Digital Image Processing
A.Y. 2020/2021
Learning objectives
The course deals with the analysis and processing of still images and videos. The goal is to convey conceptual instruments and basic algorithms which allow to know the principles of the image formation and coding, to improve the image quality, and to identify the elements of interest in real scene images/videos.
Expected learning outcomes
Learn the principle of the image formation and coding. Learn the basic image enhancement techniques. Learn the image analysis methodologies aiming at extracting high level features and real scene semantic interpretations
Lesson period: First semester
Assessment methods: Esame
Assessment result: voto verbalizzato in trentesimi
Single course
This course cannot be attended as a single course. Please check our list of single courses to find the ones available for enrolment.
Course syllabus and organization
Single session
Responsible
Lesson period
First semester
During the emergency phase, the course will be held online, using the Zoom platform, possibly in a synchronous modality. Lectures will be recorded, loaded on Ariel, and being available for the entire semester.
Material:
the program and the material will not change with respect to the standard one.
Examination:
The exam modality and the evaluation criteria will not change with respect to what indicated in the syllabus (ordinary modality).
The written exam will be held in presence or in a distance modality (according to the university guidelines) on the platform exam.net (for more details refer to the university portal)
Material:
the program and the material will not change with respect to the standard one.
Examination:
The exam modality and the evaluation criteria will not change with respect to what indicated in the syllabus (ordinary modality).
The written exam will be held in presence or in a distance modality (according to the university guidelines) on the platform exam.net (for more details refer to the university portal)
Course syllabus
- Introduction to image acquisition, digitalization and processing
- light, color and the electromagnetic spectrum
- image formats and compression (JPEG)
- punctual transformations for image enhancement
- image filtering in spatial domain
- clusteting and image binarization
- key point detection and local descriptors
- optical flow
- introduction to the classification via convolutional neural networks
- examples and simulations with Python
- light, color and the electromagnetic spectrum
- image formats and compression (JPEG)
- punctual transformations for image enhancement
- image filtering in spatial domain
- clusteting and image binarization
- key point detection and local descriptors
- optical flow
- introduction to the classification via convolutional neural networks
- examples and simulations with Python
Prerequisites for admission
Basis in statistics and linear algebra
Teaching methods
The course consists of lectures and practical classes based on Python.
Teaching Resources
Mosto of the topics are reported in the book:
Rafael C. Gonzalez & Richard E. Woods, "Digital Image Processing", Pearson
other material will be recommended during the classes
Rafael C. Gonzalez & Richard E. Woods, "Digital Image Processing", Pearson
other material will be recommended during the classes
Assessment methods and Criteria
The examination consists of two parts:
1. a written test based on the lecture subjects (75% of final grade)
2. a practical test based on Matlab programming (25% of final grade)
An exam will be provided at the end of the lectures (about end of November) with the same modalities as standard exams
1. a written test based on the lecture subjects (75% of final grade)
2. a practical test based on Matlab programming (25% of final grade)
An exam will be provided at the end of the lectures (about end of November) with the same modalities as standard exams
Professor(s)