This repository contains practical experiments, small projects, and image-processing exercises in Computer Vision (CV). It includes demos, object detection, image preprocessing, and small end-to-end projects.

Note: This repository is continuously updated with new experiments and notebooks.

image-processing/
├── binarization-otsu-soulva.py
├── salt_and_pepper_noise_removal.py
└── mini-projects/
├── action_recognition/
│ └── 02_action_recognition.ipynb
├── caption_generation/
│ └── 01_caption_generation_from_images.ipynb
├── car-dent-and-scractch-masking/
│ └── car_dent_scratch_masking.ipynb
├── pan-card-image-tampering-analysis/
│ ├── images/
│ ├── results/
│ └── pan-card-image-tampering-analysis.ipynb
├── real-life-violence-detection/
│ └── real_life_violence_detection.ipynb
├── table-items-yolo-detection/
│ ├── data/
│ ├── random-test-images/
│ ├── results/
│ └── training_notebook.ipynb
└── urdu-ocr/
├── ocr_data_processing.ipynb
└── ocr_training.ipynb

• image-processing/
  Standalone scripts for image preprocessing, e.g., binarization, noise removal.

• mini-projects/
  Contains smaller CV projects and experiments. Each project has its own folder with notebooks, datasets (if small), and results.

• Results & Images
  Relevant outputs, example images, and visualizations are kept within each project folder under results/ or images/ for clarity.

1. Clone the repository:

git clone https://github.com/your-username/cv-labs.git
cd cv-labs

Author: Aroosh Ahmad — AI Engineer (NLP, LLMs, ML Systems)             GitHub • LinkedIn