EUVIMEDEUVIMED entdecken
Crossref

Region-Specific Adaptive GLCM Framework for Surface Scratch Detection in Heterogeneous Chocolate Products

Ruth Moly Benjamin, Abraham Chandy D., Hepzibah Christinal A.

Journal of Innovative Image Processing · 16.07.2026 · 8 (3) · 1000-1021

DOI: 10.36548/jiip.2026.3.013 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Innovative Image Processing, online erschienen am 16.07.2026. Verfasst von Ruth Moly Benjamin und 2 weiteren Autor:innen. Die Arbeit nennt 18 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automated defect detection on the surface of chocolate products is one of the most important techniques that must be used to ensure the quality and consistency of chocolate products during their manufacturing processes. However, due to the variation in the shapes, textures, and reflectivity of different brands of chocolates, this process can become difficult. To address this issue, a region-based adaptive GLCM approach is proposed for the analysis of textures on the surface of chocolates. Local variance analysis is carried out to segment the images into texture homogeneous regions. Following feature extraction, Principal Component Analysis (PCA)-based transformation is performed for feature transformation and then classified using a Support Vector Machine (SVM). A dataset consisting of 233 original chocolate images from 14 commercial brands, together with augmented training samples, was used to evaluate the proposed framework. The proposed method demonstrated an accuracy of 93.59%, recall of 96.15%, precision of 86.21%, F1-score of 90.91%, and AUC of 97.78% during the multi-brand evaluation. Leave-One-Brand-Out validation results achieved a mean recall of 93.42%, demonstrating its robustness in cross-brand defect detection. The proposed framework provides reliable automated chocolate scratch defect detection while maintaining low computational complexity and high interpretability.

Zitieren

APA

Benjamin, R. M., D., A. C., & A., H. C. (2026). Region-Specific Adaptive GLCM Framework for Surface Scratch Detection in Heterogeneous Chocolate Products. Journal of Innovative Image Processing, 8(3), 1000-1021. https://doi.org/10.36548/jiip.2026.3.013

Vancouver

Benjamin RM, D. AC, A. HC. Region-Specific Adaptive GLCM Framework for Surface Scratch Detection in Heterogeneous Chocolate Products. Journal of Innovative Image Processing. 2026;8(3):1000-1021. doi:10.36548/jiip.2026.3.013

BibTeX
@article{Benjamin2026,
  author = {Benjamin, Ruth Moly and D., Abraham Chandy and A., Hepzibah Christinal},
  title = {Region-Specific Adaptive GLCM Framework for Surface Scratch Detection in Heterogeneous Chocolate Products},
  journal = {Journal of Innovative Image Processing},
  year = {2026},
  volume = {8},
  number = {3},
  pages = {1000--1021},
  doi = {10.36548/jiip.2026.3.013}
}
Kostenlos starten →