IRO Journals
Journal of Trends in Computer Science and Smart Technology

A Symmetry-Aware Shape Descriptor Framework for Automated Defect Detection in Chocolate Images using Geometric Feature Engineering

Open Access
Published: 20 July, 2026
Pages: 728-744
  • 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. “A Symmetry-Aware Shape Descriptor Framework for Automated Defect Detection in Chocolate Images Using Geometric Feature Engineering”. Journal of Trends in Computer Science and Smart Technology 8 (3): 728-44. https://doi.org/10.36548/jtcsst.2026.3.015.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Chocolate Defect Detection
Shape Analysis
Symmetry-Aware Descriptors
Support Vector Machine (SVM)
Image Processing
Quality Inspection
Geometric Features

Abstract

In recent years, developments in food quality and safety regulations have placed greater importance on high-quality food production. Foods that are inspected for quality defects include chocolates that are susceptible to defects during their manufacturing process. Currently, there are various techniques for detecting defects in chocolates, but most focus on global properties of the shape of chocolates. In this study, a new technique called Symmetry Aware Shape Descriptor (SASD) approach was proposed for automatic defect detection in chocolates. This algorithm is composed of two descriptors; Symmetry Difference Index (SDI), which measures the global symmetry properties of a shape, and Symmetry Residual Descriptor (SRD), which measures the local asymmetry properties of the shape. After the extraction of these two descriptors, they form a feature vector, which is then classified using Support Vector Machine (SVM) Classifier. To perform a comparative analysis, classical shape-based approaches, basic shape features, Hu moments, and convex hull-based approaches were also implemented. The dataset used in this study consists of 225 chocolate images from 14 different chocolate brands. The suggested framework exhibited improved performance when compared to conventional methods, where the classification accuracy and precision achieved by this framework were 77.78% and 78.95%, respectively. These results show that the suggested SASD framework is an effective, transparent, and computationally efficient method for automated defect detection in chocolates.

References

  1. Xie, Xianghua. "A Review of Recent Advances in Surface Defect Detection Using Texture Analysis Techniques." ELCVIA: electronic letters on computer vision and image analysis (2008): 1-22.
  2. Cheng, Xu, Xin Jin, Zhijing Zhang, and Jun Lu. "A Geometrical Defect Detection Method for Non-Silicon MEMS Part Based on HU Moment Invariants of Skeleton Image." In Fifth International Conference on Graphic and Image Processing (ICGIP 2013), vol. 9069, SPIE, 2014, 340-344.
  3. Alam, Mehtab, Abdullah Alourani, Ashraf Ali, and Firoj Ahamad. "Symmetry-Aware Feature Representations and Model Optimization for Interpretable Machine Learning." Symmetry 17, no. 11 (2025): 1821.
  4. Saad, Norhashimah Mohd, Nor Nabilah Syazana Abdul Rahman, Abdul Rahim Abdullah, and Farhan Abdul Wahab. "Shape Defect Detection for Product Quality Inspection and Monitoring System." In 2017 4th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI), IEEE, 2017, 1-6.
  5. Donati, Luca, Eleonora Iotti, and Andrea Prati. "A Real-Time Approach for Automatic Food Quality Assessment Based on Shape Analysis." International Journal of Computational Intelligence and Applications 20, no. 03 (2021): 2150019.
  6. Jiang, Lili, Yunfei Wang, Haohao Yan, Yingzi Yin, and Chong Wu. "Strawberry Fruit Deformity Detection and Symmetry Quantification Using Deep Learning and Geometric Feature Analysis." Horticulturae 11, no. 6 (2025): 652.
  7. Sarkar, Tanmay, Alok Mukherjee, Kingshuk Chatterjee, Vladimir Ermolaev, Dmitry Piotrovsky, Kristina Vlasova, Mohammad Ali Shariati, Paulo ES Munekata, and Jose M. Lorenzo. "Edge Detection Aided Geometrical Shape Analysis of Indian Gooseberry (Phyllanthus Emblica) for Freshness Classification." Food Analytical Methods 15, no. 6 (2022): 1490-1507.
  8. Ji, Xuyuan, Hui Guo, and Minghong Hu. "Features Extraction and Classification of Wood Defect Based on HU Invariant Moment and Wavelet Moment and BP Neural Network." In Proceedings of the 12th International Symposium on Visual Information Communication and Interaction, 2019, 1-5.
  9. Negrete, Karla, Rhys Butler, Emily Wallis, Emily Magnani, Melissa Benzinger Mcglynn, Matthew McDonald, Nicolas J. Alvarez, and Maureen Tang. "Preventing Spread of the Invasive Spotted Lanternfly via Texture-Based Automated Egg Detection." Frontiers in Insect Science 6 (2026): 1678964.
  10. Shen, Yi, Wensheng Wang, Xuanyu Luo, Feiyu Zou, and Zhen Yin. "Corn Kernel Segmentation and Damage Detection Using a Hybrid Watershed–Convex Hull Approach." Foods 15, no. 2 (2026): 404.
  11. Lv, Lanlan, Zhaohui Zheng, Jingshen Xu, Hanyu Fu, Liuyang Ren, Pei Yang, Weijun Xie, and Deyong Yang. "Research on Trimming Path for Forked Carrots Using Contour‐Based Machine Learning Methods." Journal of Food Process Engineering 47, no. 1 (2024): e14527.
  12. Rani, Anju, Daniel Ortiz-Arroyo, and Petar Durdevic. "Advancements in Point Cloud-Based 3D Defect Classification and Segmentation for Industrial Systems: A Comprehensive Survey." Information Fusion 112 (2024): 102575.
  13. Ha, Hyunwoo, and Kwanghee Ko. "A Method for Image-Based Shadow Interaction with Virtual Objects." Journal of Computational Design and Engineering 2, no. 1 (2015): 26-37.
  14. Qin, Tao, Zhaoli Liu, Pinghui Wang, Shancang Li, Xiaohong Guan, and Lixin Gao. "Symmetry Degree Measurement and Its Applications to Anomaly Detection." IEEE transactions on information forensics and security 15 (2019): 1040-1055.
  15. Tao, K. Mike. "A Closer Look at the Radial Basis Function (RBF) Networks." In Proceedings of 27th Asilomar conference on signals, systems and computers, IEEE, 1993, 401-405.
  16. Hossin, Mohammad, and Md Nasir Sulaiman. "A Review on Evaluation Metrics for Data Classification Evaluations." International journal of data mining & knowledge management process 5, no. 2 (2015): 01–11.
  17. Meyes, Richard, Melanie Lu, Constantin Waubert De Puiseau, and Tobias Meisen. "Ablation Studies in Artificial Neural Networks." arXiv preprint arXiv:1901.08644 (2019).
  18. Sheikholeslami, Sina, Moritz Meister, Tianze Wang, Amir H. Payberah, Vladimir Vlassov, and Jim Dowling. "Autoablation: Automated Parallel Ablation Studies for Deep Learning." In Proceedings of the 1st Workshop on Machine Learning and Systems, pp. 55-61. 2021.
  19. Soe, Yan Naung, Paulus Insap Santosa, and Rudy Hartanto. "Software Defect Prediction Using Random Forest Algorithm." In 2018 12th South East Asian Technical University Consortium (SEATUC), vol. 1, IEEE, 2018, 1-5.
  20. Hemamalini, V., S. Rajarajeswari, S. Nachiyappan, M. Sambath, T. Devi, Bhupesh Kumar Singh, and Abhishek Raghuvanshi. "Food Quality Inspection and Grading Using Efficient Image Segmentation and Machine Learning‐Based System." Journal of Food Quality 2022, no. 1 (2022): 5262294.
  21. Tang, Rui, Ting Yu, Zi Li, Junru Wu, Xiaoming Zheng, Leiqing Pan, Yang Chen, Kun Duan, Hui Dong, and Weijie Lan. "Infrared Spectroscopy Combined with Deep Learning to Describe the Textural Properties of Cooked Rice from Raw Materials: Revealing Spectral Variations and Internal Correlations During Processing." Food Control 180 (2026): 111681.
  22. Jackman, Patrick, and Da-Wen Sun. "Recent Advances in Image Processing Using Image Texture Features for Food Quality Assessment." Trends in food science & technology 29, no. 1 (2013): 35-43.