[Show abstract][Hide abstract] ABSTRACT: Digital recovery of cardiac signals from paper printed recordings in implantable cardioverter defibrillators (ICD) is needed whenever signals in digital format can not be retrieved from stored electrograms (EGM). Though many methods have been proposed for digital recovery of paper printed ECG, none has specifically addressed the intracardiac EGM, which are only available in black and white. Our aims were: (1) to propose an image processing algorithm suitable for recovering ICD stored EGM; (2) to evaluate its performance in different cardiac rhythms by using an adequate time synchronization processing for this application. An image processing algorithm was designed for recovering the signals from ICD paper printed EGM. EGM from simultaneously acquired tip-ring and can-coil ICD lead configurations were scanned. Tip-ring and can-coil recordings were automatically separated into two streams, and signal tracking was made for each stream. Recovered EGM were compared to their gold standard (ICD sampled and stored recordings). Time alignment of recovered and gold standard EGM was observed to be fundamental on the performance measurements, so that three different techniques (LS, spline, and matched filter) were benchmarked. Consistent lower performance was observed in tip-ring than in can-coil recovered EGM and performance was improved by LS alignment with respect to spline and matched filter. In conclusion, our algorithm allows to automatically recovering ICD EGM from paper printed recordings.