IRO Journals
Journal of Innovative Image Processing

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

Open Access
Published: 16 July, 2026
Pages: 1000-1021
  • Ruth Moly Benjamin , Ruth Moly Benjamin
    Department of Electronics and Communication Engineering, Karunya Institute of Technology and Sciences, Coimbatore, India
    Department of Electronics and Communication Engineering, Karunya Institute of Technology and Sciences, Coimbatore, India
  • Abraham Chandy D. , Abraham Chandy D.
    Department of Electronics and Communication Engineering, Karunya Institute of Technology and Sciences, Coimbatore, India
    Department of Electronics and Communication Engineering, Karunya Institute of Technology and Sciences, Coimbatore, India
  • Hepzibah Christinal A. Hepzibah Christinal A.
    Department of Computer Science and Engineering, Karunya Institute of Technology and Sciences, Coimbatore, India
    Department of Computer Science and Engineering, Karunya Institute of Technology and Sciences, Coimbatore, India
view PDF
view PDF

How to Cite

Benjamin, Ruth Moly, Abraham Chandy D., and Hepzibah Christinal A. 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.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Adaptive Feature Extraction
Chocolate Defect Detection
Gray-Level Co-occurrence Matrix (GLCM)
Region-wise Segmentation
Support Vector Machine (SVM)

Abstract

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.

References

  1. Singh, Shruti, Divya Srivastava, and Suneeta Agarwal. "GLCM and its Application in Pattern Recognition." In 2017 5th International Symposium on Computational and Business Intelligence (ISCBI), IEEE, 2017, 20-25.
  2. Olaniyi, Ebenezer O., Adefemi A. Adekunle, Temitope Odekuoye, and Adnan Khashman. "Automatic System for Grading Banana using GLCM Texture Feature Extraction and Neural Network Arbitrations." Journal of food process engineering 40, no. 6 (2017): e12575.
  3. Nyasulu, Chimango, Awa Diattara, Assitan Traore, Cheikh Ba, Papa Madiallacké Diedhiou, Yakhya Sy, Hind Raki, and Diego Hernán Peluffo-Ordóñez. "A Comparative Study of Machine Learning-Based Classification of Tomato Fungal Diseases: Application of GLCM Texture Features." Heliyon 9, no. 11 (2023).
  4. Setiaji, Pratomo, Kusworo Adi, and Bayu Surarso. "Development of Classification Method for Determining Chicken Egg Quality Using GLCM-CNN Method." Ingenierie des Systemes d'Information 29, no. 2 (2024): 397.
  5. Benco, Miroslav, Robert Hudec, Patrik Kamencay, Martina Zachariasova, and Slavomir Matuska. "An Advanced Approach to Extraction of Colour Texture Features Based on GLCM." International Journal of Advanced Robotic Systems 11, no. 7 (2014): 104.
  6. Nielsen, Birgitte, Fritz Albregtsen, and Håvard E. Danielsen. "Low Dimensional Adaptive Texture Feature Vectors from Class Distance and Class Difference Matrices." IEEE transactions on medical imaging 23, no. 1 (2004): 73-84.
  7. Kumar, Chandan, Siddharth Chauhan, and R. Narmadha Alla. "Classifications of Citrus Fruit using Image Processing-GLCM Parameters." In 2015 International Conference on Communications and Signal Processing (ICCSP), IEEE, 2015, 1743-1747.
  8. Barburiceanu, Stefania, Romulus Terebes, and Serban Meza. "3D Texture Feature Extraction and Classification using GLCM and LBP-Based Descriptors." Applied Sciences 11, no. 5 (2021): 2332.
  9. Zhang, Shu, Jinru Wu, Enze Shi, Sigang Yu, Yongfeng Gao, Lihong Connie Li, Licheng Ryan Kuo, Marc Jason Pomeroy, and Zhengrong Jerome Liang. "MM-GLCM-CNN: A Multi-Scale and Multi-Level Based GLCM-CNN for Polyp Classification." Computerized Medical Imaging and Graphics 108 (2023): 102257.
  10. Rampun, Andrik, Harry Strange, and Reyer Zwiggelaar. "Texture Segmentation using Different Orientations of GLCM Features." In Proceedings of the 6th international conference on computer vision/computer graphics collaboration techniques and applications, 2013, 1-8.
  11. Gustian, Dinda Aulia, Nur Laelatul Rohmah, Guruh Fajar Shidik, Ahmad Zainul Fanani, and Ricardus Anggi Pramunendar. "Classification of Troso Fabric using SVM-RBF Multi-Class Method with GLCM and PCA Feature Extraction." In 2019 International seminar on application for technology of information and communication (iSemantic), IEEE, 2019, 7-11.
  12. Preethi, G., and V. Sornagopal. "MRI Image Classification using GLCM Texture Features." In 2014 international conference on green computing communication and electrical engineering (ICGCCEE), IEEE, 2014, 1-6.
  13. Rafi, Mudassir, and Susanta Mukhopadhyay. "Texture Description using Multi-Scale Morphological GLCM." Multimedia Tools and Applications 77, no. 23 (2018): 30505-30532.
  14. Mu'jizah, Hanimatim, and Dian Candra Rini Novitasari. "Comparison of The Histogram of Oriented Gradient, GLCM, and Shape Feature Extraction Methods for Breast Cancer Classification Using SVM." Jurnal Teknologi dan Sistem Komputer 9, no. 3 (2021): 150-156.
  15. Malegori, Cristina, Laura Franzetti, Riccardo Guidetti, Ernestina Casiraghi, and Riccardo Rossi. "GLCM, An Image Analysis Technique for Early Detection of Biofilm." Journal of Food Engineering 185 (2016): 48-55.
  16. Ali, Syed Sumera Ershad, and Sayyad Ajij Dildar. "An Efficient Quality Inspection of Food Products using Neural Network Classification." Journal of Intelligent Systems 29, no. 1 (2019): 1425-1440.
  17. Zhang, Lei, Junfeng Jing, and Hongwei Zhang. "Fabric Defect Classification Based on LBP and GLCM." Journal of Fiber Bioengineering and Informatics 8, no. 1 (2015): 81-89.
  18. Kabir, Masud, Fatih Unal, Tahir Cetin Akinci, Alfredo A. Martinez-Morales, and Sami Ekici. "Revealing GLCM Metric Variations Across a Plant Disease Dataset: A Comprehensive Examination and Future Prospects for Enhanced Deep Learning Applications." Electronics 13, no. 12 (2024): 2299.