
| Skills: |
| S1. | Test and critically analyse results from the performed image analysis. |
|
| S2. | Perform spatial and frequency filtering and feature extraction. |
|
| S3. | Develop and analyse image analysis algorithms. |
|
| S4. | Perform classification and pattern recognition using artificial intelligence and suitable methodologies. |
|
| S5. | Evaluate optimization / network learning algorithms. |
|
| S6. | Formulate and appraise fuzzy rules. |
|
| Application of knowledge and skills: |
| A1. | Apply digital imaging and artificial intelligence techniques in areas of robot vision, condition monitoring, quality control, environmental sensing and interaction, object recognition and classification |
|
| A2. | Design, develop and optimize intelligent models based on artificial intelligence methodologies. |
|
| A3. | Develop advanced learning algorithms for a neural network model to achieve the required design objectives. |
|
| A4. | Implement the knowledge and skills gained through this subject in designing and developing intelligent mechatronics product / system. |
|
| Unit Content: |
•Introduction to digital imaging and image representation, addition and subtraction of images, spatial and frequency filtering.
•Image analysis algorithm with methods involving feature extraction, image segmentation, edge detection, object counting and measurement and other low-level image analysis techniques.
•Pattern recognition and classification techniques.
•Artificial intelligence, reasoning, search and different machine learning and optimization algorithm / techniques.
•Introduction to artificial neural network, classifier, classification errors, perceptron update rule, perceptron convergence, generalisation, regularisation, regression, boosting, Markov models and hidden Markov models.
•Bayesian networks, radial bias networks, probabilistic neural networks, generalised neural networks, self-organising and learning vector quantisation networks.
•Introduction to fuzzy logic, fuzzy set and fuzzy logic expert systems.
•Use of artificial intelligence techniques in classification and pattern recognition. |
| Graduate Attributes: |
| | Learning Outcomes Assessed | Assessment Tasks | Assessment Type | Weighting | | 1. | S1-S6, A1-A4 | Experimental work and / or projects to verify students ability to apply knowledge and skills acquired in the course | Reports, demonstrations | 10 - 30% | | 2. | K1-K7, S1-S6 | Relevant tasks and problems to enforce understanding of the students and help in gradual development of knowledge and skills throughout the course | Assignments, quizzes | 10 - 30% | | 3. | K1-K7 | Questions and problems related to the course contents | Exams / Tests | 40 - 60% |
|