Tentalabbet

TSBB19 · 6 credits · Advanced level (A1N) · Datateknik

Machine Learning for Computer Vision

Active · next start HT 2026

90%

passed the latest ordinary exam

TEN1 · 24 Oct 2025 · 39 students

91%

passed the ordinary exams, all sittings over the last 5 years

TEN1 · 194 students

40%

Harder than 40% of courses at advanced level

Compared with 285 courses at the same level, ordinary exams over the last three academic years. 76 students.

Part of 8 programmes

Exam

TEN1 Written examiation

  • 5
  • 4
  • 3
  • U

Ordinary exams

91% passed · 194 students

  • 90%39
  • 89%37
  • 100%32
  • 83%46
  • 98%40

Re-exams

67% passed · 6 students

  • 67%6
  • Pass the re-exam: 67% (6 students), compared with 91% (194 students) on the ordinary exam
  • Get 4 or 5: 49% (200 students)
Show small sittings (8)

Sittings with fewer than 5 students, often credit transfers or special sittings. They are not part of any figure on this page.

  • 100%2
  • 100%1
  • 100%3
  • 100%2
  • 100%1
  • 100%1
  • 100%1
  • 0%1

Other modules

Partial exams, hand-ins and labs. They are not part of the figures at the top.

Hand-in or lab

PRA1 Project with oral and written presentation

  • G
  • U

Main rounds

97% passed · 158 students

  • 100%35
  • 93%41
  • 94%35
  • 100%47

Later rounds

100% passed · 5 students

  • 100%5
  • Pass a later round: 100% (5 students), compared with 97% (158 students) on the ordinary exam
Show small sittings (1)

Sittings with fewer than 5 students, often credit transfers or special sittings. They are not part of any figure on this page.

  • 100%1

About the course

Aim

Ability to:

  • Explain basic terminology, theories and methods for recognition, detection and tracking of objects in images
  • Explain basic theories of how the brain categorizes visual information
  • Explain current approaches for object recognition, detection and tracking, and current ways to analyze these
  • Develop and experimentally evaluate and analyze different recognition and semantic segmentation algorithms and summarize the results
  • Select suitable methods for automatic training of recognition and semantic segmentation systems

Content

Machine learning with convolutional neural networks, and support vector machines. Invariant local features and feature extraction in digital images, bag-of- features framework, principles of object recognition and detection, constellation models, shape descriptors and matching, part-based models for recognition, the role of context in recognition, deep feature learning, and connections to human object recognition.

Examiner
Per-Erik Forssén
Scheduled hours
48 h
Main field of study
Datateknik
Syllabus on Studieinfo ↗