Non-destructive Evaluation of Bread Staling Using Gray Level Co-occurrence Matrices

Abstract

The potential application of image texture processing for non-destructive evaluation of bread staling was investigated by monitoring the changes in gray level co-occurrence matrix (GLCM) features (energy, contrast, homogeneity, correlation, and entropy) of baguette bread over a 5-day storage period. Energy experienced a significant reduction after 2 days of storage and increased significantly afterwards. However, contrast tended to increase dramatically over the entire storage time. While homogeneity and correlation showed a decreasing trend during the storage period, no meaningful trend was observed for changes of entropy. The GLCM texture features contrast, homogeneity, and correlation showed high correlations with the instrumental texture parameters and physicochemical properties of the bread during storage; in fact, the breads with firmer and less springy crumbs and higher crust moisture contents (the stale breads) had noticeably higher contrast and lower homogeneity and correlation values compared to the freshly baked samples. The results suggested that the GLCM texture features are promising indices for non-destructively assessing bread staling progress.