AI Bauchi — Computer Vision Course Materials

This repository contains curated materials for teaching and learning Computer Vision with Python. It has lecture notebooks, example code, datasets, and references grouped into modules.

Learning outcomes

• Understand image formation and basic image processing
• Implement feature detection, description and matching
• Build and train CNNs for classification and object detection
• Apply segmentation, tracking and deployment techniques

Prerequisites

• Python 3.9+ (3.10/3.11 tested)
• Basic Python programming and linear algebra
• Familiarity with Jupyter Notebooks is helpful

Quickstart

1. Clone the repository:

git clone https://github.com/AIBauchi/AIBauchi-Computer-Vision-Bootcamp.git
cd AIBauchi-Computer-Vision-Bootcamp

2. Create a virtual environment and install dependencies:

python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

3. Start Jupyter Lab/Notebook and open the modules:

jupyter lab

Recommended libraries

• numpy, scipy, pandas
• matplotlib, seaborn
• opencv-python, scikit-image
• scikit-learn
• tensorflow, keras, torch, torchvision
• albumentations, pillow

How the repository is organized

• Modules are in folders 01_... to 06_... (previously Week1..Week6)
• Each module contains daily notebooks and example code

Module Index

Below is a curated index of the course materials grouped by module (folders were renamed from WeekX to descriptive module names).

• 01 Introduction and Python: 01_Introduction_and_Python

  • 01_Introduction_and_Python/day1/1.1 introduction.md
  • 01_Introduction_and_Python/day2/1.2.1 python review.ipynb
  • 01_Introduction_and_Python/day3/1.3.0-Digital Image.ipynb
  • 01_Introduction_and_Python/day3/1.3.1-Setting Up the Environment.ipynb

• 02 Image Processing: 02_Image_Processing

  • 02_Image_Processing/day1/2.1.0-Matplotlib.ipynb
  • 02_Image_Processing/day1/2.1.1-Image Transformation.ipynb
  • 02_Image_Processing/day2/2.2.0-Advanced Image Processing.ipynb
  • 02_Image_Processing/day3/2.3.0-Feature_Detection_and_Description.ipynb
  • 02_Image_Processing/day3/2.3.1-Hough Transform for Shape Detection.ipynb
  • 02_Image_Processing/day3/2.3.2-Template Matching.ipynb

• 03 Deep Learning for CV: 03_Deep_Learning_for_CV

  • 03_Deep_Learning_for_CV/day1/3.1.0.CV-with-AI.ipynb
  • 03_Deep_Learning_for_CV/day1/3.1.1-Introduction to Deep Learning.ipynb
  • 03_Deep_Learning_for_CV/day2/3.2.0-Training_ANN.ipynb
  • 03_Deep_Learning_for_CV/day3/3.3.0-Introuction to CNN.ipynb
  • 03_Deep_Learning_for_CV/day3/3.3.1-CV CNN.ipynb
  • 03_Deep_Learning_for_CV/day3/3.3.1-Training_ResNet.ipynb

• 04 Transfer Learning & Face Recognition: 04_Transfer_Learning_and_FaceRec

  • 04_Transfer_Learning_and_FaceRec/day1/4.1_transfer-learning.ipynb
  • 04_Transfer_Learning_and_FaceRec/day2/4_2_0_Classification.ipynb
  • 04_Transfer_Learning_and_FaceRec/day3/4.3.1-. Facial Recognition with VGGFace in Keras.ipynb
  • 04_Transfer_Learning_and_FaceRec/day3/4.3.0Face%20Recognition.pdf

• 05 Segmentation and Detection: 05_Segmentation_and_Detection

  • 05_Segmentation_and_Detection/day1/5.1.Image Segmentaion.ipynb
  • 05_Segmentation_and_Detection/day1/5.2. Image Segmentation - Keras, U-Net and SegNet.ipynb
  • 05_Segmentation_and_Detection/day1/5.3. Detectron2 - Mask R-CNN.ipynb
  • 05_Segmentation_and_Detection/day2/5.2.0-Optical Character Recognition (OCR).ipynb
  • 05_Segmentation_and_Detection/day3/5.3.0- Object-Detection.ipynb
  • 05_Segmentation_and_Detection/day3/5.3.1- Annotation.ipynb
  • 05_Segmentation_and_Detection/day3/5.3.2- Yolotest.ipynb
  • 05_Segmentation_and_Detection/day3/5.3.4-Model Accuracy.ipynb

• 06 Deployment and Tracking: 06_Deployment_and_Tracking

  • 06_Deployment_and_Tracking/day1/6.1-object tracking.ipynb
  • 06_Deployment_and_Tracking/day1/training_yolo.ipynb
  • 06_Deployment_and_Tracking/day2/6.2-deploying CV.ipynb
  • 06_Deployment_and_Tracking/day3/6.3-Pose Estimation.ipynb

Suggested improvements and next steps

• Add requirements.txt for reproducible installs (created in this commit)
• Standardize notebook titles and filenames for consistent linking
• Add short README inside each module describing the day's goals
• Consider extracting heavy datasets to an external storage (Git LFS or cloud)

Contributing

• Please open issues or pull requests for corrections, additional exercises or updated materials.

Contributors

This project is maintained and contributed to by:

• Nathaniel Handan — https://github.com/Tinny-Robot
• Matthew Wisdom — https://github.com/matt-wisdom
• Ogochukwu Stanley Ikegbo — https://github.com/Staneering

See CONTRIBUTORS.md for details.

---

This README was updated to be a canonical course index and quickstart guide.

Module Index

Below is a curated index of the course materials grouped by module (folders were renamed from WeekX to descriptive module names).

• 01 Introduction and Python: 01_Introduction_and_Python

  • 01_Introduction_and_Python/day1/1.1 introduction.md
  • 01_Introduction_and_Python/day2/1.2.1 python review.ipynb
  • 01_Introduction_and_Python/day3/1.3.0-Digital Image.ipynb
  • 01_Introduction_and_Python/day3/1.3.1-Setting Up the Environment.ipynb

• 02 Image Processing: 02_Image_Processing

  • 02_Image_Processing/day1/2.1.0-Matplotlib.ipynb
  • 02_Image_Processing/day1/2.1.1-Image Transformation.ipynb
  • 02_Image_Processing/day2/2.2.0-Advanced Image Processing.ipynb
  • 02_Image_Processing/day3/2.3.0-Feature_Detection_and_Description.ipynb
  • 02_Image_Processing/day3/2.3.1-Hough Transform for Shape Detection.ipynb
  • 02_Image_Processing/day3/2.3.2-Template Matching.ipynb

• 03 Deep Learning for CV: 03_Deep_Learning_for_CV

  • 03_Deep_Learning_for_CV/day1/3.1.0.CV-with-AI.ipynb
  • 03_Deep_Learning_for_CV/day1/3.1.1-Introduction to Deep Learning.ipynb
  • 03_Deep_Learning_for_CV/day2/3.2.0-Training_ANN.ipynb
  • 03_Deep_Learning_for_CV/day3/3.3.0-Introuction to CNN.ipynb
  • 03_Deep_Learning_for_CV/day3/3.3.1-CV CNN.ipynb
  • 03_Deep_Learning_for_CV/day3/3.3.1-Training_ResNet.ipynb

• 04 Transfer Learning & Face Recognition: 04_Transfer_Learning_and_FaceRec

  • 04_Transfer_Learning_and_FaceRec/day1/4.1_transfer-learning.ipynb
  • 04_Transfer_Learning_and_FaceRec/day2/4_2_0_Classification.ipynb
  • 04_Transfer_Learning_and_FaceRec/day3/4.3.1-. Facial Recognition with VGGFace in Keras.ipynb
  • 04_Transfer_Learning_and_FaceRec/day3/4.3.0Face%20Recognition.pdf

• 05 Segmentation and Detection: 05_Segmentation_and_Detection

  • 05_Segmentation_and_Detection/day1/5.1.Image Segmentaion.ipynb
  • 05_Segmentation_and_Detection/day1/5.2. Image Segmentation - Keras, U-Net and SegNet.ipynb
  • 05_Segmentation_and_Detection/day1/5.3. Detectron2 - Mask R-CNN.ipynb
  • 05_Segmentation_and_Detection/day2/5.2.0-Optical Character Recognition (OCR).ipynb
  • 05_Segmentation_and_Detection/day3/5.3.0- Object-Detection.ipynb
  • 05_Segmentation_and_Detection/day3/5.3.1- Annotation.ipynb
  • 05_Segmentation_and_Detection/day3/5.3.2- Yolotest.ipynb
  • 05_Segmentation_and_Detection/day3/5.3.4-Model Accuracy.ipynb

• 06 Deployment and Tracking: 06_Deployment_and_Tracking

  • 06_Deployment_and_Tracking/day1/6.1-object tracking.ipynb
  • 06_Deployment_and_Tracking/day1/training_yolo.ipynb
  • 06_Deployment_and_Tracking/day2/6.2-deploying CV.ipynb
  • 06_Deployment_and_Tracking/day3/6.3-Pose Estimation.ipynb