| CODE | ICS3129 | |||||||||
| TITLE | Content Based Image Retrieval and Categorization | |||||||||
| UM LEVEL | 03 - Years 2, 3, 4 in Modular Undergraduate Course | |||||||||
| MQF LEVEL | Not Applicable | |||||||||
| ECTS CREDITS | 5 | |||||||||
| DEPARTMENT | Artificial Intelligence | |||||||||
| DESCRIPTION | This study-unit is about the fundamentals of how to search for images based on their content, similar to Google Image search. We will study various filtering and keypoint detection methods together with the bag of visual words approach. The study-unit will be useful for students interested in image analytics and artificial vision related to areas such as object recognition, visual quality inspection, image databases, multimedia management, animation, GIS, computer graphics, medical imaging, remote sensing and robotics. Hands on experience with Matlab and/or Python will be gained by the implementation of several important image analysis techniques, which may be applied in different applications. Specific topics include, but are not limited to: • Linear Filtering; • Keyoint detection based on Difference-of-Gaussians scale-space and Harris corner detector; • Keypoint description with SIFT, SURF, LBP and others; • Bag of Visual Words; • Feature Selection and Reduction techniques; • Beyond Bag of Words: Spatial Pyramid and VLAD (Vector of Locally Aggregated Descriptors); • Classification. Study-Unit Aims: • Introduce students to a popular and effective paradigm of content-based image retrieval that is widely used in the ever-increasing computer vision applications; • Expose students to how systems, such as Google Image Search, are implemented; • Provide hands-on experience to students with popular tools, such as Matlab and Python for image processing.The VLFeat and OpenCV libraries will be used; • Provide a solid basis for students interested to further their studies in the fields of computer vision, computer graphics, video analytics and human computer interface. Learning Outcomes: 1. Knowledge & Understanding: By the end of the study-unit the student will be able to: • Explain in simple terms the mechanism and rationale of content-based image retrieval tools; • Explain the basic understanding of how the image matching can be performed effectively and efficiently; • Identify which image techniques are mostly appropriate for a given application; • Understand the benefits and limitations of the covered techniques in real-life applications. 2. Skills: By the end of the study-unit the student will be able to: • Use the paradigm taught in study-unit to perform image matching in different applications; • Compare the appropriateness of a number of keypoint description methods to solve simple problems; • Implement various state-of-the-art image processing techniques; • Proceed with advanced image analytics in a Masters degree. Main Text/s and any supplementary readings: Main Texts: Digital Image Processing (3rd Edition) Hardcover – August 31, 2007, by Rafael C. Gonzalez (Author), Richard E. Woods (Author). ISBN-13: 978-0131687288 ISBN-10: 013168728X Edition: 3rd. |
|||||||||
| ADDITIONAL NOTES | Pre-requisite Qualifications: Pure Mathematics or Computer Science (Intermediate Level) | |||||||||
| STUDY-UNIT TYPE | Lecture and Tutorial | |||||||||
| METHOD OF ASSESSMENT |
|
|||||||||
| LECTURER/S | Adam Gauci |
|||||||||
|
The University makes every effort to ensure that the published Courses Plans, Programmes of Study and Study-Unit information are complete and up-to-date at the time of publication. The University reserves the right to make changes in case errors are detected after publication.
The availability of optional units may be subject to timetabling constraints. Units not attracting a sufficient number of registrations may be withdrawn without notice. It should be noted that all the information in the description above applies to study-units available during the academic year 2023/4. It may be subject to change in subsequent years. |
||||||||||