Computer-Vision 👁️

A collection of computer vision notebooks exploring fundamental image processing techniques and advanced deep learning models.
This repository serves as a hands-on guide to understanding, implementing, and experimenting with algorithms in image analysis, segmentation, classification, and object detection.

---

📂 Repository Structure

🔹 Fundamentals

• Understanding_Images.ipynb – Basics of image representation.
• Edge_Detection.ipynb – Classic edge detection methods.
• Edge_Detection_Algorithms.ipynb – Sobel, Canny, and others.
• Histogram_Equalization.ipynb – Contrast enhancement.
• Histogram_Normalization_Algorithms.ipynb – Normalization techniques.
• Image_Transformations.ipynb – Rotation, scaling, flipping.

🔹 Classical & Deep Learning Models

• Image_Segmentation.ipynb – Segmentation techniques.
• Auto_Encoders.ipynb – Feature extraction & dimensionality reduction.
• AlexNet.ipynb – Classic CNN for image classification.
• ResNet_and_VGG_16.ipynb – Deep CNN architectures.
• VGG16_RockPaperScissor.ipynb – RPS classification with VGG16.
• RPS_Net.ipynb – Custom CNN for Rock-Paper-Scissors.

🔹 Object Detection

• YOLO_v9.ipynb – Object detection with YOLO.
• traffic_sign_detection_yolov3.ipynb – Traffic sign detection.
• Faster_RCNN.ipynb – Region-based object detection.
• Fine_tuning_Fastercnn.ipynb – Transfer learning with Faster R-CNN.
• Fruit_Detection.ipynb – Object detection on fruit dataset.
• InceptionResNetV2_UNet.ipynb – Image segmentation with U-Net backbone.

---

🚀 Features

• Covers image processing fundamentals and state-of-the-art CV models.
• Hands-on implementation of object detection, segmentation, and classification.
• Applications in traffic signs, fruit detection, and real-world datasets.
• Includes both traditional algorithms and deep learning pipelines.

---

🛠️ Requirements

• Python 3.8+
• Jupyter Notebook / JupyterLab
• Libraries:

  pip install tensorflow torch torchvision opencv-python numpy pandas matplotlib scikit-learn seaborn