Electrocardiograms (ECGs) as one of the most widely used tests for detecting cardiovascular issues. The electrocardiogram (ECG or EKG) is a diagnostic technique used for regular evaluation of the heart's electrical and muscular activities. Although the ECG test may seem relatively straightforward, extensive training is required to interpret ECG charts. Historically, the majority of ECG recordings were documented on paper. Manually reviewing and revaluating ECG paper records can be a tedious and challenging task. However, by digitizing these paper ECG recordings, we can automate the diagnosis and analysis process. The primary aim of this paper is to utilize ML techniques to convert paper ECG data into a one-dimensional signal. This objective can be achieved by employing diverse techniques to extract the P, QRS, and T waves from ECG readings, revealing the heart's electrical activity. The methods include dividing the original ECG report into 13 Leads, extracting, and converting the signal, smoothing, and then converting these binary pictures using threshold and scaling. To interpret the data, post-feature extraction and dimension reduction methods like Principal Component Analysis are used. The techniques include splitting the original ECG report into 13 Leads, extracting and converting into the signal, smoothing, and converting binary images using threshold and scaling. Post-feature extraction, and dimension reduction techniques like Principal Component Analysis are applied to understand the data. Several classifiers, including CNN, k-nearest neighbors (KNN), logistic regression, support vector machine (SVM), and a voting-based ensemble classifier, have been incorporated. The final selection of the model will be based on acceptable criteria such as accuracy, precision, recall, F1-score. This final model will aid in the diagnosing of cardiac diseases, to detect whether a patient has/had Myocardial Infarction, Abnormal Heartbeat, or the patient is hale and healthy by inferring the ECG reports.