**Problem Statement**: In the field of ECG analysis, data comes in two forms: numerical arrays representing voltage measurements and visual representations of electrical activity as graphs. However, for tasks like prediction and analysis, we can only utilize one format at a time. This challenge specifically addresses this conversion process. You'll be presented with a dataset containing thousands of ECG graphs. Your objective is to develop an algorithm that can accurately translate these graphs, each containing 187 corresponding voltage data points, into the desired numerical voltage arrays. In essence, you'll be building a system that bridges the gap between the visual representation of heart activity (the ECG graph) and the underlying numerical data critical for further analysis.