Wound Depth Measurement System in Forensic Cases using Image Processing and Machine Learning
DOI:
https://doi.org/10.31961/eltikom.v9i2.1636Keywords:
HSV, image processing, LAB, support vector machine, woundAbstract
Accurate evaluation of wound depth is crucial in forensic investigations, as it significantly affects case assessments and outcomes. This study introduces a method for classifying wound depth using a Support Vector Machine (SVM) model and compares its performance with Decision Tree and Logistic Regression models. The classification was based on color features extracted from HSV and LAB color spaces. The da-taset consisted of 76 images categorized into three stages: stage 2 (36 images), stage 3 (12 images), and stage 4 (28 images). Model performance was evaluated using confusion matrices, precision, recall, and F1-score. The SVM model achieved an overall accuracy of 85%, demonstrating higher precision and re-call across all stages compared to the Decision Tree and Logistic Regression models, which achieved 50% and 70%, respectively. The results indicate that the SVM model performed particularly well in distinguish-ing stage 2 wounds, although differentiating between stages 3 and 4 remained challenging. Overall, the proposed system shows potential to enhance the accuracy and efficiency of forensic wound evaluation by providing a rapid and objective classification tool. However, as the system was tested on a limited dataset under controlled conditions, further research should expand the dataset, incorporate additional features, and explore other machine learning algorithms to improve robustness and applicability in real forensic contexts.
Downloads
References
[1] R. Sumino, Adriano, and B. Pramono, “Medicolegal Aspects of Visum Et Repertum in Sexual Violence Criminal Cases,” jirpl, vol. 5, no. 1, pp. 88–98, Oct. 2023, doi: 10.56371/jirpl.v5i1.166.
[2] M. H. Wardhana, B. Hussin, A. S. Bin Hasan Basari, and D. Afandi, “Enhanced degree of injury classification model: determination critical indicator and criteria degree of injury from Visum et Repertum (Ver) in Pekanbaru, Indonesia,” Egypt J Forensic Sci, vol. 8, no. 1, p. 36, Dec. 2018, doi: 10.1186/s41935-018-0066-6.
[3] L. Wunsch, C. G. Tenorio, K. Anding, A. Golomoz, and G. Notni, “Data Fusion of RGB and Depth Data with Image Enhancement,” J. Imaging, vol. 10, no. 3, p. 73, Mar. 2024, doi: 10.3390/jimaging10030073.
[4] S. Suyoko, “Literatur Review Kualitas Visum et Repertum dalam Mendukung Penegakan Hukum di Indonesia,” INOHIM, vol. 10, no. 2, pp. 73–84, Dec. 2022, doi: 10.47007/inohim.v10i2.391.
[5] B. Rostami, D. M. Anisuzzaman, C. Wang, S. Gopalakrishnan, J. Niezgoda, and Z. Yu, “Multiclass wound image classification using an ensemble deep CNN-based classifier,” Computers in Biology and Medicine, vol. 134, p. 104536, Jul. 2021, doi: 10.1016/j.compbiomed.2021.104536.
[6] H. Mohafez, S. A. Ahmad, S. Ahmad Roohi, and M. Hadizadeh, “Wound Healing Assessment Using Digital Photography: A Review,” JBEMi, vol. 4, no. 5, Oct. 2016, doi: 10.14738/jbemi.35.2203.
[7] C. Liu, X. Fan, Z. Guo, Z. Mo, E. I.-C. Chang, and Y. Xu, “Wound area measurement with 3D transformation and smartphone images.,” BMC Bioinformatics, vol. 20, no. 1, p. 724, Dec. 2019, doi: 10.1186/s12859-019-3308-1.
[8] N. Zimmermann, T. Sieberth, and A. Dobay, “Automated wound segmentation and classification of seven common injuries in forensic medicine.,” Forensic Sci Med Pathol, vol. 20, no. 2, pp. 443–451, Jun. 2024, doi: 10.1007/s12024-023-00668-5.
[9] H. Carrión, M. Jafari, M. D. Bagood, H. Yang, R. R. Isseroff, and M. Gomez, “Automatic wound detection and size estimation using deep learning algorithms,” PLoS Comput Biol, vol. 18, no. 3, p. e1009852, Mar. 2022, doi: 10.1371/journal.pcbi.1009852.
[10] L. Dang et al., “Novel Prediction Method Applied to Wound Age Estimation: Developing a Stacking Ensemble Model to Improve Predictive Performance Based on Multi-mRNA,” Diagnostics, vol. 13, no. 3, p. 395, Jan. 2023, doi: 10.3390/diagnostics13030395.
[11] C. Zhao, Y. Guo, L. Li, and M. Yang, “Non-invasive techniques for wound assessment: A comprehensive review.,” Int Wound J, vol. 21, no. 11, p. e70109, Nov. 2024, doi: 10.1111/iwj.70109.
[12] D. Griffa et al., “Artificial Intelligence in Wound Care: A Narrative Review of the Currently Available Mobile Apps for Automatic Ulcer Segmentation,” Oct. 16, 2024. doi: 10.20944/preprints202410.1244.v1.
[13] B. Zorić, D. Bajer, and M. Dudjak, “Feature extraction procedures for chronic wound tissue classification,” in 2024 Zooming Innovation in Consumer Technologies Conference (ZINC), May 2024, pp. 1–6. doi: 10.1109/ZINC61849.2024.10579393.
[14] M. A. Khan and M. A. AlGhamdi, “An intelligent and fast system for detection of grape diseases in RGB, grayscale, YCbCr, HSV and L*a*b* color spaces,” Multimedia Tools and Applications, vol. 83, no. 17, pp. 50381–50399, May 2024, doi: 10.1007/s11042-023-17446-8.
[15] E. Wahyuni, A. Putri, N. Pelu, Firdaus, and I. Wiraagni, “Image Processing-Based Application for Determining Wound Types in Forensic Medical Cases,” Jurnal Nasional Teknik Elektro, pp. 12–19, Mar. 2024, doi: 10.25077/jnte.v13n1.1148.2024.
[16] I. A. Wiraagni et al., “An Application for Wound Type Determination Based on Image Processing in Forensic Cases,” International Journal of Medical Toxicology & Forensic Medicine, vol. 14, no. 2, pp. 1–8, 2024, doi: https:/doi.org/10.32598/ijmtfm.v14i2.43899.
[17] A. Anaya-Isaza, L. Mera-Jiménez, and M. Zequera-Diaz, “An overview of deep learning in medical imaging,” Informatics in Medicine Unlocked, vol. 26, p. 100723, 2021, doi: 10.1016/j.imu.2021.100723.
[18] R. Zhang, D. Tian, D. Xu, W. Qian, and Y. Yao, “A Survey of Wound Image Analysis Using Deep Learning: Classification, Detection, and Segmentation,” IEEE Access, vol. 10, pp. 1–1, Jan. 2022, doi: 10.1109/ACCESS.2022.3194529.
[19] D. Bora, A. Gupta, and F. Khan, “Comparing the Performance of L*A*B* and HSV Color Spaces with Respect to Color Image Segmentation,” Jun. 2015.
[20] F. Ferreira et al., “A Systematic Investigation of Models for Color Image Processing in Wound Size Estimation,” Computers, vol. 10, no. 4, p. 43, Apr. 2021, doi: 10.3390/computers10040043.
[21] T. Wu, X. Gu, J. Shao, R. Zhou, and Z. Li, “Color image segmentation based on a convex K-means approach,” Mar. 17, 2021, arXiv: arXiv:2103.09565. doi: 10.48550/arXiv.2103.09565.
[22] S. R. H. Zaidi and S. Sharma, “Pressure Ulcer,” StatPearls Publishing, 2024, [Online]. Available: https://www.ncbi.nlm.nih.gov/books/NBK553107/
[23] M. Alauthman et al., “Enhancing Small Medical Dataset Classification Performance Using GAN,” Informatics, vol. 10, no. 1, p. 28, Mar. 2023, doi: 10.3390/informatics10010028.
[24] K. B. Shaik, P. Ganesan, V. Kalist, B. S. Sathish, and J. M. M. Jenitha, “Comparative Study of Skin Color Detection and Segmentation in HSV and YCbCr Color Space,” Procedia Computer Science, vol. 57, pp. 41–48, 2015, doi: 10.1016/j.procs.2015.07.362.
[25] F. Jaison, V. K. Pandey, and A. Bishnoi, “Developing Support Vector Machines for Accurate Medical Image Analysis,” in 2024 International Conference on Optimization Computing and Wireless Communication (ICOCWC), Jan. 2024, pp. 1–7. doi: 10.1109/ICOCWC60930.2024.10470551.
[26] N. Panda, “A Review on Logistic Regression in Medical Research,” National Journal of Community Medicine, vol. 13, pp. 265–270, Apr. 2022, doi: 10.55489/njcm.134202222.
[27] A. Amro, M. Al-Akhras, K. E. Hindi, M. Habib, and B. A. Shawar, “Instance Reduction for Avoiding Overfitting in Decision Trees,” Journal of Intelligent Systems, vol. 30, no. 1, pp. 438–459, Jan. 2021, doi: 10.1515/jisys-2020-0061.
[28] S. Swaminathan and B. R. Tantri, “Confusion Matrix-Based Performance Evaluation Metrics,” African Journal of Biomedical Research, vol. 27, pp. 4023–4031, Nov. 2024, doi: 10.53555/AJBR.v27i4S.4345.
[29] S. K and E. B, “Wound Image Analysis Classifier for Efficient Tracking of Wound Healing Status,” Signal & Image Processing : An International Journal, vol. 5, pp. 15–27, Apr. 2014, doi: 10.5121/sipij.2014.5202.
[30] M. Reiter, R. Donner, G. Langs, and H. Bischof, “Estimation of Face Depth Maps from Color Textures using Canonical Correlation Analysis,” vol. 24, pp. 308–312, 2011, doi: 10.1016/j.proeng.2011.11.2647.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Elvira Sukma Wahyuni, Kern Cesarean Ahnaf, Firdaus Firdaus, Nurul Ashikin Abdul-Kadir, Nor Aini Zakaria, Idha Arfianti Wiraagni, Diwangkoro Aji Kadarmo
This work is licensed under a Creative Commons Attribution 4.0 International License.
All accepted papers will be published under a Creative Commons Attribution 4.0 International (CC BY 4.0) License. Authors retain copyright and grant the journal right of first publication. CC-BY Licenced means lets others to Share (copy and redistribute the material in any medium or format) and Adapt (remix, transform, and build upon the material for any purpose, even commercially).
