Computer Vision - Workshop 2018-07

info.md

Computer Vision Lecture

• Place: Koombea SAS, Calle 85 #53-14
• Date and Time: Saturday, july 7th, 8:00am-5:00pm
• Duration: One day workshop
• Lecturers: Wayner Barrios and Jorge Martinez
• Repository: https://github.com/PyBAQ/taller-vision-por-computadora (WIP)

Requirements:

• Python 3
• Jupyter Notebook
• OpenCV
• NumPy
• matplotlib
• SciPy
• Reading English Skill

Schedule:

• 8:00~9:00 am: Opening (Introduction, state of art, workshop description)
• 9:00~12:00 pm Basic operations using images.
• 12:00~1:00 pm: Lunch
• 1:00~4:00 pm: Digital Image processing applications (Calculate bottle fill / Clear letters / Face detection)
• 4:00~5:00 pm: Closing (Homeworks, links for studying, deep learning + Stanford vision)

Description:

Computer vision is an interdisciplinary field that deals with how computers can be made for gaining high-level understanding from digital images or videos. From the perspective of engineering, it seeks to automate tasks that the human visual system can do.

Computer vision is concerned with the automatic extraction, analysis and understanding of useful information from a single image or a sequence of images. It involves the development of a theoretical and algorithmic basis to achieve automatic visual understanding.

Content:

1. Introduction and organization, physics of vision, resolution, impulse response.
2. Linear systems, matrix transformations, scaling, translation and rotations
3. Contrast and grey levels, histograms, Gaussian and other non-linear stretches.
4. Color representation, RGB, HSI, 24 bit and 8 bit color tables.
5. Convolution, simple filters, edge detection.
6. Digital filtering, image enhancement, noise.
7. FFTs, Image filtering: smoothing and sharpening.
8. Morphological Operations.
9. Bag of Words, Sift and Surf.
10. Basic Machine Learning Models: KNNs, SVM (linear).