A novel method to extract ECG morphology from scanned ECG records

ECG is a valuable source of information regarding the patient's clinical data repository. Archiving the paper Electrocardiogram (ECG) trace as an image requires immense storage space and manpower for storage and retrieval of the patient records. Objective of this paper is to extract the ECG Morphological features from the paper ECG. In this paper, we have proposed a novel technique to extract the ECG Morphological features. The proposed algorithm has been evaluated with 25 patient's ECG sheets printed from 12-lead ECG equipments. Further, the proposed technique enhances the accuracy of heart rate and morphological feature extraction from the obtained time series signal. The evaluation of the digital time series data conversion algorithm has been performed by comparing obtained heart rate with value printed on the paper. The accuracy of the heart rate was found to be 99.12%. Evaluation of the proposed slope method for ECG morphological feature extraction was done by comparing the obtained values with manual data and this method offered an accuracy of 97.09%.