This repository encompasses five distinct projects, each exploring different aspects and techniques within the field of computer vision.
Each sub-project within this repository is designed to tackle a unique challenge in computer vision, ranging from image processing and enhancement to object detection and recognition.
- Description: Focuses on implementing algorithms for demosaicing images and enhancing them using High Dynamic Range (HDR) techniques.
- Read More
- Description: Develops a system capable of recognizing and re-identifying faces within video streams, leveraging both supervised and unsupervised learning methods.
- Read More
- Description: Implements the selective search algorithm for object detection, coupled with a pipeline for recognizing objects within images.
- Read More
- Description: Creates a system for writer identification and retrieval, analyzing handwriting samples to match writers.
- Read More
- Description: Estimates the size of a box from distance images using RANSAC for robust plane fitting, addressing challenges in noise sensitivity and measurement accuracy.
- Read More
To begin exploring these projects, clone this repository to your local machine:
git clone <repository-url>Navigate into each project's directory to find specific instructions on installation, dependencies, and usage.
The projects may have varying dependencies, primarily including libraries such as numpy, scipy, matplotlib, scikit-learn, and opencv-python. Ensure to check the requirements.txt file within each project's directory and install necessary packages:
pip install -r requirements.txtContributions across any of the sub-projects are highly encouraged. Please refer to the specific guidelines in the respective project's README for more details on contributing.