Corrugated board is widely used as an eco-friendly and robust material in the packaging sector. Ensuring the proper mechanical properties of such composite materials is crucial. Therefore, designing packaging made of corrugated board often involves various numerical techniques to analyze the mechanical behavior of the structure under specified loads. To expedite the process of creating digital models of corrugated board, this study introduces an algorithm that leverages image processing techniques.

The proposed algorithm consists of two stages. The first stage utilizes basic image processing methods to extract geometrical parameters of the corrugated board, including layer and overall board thickness, as well as flute height. It also determines the locations of the center lines of each layer. In the second stage, it is assumed that the flutes can be modeled as a sinusoidal function. An objective function is defined based on the sum of the distances between the points of the potential sinusoidal function and the corresponding points on the binary image obtained in the first stage.

This study compares the effectiveness of four metaheuristics—genetic algorithms, particle swarm optimization, simulated annealing, and surrogate optimization—in refining the sinusoidal model of the flutes. The algorithm was successfully applied to three- and five-layered corrugated boards, demonstrating its capability to accurately model the geometric structure and support the design of packaging with optimized mechanical properties.