- Course
- 2024-2025
- Semester
- 2
- ECTS
- 6
- Type
- Compulsory
- University
- UDC and UPorto
Subject objectives
-Study and application of advanced digital image processing techniques.
-Study and application of advanced techniques of digital image analysis.
-Analysis of real problems, and design and development of solutions based on advanced image processing and analysis technologies.
-Evaluation of the adequacy of the methodologies applied in specific problems.
This curricular unit addresses the most advanced topics in image processing and analysisand presents itself as a sequence of a curricular unit where the fundamental topics arepresented. It is designed to provide the essential foundation for students wishing topursue research in this area. In addition to the study and application of advancedtechniques of image processing and analysis, applications in this area are studied thataim to solve real problems. This approach gives students the necessary tools to apply the algorithms studied in practical cases, as well as the basis for developing new algorithms.
Contents
-Advanced denoising
Total variation
-Advanced edge detection
Bilateral filter
Anisotropic diffusion
Phase congruence
-Advanced segmentation
Deformable models
Level-set methods
Markov Random Fields
Graph cuts
-Learning-based segmentation
Active shape/appearance models
– Salience and attention models
-Selected topics on advanced image processing and analysis
Semantic segmentation
Multi-view enhancement
Superresolution
Inpainting
Coloring
Photo stitching
Background removal
Basic and complementary bibliography
Basic:
Gary Bradski, Adrian Kaehler (2008). Learning OpenCV. O’Reilly
David A. Forsyth, Jean Ponce (2002). Computer vision: a modern approach. Prentice- Hall
Richard Szeliski (2010). Computer vision: algorithms and applications. Springer
Simon J.D. Prince (2012). Computer Vision: Models, Learning, and Inference. Cambridge University Press
Ian Goodfellow, Yoshua Bengio, Aaron Courville (2016). Deep learning. MIT Press
M. Sonka, V. Hlavac, R. Boyle. Image Processing, Analysis, and Machine Vision. 4th edition. Cengage Learning. 2015
Competencies
CE1 – To know and apply the concepts, methodologies and technologies of image processing
CE3 – To know and apply the concepts, methodologies and technologies of image and video analysis
CE4 – To conceive, develop and evaluate complex computer vision systems
CE5 – To analyze and apply methods of the state of the art in computer vision
CB6 – To possess and understand knowledge that provides a basis or opportunity to be
original in the development and/or application of ideas, often in a research contextB5 CB10 – That students possess the learning skills to enable them to continue studying in a largely self-directed or autonomous manner
CG2 – Ability to analyze a company’s needs in the field of computer vision and determine the best technological solution for it
CG3 – Ability to develop computer vision systems depending on existing needs and apply the most appropriate technological tools
CG5 – Ability to identify unsolved problems and provide innovative solutions
CG7 – Ability to learn autonomously for specialization in one or more fields of study
Teaching methodology
Laboratory practice:
Analysis and resolution of practical cases using techniques learned in the lectures.
Objective test:
Test with questions about the theoretical contents of the subject as well as practical problems.
Guest lecture / keynote speech:
Oral presentation (using audiovisual material and student interaction) designed to transmit knowledge and encourage learning.
Evaluation system
Option 1:
Laboratory practice: Practical exercises about the topics learned in the lectures. It will be assessed the suitability of the proposed solutions and the quality of the obtained results.
Qualification: 80%
Competences: CE1 CE3 CE4 CE5 CG2 CG7
Short answer questions: Face-to-face quizzes with short answer questions about the topics learned in the lectures that will be used to assess the acquisition of knowledge.
Qualification: 20%
Competences:CB6 CG3 CG5
Option 2:
The objective face-to-face test is 100% of the final grade.
Studying time and personal work
Recommended study time for students is about 2 hours per week. Additionally, we estimate that they should spend about 6,5 hours / week working in a number of assignments. All of these activities add up to around 120h/semester.
Subject study recommendations
Subjects that it is recommended to have taken before:
Fundamentals of Machine Learning for Computer Vision /614535007
Fundamentals of Image Analysis and Processing/614535001
Image Description and Modeling/614535004
Subjects that are recommended to be taken simultaneously:
Visual Recognition/614535005
Advanced Machine Learning for Computer Vision/614535008