Matching method for mutated veneer sheet images using gray-level co-occurrence matrix features

Abstract This paper studies the tracking of wooden veneer sheets by matching their respective wet and dry colour images. The has proved to be a challenging task due random mutations during processing in terms color changes, emergence defects, and, occasionally, lost pieces surface. proposed procedure involves image segmentation with five different sizes, followed segment-wise extraction Gray Level Co-occurrence Matrix (GLCM) textural feature arrays, similarity comparisons respectively. A voting mechanism is introduced that allocates correct match based on majority. An optional shifting applied candidates missing areas. method demonstrated benchmarked using real-world dataset sourced from industry, comprising 2579 high-quality images spruce pairs obtained peeling drying. In comparison earlier employed randomized 50 pair sampling same dataset, our approach yields accuracy 99.41%, outperforming previously reported 84.93%. These findings have relevance for researchers wood analytics carry practical implications large-scale, automated production facilities seeking innovative ways optimize raw material usage.