This project focuses on automating the analysis of GEM efficiency plots by leveraging OpenCV and machine learning techniques, replacing the time-consuming and error-prone manual inspection process. In the current workflow, efficiency plots generated from each run are manually assessed to evaluate performance. To address this, we propose developing a robust Python-based framework that automates image comparison using well-defined metrics. The implementation involves reading efficiency plot images, extracting and analyzing key features, and optimizing the process for precision and scalability. The system applies predefined acceptance criteria to evaluate the plots, determining whether GEM events meet the required efficiency thresholds. By automating this workflow, the solution not only accelerates the evaluation process but also enhances accuracy, consistency, and reliability in assessing GEM efficiency, ultimately contributing to more efficient data processing and decision-making.