https://github.com/vinukavinnath/ipcv
A collection of image processing and computer vision tutorials covering topics from shape detection to deep learning-based image classification. Created under the supervision of Dr. Kaneeka Vidanage.
https://github.com/vinukavinnath/ipcv
computer-vision deep-learning image-processing multiclass-classification neural-network opencv tensorflow vgg16
Last synced: 2 months ago
JSON representation
A collection of image processing and computer vision tutorials covering topics from shape detection to deep learning-based image classification. Created under the supervision of Dr. Kaneeka Vidanage.
- Host: GitHub
- URL: https://github.com/vinukavinnath/ipcv
- Owner: vinukavinnath
- Created: 2024-07-05T16:42:31.000Z (almost 2 years ago)
- Default Branch: dev
- Last Pushed: 2024-07-26T10:57:01.000Z (almost 2 years ago)
- Last Synced: 2025-06-01T11:59:15.558Z (about 1 year ago)
- Topics: computer-vision, deep-learning, image-processing, multiclass-classification, neural-network, opencv, tensorflow, vgg16
- Language: Jupyter Notebook
- Homepage:
- Size: 16.1 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Image Processing and Computer Vision - Tutorials
This repository contains a collection of image processing and computer vision tutorials created under the supervision of [Dr. Kaneeka Vidanage](https://foc.kdu.ac.lk/computer_science/dr-kaneeka-vidanage/). The tutorials cover various topics, from basic shape detection to complex image classification tasks using deep learning models.
## Table of Contents
1. Shape Detection
2. Face Recognition
3. Vehicle Number Plate Detection
4. Object Detection with MobileNet
5. Pneumonia Detection with VGG16
6. Gun Detection with VGG16
7. Multiclass Image Classification
### Shape Detection
This tutorial covers the basics of shape detection using OpenCV. It includes code for set of preprocessing tasks and identify the shape using contours in an image.
### Face Recognition
Demonstrates face recognition using OpenCV's pre-trained models and face_recognition library. It explains how to detect faces in an image and recognize known individuals.
### Vehicle Number Plate Detection
This tutorial focuses on detecting vehicle number plates using OpenCV and easy_ocr. It covers image preprocessing, plate detection, and character recognition.
### Object Detection with MobileNet
Explains how to use the MobileNet SSD model for object detection. It includes steps for loading the model, processing images, and identifying objects in real-time.
### Pneumonia Detection with VGG16
This tutorial uses the VGG16 deep learning model to detect pneumonia from chest X-ray images. It covers data preprocessing, model training, and evaluation using transfer learning techniques.
### Gun Detection with VGG16
Similar to the pneumonia detection tutorial, this one uses the VGG16 model to detect guns in images. It includes steps for training the model and making predictions.
### Multiclass Image Classification
This tutorial demonstrates how to perform multiclass image classification using CIFAR10 dataset and campares ANN and CNN characteristics.
## Reflective Journal
[Click here](https://kduac-my.sharepoint.com/:b:/g/personal/39-bcs-0005_kdu_ac_lk/EZZ_htCTLeBAmt1F-C2nG08B4biDHS6Ba-SkmXZUvKTL_A?e=lDKYJ7) to refer the Reflective Journal based on above activities.
## Setting up the repository
1. Clone this repository
```bash
git clone https://github.com/vinukavinnath/ipcv.git "IPCV"
```
2. Download and install Anaconda Distribution
Click [here](https://www.anaconda.com/download) to download.
3. Create a virtual environment using `conda` commands and activate it.
4. Open Anaconda Navigator and launch Jupyter Notebook.
5. Open notebooks through jupyter notebook and run python commands.
## Contributing
Contributions are welcome! If you have any improvements or new tutorials to add, please fork the repository and submit a pull request. Make sure to follow the existing code style and include detailed explanations for any new content.