Scholarlink

<p>Many studies have addressed the reformulation and preservation of sliced bread, yet the evaluation of its physical properties often demands standardized procedures and extensive manual labor. While advanced techniques such as electron microscopy and microtomography enable microscopic analysis of ingredient interactions, their high-cost limits accessibility. In contrast, digital image analysis provides a rapid and non-invasive alternative for extracting structural information. For this reason, in this study, an algorithm was developed to measure the color, size and morphology of the alveoli from the crumb structure of sliced bread images of two varieties (white and whole). Additionally, a cabin was designed to standardize environmental conditions to measure some variables (color and size), this cabin allows replicate the process to acquired image data. For color measurement, three models (Linear, Polynomial and Stacked Ensemble) were developed to predict CIELAB coordinates from red, green and blue coordinates. The Stacked Ensemble model obtained a coefficient of determination (R²) of 0.99 and smaller errors in the a* (1.29) and b* (1.57) coordinates. For size, an algorithm based on digital image processing reduced the measurement time by 80% with respect to the manual method, although the asymmetry of the samples generated significant differences in the measurement. Finally, nine variables were established to measure the morphological alveoli features. In this way, the user will not have to apply subjective data analysis techniques, and the algorithm represents a low-cost solution for measure some physicals properties for sliced bread products.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Analysis of physical properties in white and whole wheat sliced bread using digital image processing

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年8月8日

查看全文
  • Neiry-Dayán Martínez-Lara,
  • Claudia L. Garzón-Castro,
  • Annamaria Filomena-Ambrosio

摘要

Many studies have addressed the reformulation and preservation of sliced bread, yet the evaluation of its physical properties often demands standardized procedures and extensive manual labor. While advanced techniques such as electron microscopy and microtomography enable microscopic analysis of ingredient interactions, their high-cost limits accessibility. In contrast, digital image analysis provides a rapid and non-invasive alternative for extracting structural information. For this reason, in this study, an algorithm was developed to measure the color, size and morphology of the alveoli from the crumb structure of sliced bread images of two varieties (white and whole). Additionally, a cabin was designed to standardize environmental conditions to measure some variables (color and size), this cabin allows replicate the process to acquired image data. For color measurement, three models (Linear, Polynomial and Stacked Ensemble) were developed to predict CIELAB coordinates from red, green and blue coordinates. The Stacked Ensemble model obtained a coefficient of determination (R²) of 0.99 and smaller errors in the a* (1.29) and b* (1.57) coordinates. For size, an algorithm based on digital image processing reduced the measurement time by 80% with respect to the manual method, although the asymmetry of the samples generated significant differences in the measurement. Finally, nine variables were established to measure the morphological alveoli features. In this way, the user will not have to apply subjective data analysis techniques, and the algorithm represents a low-cost solution for measure some physicals properties for sliced bread products.