This repository is a compilation of the activities and projects given to members of the AY 2020-2021 Computer Vision Group under Mr. Arren C. Antioquia of the Department of Software Technology, De La Salle University.
The focus of the activities is to expose the members of the group to technologies and techniques related to the study of computer vision, "a field of artificial intelligence that enables computers and systems to derive meaningful information from digital images, videos, and other visual inputs" (IBM, n.d.).
The activities that I worked on are as follows:
| Period | Topic | Author of the Activity |
|---|---|---|
| Term 2, AY 2020-2021 | Jupyter Notebook and Python | Mr. Arren C. Antioquia arren.antioquia@dlsu.edu.ph |
| Term 2, AY 2020-2021 | Vector and Matrix Operations | Mr. Arren C. Antioquia arren.antioquia@dlsu.edu.ph |
| Term 2, AY 2020-2021 | k-Nearest Neighbors (kNN) | Adapted from Stanford University's CS231n: Convolutional Neural Networks |
This project consists of Jupyter notebooks, with the following Python libraries and modules used:
| Libraries/Modules | Description | License |
|---|---|---|
random |
Provides functions for generating pseudo-random numbers with various common distributions | Python Software Foundation License |
pickle |
Provides functions for converting Python objects to streams of bytes and back | Python Software Foundation License |
os |
Provides miscellaneous operating system interfaces | Python Software Foundation License |
numpy |
Provides a multidimensional array object, various derived objects, and an assortment of routines for fast operations on arrays | BSD 3-Clause "New" or "Revised" License |
matplotlib |
Provides functions for creating static, animated, and interactive visualizations | Matplotlib License (BSD-Compatible) |
The descriptions are taken from their respective websites.
The activities were accomplished by:
- Mark Edward M. Gonzales
mark_gonzales@dlsu.edu.ph
gonzales.markedward@gmail.com
The authors of the activities are credited in the Task section and in the pertinent Jupyter notebooks.
The dataset used in the kNN notebook is CIFAR-10, which is taken from Alex Krizhevsky's 2009 paper Learning Multiple Layers of Features from Tiny Images.