South African Coin Recognition System using multiple feature extraction techniques and classifiers

This project is about real-time 2D object recognition. The goal is to have the computer identify a specified set of objects placed on a white surface in a translation, scale, and rotation invariant manner from a camera looking straight down. The computer should be able to recognize single objects placed in the image and identify the objects.

This C++ from-scratch project implements a machine learning system to classify images of washers and coins using the K-nearest neighbors (Knn) classifier and K-means clustering for segmentation. The system incorporates Sobel edge detection and Hu moments for shape analysis, allowing it to accurately distinguish between similar circular objects.