Skip to content

semthedev/OpenCV-projects

Repository files navigation

Computer Vision — Lab Projects

Academic projects for a Computer Vision course. Each lab covers a distinct topic in image processing or deep learning, implemented in Python as Google Colab notebooks.


Labs

Lab 1 · Basic Image Processing

Open In Colab

Introduction to OpenCV and Matplotlib. Covers loading images, creating copies, drawing shapes, and adding text annotations.


Lab 2 · Spatial Filtering & Laplacian Operator

Open In Colab

Applies and compares classical image filters — median, mean, Gaussian blur, and erosion — followed by edge detection using the Laplacian operator.


Lab 3 · MNIST Digit Recognition with PyTorch

Open In Colab

Builds and trains a fully connected neural network on the MNIST handwritten digit dataset using PyTorch. Covers data normalization, one-hot encoding, nn.Sequential, Adam optimizer, MSE loss, and training loop with history visualization.


Lab 4 · Face Detection with MediaPipe

Open In Colab

Real-time face detection using the MediaPipe Tasks API and the pre-trained BlazeFace (short-range) model. Draws bounding boxes and facial keypoints on detected faces.


Lab 5 · Object Recognition on CIFAR-10 (Keras CNN)

Open In Colab

Trains a convolutional neural network (Conv2D + MaxPooling + Dropout) on the CIFAR-10 dataset (10 object classes) using Keras. Includes model saving and inference on custom images.


Lab 6 · Clothing Recognition on Fashion-MNIST (Keras)

Open In Colab

Classifies clothing items from the Fashion-MNIST dataset (10 categories) using a dense neural network in Keras/TensorFlow. Includes evaluation, prediction visualization, and inference on custom images.


Stack

Area Tools
Image processing OpenCV, NumPy
Deep learning PyTorch, TensorFlow / Keras
Computer vision MediaPipe (BlazeFace)
Visualization Matplotlib
Environment Python 3, Google Colab

About

This repository is designed for storing and showcasing my academic projects for the Computer Vision course.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors