An improved method for digital time series signal generation from scanned ECG records

Archiving the paper Electrocardiogram (ECG) trace as an image in hospitals and clinics is a regular practice to maintain the patients´ history. However, it requires immense storage space and manpower for storage and retrieval of the patient records. In this paper we have proposed an improved algorithm for the existing paper ECG trace to digital time series with adaptive and iterative image processing techniques. We have tested our algorithm with a number of ECG sheets printed from 12-lead ECG equipments. Further, the proposed technique is enhanced to calculate the heart rate from the obtained time series to facilitate the evaluation of the methodology. Compared with the manually obtained heart rate, the methodology shows an accuracy of 95%, demonstrating the usefulness of the approach. Also, elaborate experimentation with the algorithm has brought out the robustness of the methodology in handling ECG traces from different sources.