Abstract Efficient utilization of materials in industrial processes is a significant challenge, particularly in furniture manufacturing, sheet metal cutting, and other sectors requiring precise material cutting and packing. However, existing approaches often struggle to achieve both high efficiency and compactness in the arrangement of irregularly shaped 2D components, leading to significant material waste and suboptimal layout solutions. To address this issue, this study introduces a novel methodology that integrates advanced image processing and computational intelligence to optimize the arrangement of irregularly shaped components on fixed boards. Employing normalized two-dimensional cross-correlation for enhanced template matching, our approach not only improves material utilization but also enhances packing efficiency by reducing gaps between components. The developed method involves several key steps, including the cropping of cross-correlation matrices and strategic pattern placement, which are critical for achieving a highly compact and computationally efficient arrangement. Experimental results demonstrate that our approach significantly enhances both material conservation and computational efficiency compared to traditional methods, ensuring a more optimized and automated packing process. Our findings provide a practical and scalable solution bridging the gap between theoretical research and industrial applications. This research contributes to advancing computational efficiency, reducing material waste, and optimizing spatial utilization in industrial cutting and packing scenarios.