Master of Science in Data Science La Salle Campus Barcelona URL

Master of Science in Data Science

Become an expert in analysing, structuring, filtering, visualizing and valuing the production of generated data

Image processing

Back to Syllabus

Description
Image processing and computer vision are two areas that are undergoing a huge evolution within the computer sciences, in everything related to new applications and new methods. In this field, the purpose is to endow a machine with the ability to perceive an image, process it and extract information to understand its content and make decisions. This is where data science plays a relevant role, as digital images are a collection of information (data) that represent our environment, and the methods of data analysis, pattern recognition and data grouping are basic in the processes of information extraction and decision making. Methods of feature extraction, machine learning, deep learning, data compression, variance and principal component analysis are basic tools in the field of computer vision.
Type Subject
Optativa
Semester
Second
Credits
5.00

Titular Professors

Alejandro Gonzalez Alzate
Professor

Professors

Xavier Sevillano Domínguez
Previous Knowledge

Md008 and MD008 subjects

Objectives

The goals will focus on:
• Learn about image processing, basic techniques of image manipulation and visual features extraction.
• Apply different machine learning and deep learning techniques for solving computer vision problems (classification, detection, segmentation, tracking)

Contents

SYLLABUS

1. Image processing I: image definition, basic processing techniques and spatial deformations. (Theoretical and practical) (1.5 hours)
2. Image processing II: Filtering techniques, morphology, segmentation, low-scale descriptors. (Theoretical and practical) (1.5 hours)
3. Image processing III: Classical extraction of visual descriptors: Histograms, HOG, LBP, Fourier, Wavelets, filters. (Theoretical and practical) (1.5 hours)
4. Computer Vision I: Classification methods, detection and segmentation (Machine Learning). (Theoretical) (1.5 hours)
5. Computer Vision II: Machine learning practice: KNN, SVM, Random forest. (Practice) (1.5 hours)
6. Computer vision III: Deep learning applied to detection / classification. (Theoretical) (1.5 hours)
7. Computer Vision IV: Deep Learning Practice. (Practice) (1.5 hours)
8. Computer Vision V: Advanced deep learning techniques, transfer learning, image generation. (Theoretical practice) (1.5 hours)

Note: Topics can be adjusted and/or modified at the discretion of the master's coordination.

Methodology

The methodology used combines master classes, student participation, practical exercise at class and solving a challenge or doing a research exercise as final work. For the student, this will involve group work with an oral presentation at class and a written assessment.

Evaluation

This subject will be evaluated on a continuous way via the development of a challenge proposed or by a research work on already existing solutions in some scientific context and a final presentation in class.

Evaluation Criteria

Continuous assessment
This subject will be evaluated on a continuous way via the development of a challenge proposed or by a research work on already existing solutions in some scientific context and a final presentation in class.
The final grade will be a weighting of:
- Challenge solution (implementation) and/or presentation or research work: 80%
- Short questionaries in class: 20%

Extraordinary call
The exam and/or works of extraordinary call will be determined from the coordination of the subject.

Copies regulations
The subject is governed by the general regulations of copies of La Salle Campus BCN:
https://www.salleurl.edu/en/copies-regulation
The training activities will be considered to have the following category:
• Final exercise or challenge: highly significant

Basic Bibliography

The bibliography will be detailed throughout the course.
All class material (presentations, exercises, articles, documents, etc.) will be shared in the subject folder of the La Salle Intranet: eStudy.

Additional Material

The complementary bibliography will be detailed throughout the course.