Course Code: 14108 Q1
Author: PhD. Raúl Llasag Rosero
Email: raulhomero.llasag-externo@unir.net
GitHub: @rhllasag
ECTS Credits: 6
Welcome to the Artificial Vision course! This repository contains all the interactive presentation materials, code examples, and resources you'll need throughout the semester. The course provides a comprehensive introduction to computer vision techniques, from basic image processing to advanced machine learning applications.
By the end of this course, you will be able to:
- ✅ Work with computational vision models and understand their applications
- ✅ Apply techniques for image pre-processing, segmentation, and feature extraction
- ✅ Develop systems for voice, image, and object recognition
- ✅ Evaluate performance metrics in computational perception systems
- ✅ Implement practical solutions using modern computer vision libraries
- Topics & Tests: 15 mini-tests (1.5 pts total)
- Laboratory: 1 practical lab (5.0 pts)
- Activities: 3 assignments (8.5 pts total)
- Final Exam: 1 comprehensive exam
- Topic 1: Introduction to perception systems
- Topic 2: Elements of a perception system
- Topic 3: Signal capture and digitization
- Topic 4: Sources and types of noise
- Topic 5: Anomaly detection and cancellation
- Topic 6: Image processing - Elementary operations
- Topic 7: Image processing - Spatial operations
- Topic 8: Signal processing - Filtering and frequency analysis
- 🧪 Lab 1: Image enhancement using elementary operations (5.0 pts)
- Topic 9: Mathematical morphology
- Topic 10: Growing region techniques
- 📝 Activity 2: Spatial and morphological filters in real scenarios (3.5 pts)
- 📝 Activity 3: Amazon deforestation analysis with segmentation (5.0 pts)
- Topic 11: Statistical and frequency properties of signals
- Topic 12: Texture characterization in images
- Topic 13: Multiscale processing and advanced methods
- Topic 14: Decision support algorithms - principles and implementation
- Topic 15: Current applications of signal processing
- Basic knowledge of mathematics (linear algebra, statistics)
- Programming experience (Python recommended)
- Familiarity with image formats and basic digital concepts
Classes/
├── Introduction/ # Course introduction materials
│ ├── index.html # Interactive presentation
│ ├── style.css # Custom styling
│ ├── scripts/ # JavaScript modules
│ │ ├── main.js # Main presentation logic
│ │ ├── interactive.js # Interactive elements
│ │ └── date-handler.js # Date utilities
│ ├── images/ # Course images and diagrams
│ └── unir/ # UNIR branding assets
├── Block1/ # (To be added)
├── Block2/ # (To be added)
├── Block3/ # (To be added)
├── Block4/ # (To be added)
├── Block5/ # (To be added)
└── README.md # This file
-
Local Access:
# Navigate to the course directory cd "c:\Users\[YourUsername]\Desktop\UNIR\Classes" # Open any presentation in your browser # Double-click on index.html or open with your preferred browser
-
Navigation Controls:
- → / Space: Next slide
- ← : Previous slide
- ↑ / ↓: Vertical navigation (if available)
- Esc: Overview mode
- F: Fullscreen
- S: Speaker notes (when available)
- R: Reload presentation
- Browser: Chrome, Firefox, Safari, or Edge (latest versions)
- Code Editor: VS Code, PyCharm, or Jupyter Notebook
- Python Environment: Python 3.8+ with the following libraries:
pip install opencv-python numpy matplotlib scikit-image pillow
- RAM: 8GB minimum (16GB recommended)
- Storage: 5GB free space for course materials and projects
- Display: 1920x1080 minimum resolution for optimal presentation viewing
| Week | Content | Deliverables |
|---|---|---|
| 1-3 | Block 1: Perception Systems | Mini-tests 1-5 |
| 4-6 | Block 2: Image Processing | Lab 1 submission |
| 7-9 | Block 3: Morphology & Segmentation | Activities 2 & 3 |
| 10-12 | Block 4: Feature Extraction | Mini-tests 11-13 |
| 13-15 | Block 5: Decision Making | Final preparation |
| 16 | Final Exam Period | Final Exam |
- Practice Regularly: Computer vision is hands-on - code examples weekly
- Visual Learning: Create your own image processing examples
- Join Study Groups: Collaborate with classmates on understanding concepts
- Use the Forums: Don't hesitate to ask questions in course forums
- Real-world Applications: Try to relate concepts to everyday image processing tasks
- Digital Image Processing by Gonzalez & Woods
- Computer Vision: Algorithms and Applications by Richard Szeliski
- Learning OpenCV 4 by Adrian Kaehler & Gary Bradski
- CS231n: Convolutional Neural Networks for Visual Recognition (Stanford)
- Computer Vision Basics (Coursera)
- Course Forums: Primary channel for academic questions
- Office Hours: Schedule via email for complex topics
- Email: For urgent or personal matters only
- GitHub Issues: For technical problems with course materials
- Forum questions: Within 24-48 hours
- Email inquiries: Within 48-72 hours
- Assignment feedback: Within 1 week of submission
The presentation covers key milestones in computer vision history:
- 4th century BC: Camera Obscura (Aristotle)
- 1957: Perceptron (Frank Rosenblatt)
- 1960s: Digital Image Processing (Azriel Rosenfeld)
- 1960s: Computer Vision (Larry Roberts)
- 1986: Edge Detection (John Canny)
- 1989: CNNs (Yann LeCun)
- 2000s: Deep Learning Revolution
This course material is provided for educational purposes within the UNIR Master's program. Please respect intellectual property rights and use materials according to university guidelines.
Best of luck with your studies! 🎓
Last updated: November 2025
"Computer vision is not just about seeing - it's about understanding what we see."
- PhD. Raúl Llasag Rosero