The manufacturing industry has transformed significantly with the advent of advanced technologies such as Additive Manufacturing (AM), commonly known as 3D printing. AM enables intricate geometries, reduces the need for component joints, and facilitates design customization. However, its widespread adoption is limited by technical challenges, notably the precise control required over process parameters like temperature, laser power, speed, and material feed rates. This thesis introduces a novel Direct Image-to-Control Methodology (DItC) to enhance control accuracy and efficiency across various manufacturing processes, including but not limited to AM. The primary objective of this research is to integrate vision-based feedback directly into control systems using data-driven control techniques, specifically Data-enabled Predictive Control (DeePC). This approach is expected to address the lack of real-time feedback control in AM, crucial for ensuring consistent product quality and managing dynamic thermal conditions. A comprehensive literature review critically evaluates existing control methodologies in Additive Manufacturing, highlighting their strengths and limitations and identifying gaps that the proposed DItC aims to fill. The motivation for DItC is discussed, along with its potential to revolutionize manufacturing by enabling real-time adjustments based on visual data. Despite the inspiration from AM, due to the non-existence of their models and the need for methodology development in validating DItC feasibility, the work incorporated a thermoforming process model outlined in the methodology section. Mathematical tools and techniques used for visualizing control dynamics within image spaces are also shown. Results from implementing DItC demonstrate its feasibility in following certain heat distributions, and the findings are interpreted in the following discussion chapter. This thesis concludes with current limitations and proposed future directions. This research establishes a foundational framework for DItC, offering insights into the potential benefits and challenges of implementing data-driven control strategies across the manufacturing industry. By continuing to refine models, methodologies, and interpretations, this work aims to enable and simplify vision-based feedback control in advanced manufacturing, paving the way for broader industrial adoption.