ECG Image Classification in Real time based on the Haar-like Features and Artificial Neural Networks

Abstract The paper presents a ECGs classification system that uses powerful algorithms image processing and artificial intelligence. The descriptor haar-like is based on the concept of the integral image to accelerate the calculation of haar features and the classifier multilayer perceptron type. The training and testing of the proposed system were performed on two basic types: a learning base containing labeled data (normal ECG and ECG sick) and another base unlabeled data. The experimental results have shown that the system combines between the respective advantages of haar-like descriptor and artificial neuron networks in terms of robustness and speed.