Overview
Computer Vision is a subfield of Artificial Intelligence whose goal is to process images or videos to extract information that could be used by a human end-user, or that could serve as input to further computational processes. Recent advances created a distance from the traditional image processing methods, bringing this … For more content click the Read More button below.
This topic introduces the fundamental methods in image processing and computer vision, as well as to the novel deep learning models for image recognition and understanding, including: image formation, image filtering, thresholding and image segmentation, feature detection, image classification, object recognition, and deep learning for computer vision. The students are evaluated with the development of practical and theoretical components and a final research project.
Topic availabilities
To view topic availabilities, select an availability from the drop down, towards the top right of the screen.
Tuition pattern
To view tuition patterns, select an availability from the drop down, towards the top right of the screen.
Aims
This topic aims to:
- Provide the student with knowledge of the theories and applications of image processing and machine vision
- Familiarize the student with some important concepts and analytical techniques for linear and non-linear image processing.
- Give the student some experience in the development of image processing applications and research using Python, OpenCV and other Python libraries for numeric processing
- Familiarize the student with a broad range of operators and processing techniques for image reconstruction, filtering, enhancement, expansion, motion estimation, optic flow, image classification and video processing
- Provide the students the basic knowledge to explore the field of machine vision, including methods related to the industrial and scientific development of robotic systems
Learning outcomes
On completion of this topic you will be expected to be able to:
1.
Understand the theories and methods in image processing and computer vision
2.
Critically review and assess scientific literature related to the field
3.
Identify, formulate and solve problems in image processing and computer vision
4.
Analyse, evaluate and examine existing computer vision systems
5.
Communicate effectively and work in teams to develop complex projects involving image or video processing
6.
Attain competence on the use of Python, OpenCV, Keras, Tensorflow and other computer development tools for research and applications of image processing and machine vision
7.
Design and develop practical image processing and computer vision applications
8.
Conduct themselves professionally and responsibly in the various areas related to AI, machine learning and computer vision
Assessments
To view assessment information, select an availability from the drop down, towards the top right of the screen.
Requisites information
Pre-requisites:
Assumed knowledge
Students should have a good notion of probability, statistics and linear algebra