logo-polimi
Loading...
Degree programme
Programme Structure
Show/Search Programme
Course Details
Save Document
Degree Programme
Read Degree Programme
Faculty
Infrastructures
Quantitative data
International context
Customized Schedule
Your customized time schedule has been disabled
Enable
Search
Search a Professor
Search a Course
Search a Course (system prior D.M. n. 509)
Search Lessons taught in English

Glossary
Semester (Sem)
1First Semester
2Second Semester
AAnnual course
Language
Course completely offered in italian
Course completely offered in english
--Not available
Innovative teaching
The credits shown next to this symbol indicate the part of the course CFUs provided with Innovative teaching.
These CFUs include:
  • Subject taught jointly with companies or organizations
  • Blended Learning & Flipped Classroom
  • Massive Open Online Courses (MOOC)
  • Soft Skills
Course Details
Context
Academic Year 2017/2018
School School of Industrial and Information Engineering
Name (Master of Science degree)(ord. 270) - MI (481) Computer Science and Engineering
Track T2A - COMPUTER SCIENCE AND ENGINEERING
Programme Year 2

Course Details
ID Code 051909
Course Title IMAGE CLASSIFICATION: MODERN APPROACHES
Course Type Mono-Disciplinary Course
Credits (CFU / ECTS) 5.0
Semester --
Course Description The goal of this course is to provide students with an understanding of the most important image-classification algorithms, and in particular of the feature-extraction phase, which is often their most critical component. We will provide an overview of both hand-crafted features, that are still adopted in many industrial and automation-control scenarios, and data-driven (i.e. learned) features, which have recently become a standard in challenging natural-image recognition problems with huge training datasets. In particular, the main goals of this course are the following. Understanding image-classification problems, the main challenges of handling images, and the basic framework for image-classification algorithms. Present the most relevant techniques to extract features. In particular, we will address both i) hand-crafted features, which descend from computer-vision literature, and ii) data-driven features, which are learned from a training set of images. Provide students with some guidance to tackle practical issues rising in image classification, including: performance assessment, dataset augmentation, transfer learning for pre-trained models. Illustrate the structure of convolutional networks, as a meaningful example of a deep-learning architecture. Provide an overview of techniques to process images in Python/Matlab.

Schedule, add and removeAlphabetical groupProfessorLanguageCourse details
From (included)To (excluded)
--AZZZZBoracchi Giacomo
manifesti v. 3.3.7 / 3.3.7
Area Servizi ICT
16/07/2020