Sualtı Görüntülerinin Analizi için Hibrit Renk Uzayı ve GLCM Özellik Çıkarım Tabanlı Sınıflandırma Yöntemi

Year 2025, Volume: 13 Issue: 4, 1676 - 1694, 30.10.2025

Nafiye Nur Apaydın , Gülşah Karaduman , Orhan Yaman

https://doi.org/10.29130/dubited.1651026

Abstract

İnsan yapımı balık ağlarının su altında unutulması, kaybolması durumlarında bu ağlara hayalet ağ denilmektedir. Bu hayalet ağlar zamanla su altı ekosistemini tehdit ederek su altında yaşayan canlıların biyolojik çeşitliliğini azaltmaktadır. Bu nedenle su altındaki hayalet ağların tespiti için çalışmalar yapılmaktadır. Bu çalışmada su altında ağ, çöp, ROV ve biyolojik canlı sınıflarını tespit edebilmek için SODD ve Trash Icra veri setleri kullanılmıştır. Her sınıf için GLCM filtresi ile HSV, YUV, LAB ve RGB renk uzayları kullanılarak öznitelikler çıkarılmıştır. Çıkarılan bu öz nitelikler Random Forest Sınıflandırma Algoritmasıyla eğitilerek sonuçlar elde edilmiştir. Eğitim sonucunda her renk uzayının kendi başına düşük doğruluk değerine sahip olsa da birlikte kullanıldığında performansı iyi yönde etkileyerek doğruluğu arttırdığı ve en iyi doğruluk değerinin %89.16 ile önerilen yöntemde (HSV + YUV + LAB + RGB + GLCM) olduğu görülmüştür. Ayrıca en iyi durum olan tüm renk uzaylarının kullanıldığı durum için Naive Bayes, KNN ve SVM sınıflandırma algoritmaları da uygulanarak sonuçları önerilen yöntem olan Random Forest Classification ile karşılaştırılmıştır. Naive Bayes ile %52, KNN ile %62.17 ve SVM ile %73.67 doğruluk (accuracy) değerleri elde edilmiş ve en iyi yöntemin önerilen yöntem olan Random Forest Classification algoritmasıyla olduğu kanıtlanmıştır.

Keywords

SODD ve Trash Icra veri seti , GLCM filtresi , HSV , RGB , YUV , LAB renk uzayları

Hybrid Color Space and GLCM Feature Extraction Based Classification Method for Underwater Image Analysis

Abstract

In cases where man-made fishing nets are forgotten or lost underwater, these nets are called ghost nets. These ghost nets threaten the underwater ecosystem over time and reduce the biodiversity of living creatures underwater. For this reason, studies are being carried out to detect ghost nets underwater. In this study, SODD and Trash Icra data sets were used to detect net, trash, ROV and biological creature classes underwater. For each class, features were extracted using the GLCM filter and HSV, YUV, LAB and RGB color spaces. The extracted features were trained with the Random Forest Classification Algorithm and the results were obtained. As a result of the training, it was seen that although each color space had a low accuracy value on its own, when used together, it affected the performance positively and increased the accuracy, and the best accuracy value was 89.16% in the proposed method (HSV + YUV + LAB + RGB + GLCM). In addition, for the best case where all color spaces were used, Naive Bayes(NB), KNN and SVM classification algorithms were applied and the results were compared with the proposed method, Random Forest Classification. Accuracy values of 52% with NB, 62.17% with KNN and 73.67% with SVM were obtained and it was proven that the best method was the proposed method, Random Forest Classification algorithm. The results of the study demonstrate the effectiveness of integrating multi-color space features with texture analysis for underwater object classification, offering a promising approach for ghost net detection in real-world scenarios. Ghost nets, which are abandoned or lost man-made fishing nets, pose a significant threat to the marine ecosystem by entangling and endangering underwater life.

Keywords

GLCM filter , HSV , RGB , YUV , LAB Color Spaces

Ethical Statement

This study does not involve human or animal participants. All procedures followed scientific and ethical principles, and all referenced studies are appropriately cited

References

• Akbulut, H., Atasever, S., & Sıramkaya, E. (2025). Makine öğrenmesine dayalı portakal kalite sınıflandırması: Puma optimize edici ile bir hiperparametre optimizasyon yaklaşımı. In 7th International Conference on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA). (pp. 1–5). https://doi.org/10.1109/ICHORA65333.2025.11017028
• Al-Tairi, Z. H., Rahmat, R. W., Saripan, M. I., & Sulaiman, P. S. (2014). Skin segmentation using YUV and RGB color spaces. Journal of Information Processing Systems. 10(2), 283–299. https://doi.org/10.3745/JIPS.02.0002
• Apaydın, N. N., Apaydın, M.,& Yaman, O. (2022). Su altı görüntülerinden adli delil tespiti için LBP tabanlı sınıflandırma yöntemi. Fırat Üniversitesi Uzay ve Savunma Teknolojileri Dergisi. 1(1), 272-276.
• Belgiu, M., & Drăguţ, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing. 114, 24–31. https://doi.org/10.1016/j.isprsjprs.2016.01.011
• Character, L., Ortiz, A., Jr., Beach, T., & Luzzadder-Beach, S. (2021). Archaeologic machine learning for shipwreck detection using LiDAR and sonar. Remote Sensing. 13(9), Article 1759. https://doi.org/10.3390/rs13091759
• De Langis, K., Fulton, M., & Sattar, J. (2020). An analysis of deep object detectors for diver detection. arXiv. https://doi.org/10.48550/arXiv.2012.05701
• Demir, K., & Yaman, O. (2024a). A HOG feature extractor and KNN-based method for underwater image classification. Fırat University Journal of Experimental and Computational Engineering (FUJECE). 3(1), 1–10. https://doi.org/10.62520/fujece.1443818
• Demir, K., & Yaman, O. (2024b). Projector deep feature extraction-based garbage image classification model using underwater images. Multimedia Tools and Applications. 83(33), 79437–79451. https://doi.org/10.1007/s11042-024-18731-w
• Fulton, M. S., Hong, J., & Sattar, J. (2020). Trash-ICRA19: A bounding box labeled dataset of underwater trash [Data set]. Data Repository for the University of Minnesota (DRUM). https://doi.org/10.13020/x0qn-y082
• Han, F., Yao, J., Zhu, H., & Wang, C. (2020). Underwater image processing and object detection based on deep CNN method. Journal of Sensors. 2020, 1–20. https://doi.org/10.1155/2020/6707328
• Imam, H. M. A., Basso, E. A., Hoff, S. A., Rexha, H., Lafond, S., & Iancu, B. (2023, November 30). SODD – subaquatic object detection dataset [Data set]. Zenodo. https://doi.org/10.5281/zenodo.10230328
• Kim, J., Kim, T., Kim, J., Rho, S., Song, Y., & Yu, S.-C. (2019a). Simulation and feasibility test of mini-ROVs with AUV for the manipulation purpose. OCEANS 2019 MTS/IEEE SEATTLE. (pp. 1–6). https://doi.org/10.23919/OCEANS40490.2019.8962810
• Kim, J., Kim, T., Kim, J., Yu, S.-C., & Kim, T. (2019b). Manipulation purpose underwater agent vehicle for ghost net recovery mission. 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). (pp. 3905–3910). https://doi.org/10.1109/IROS40897.2019.8967625
• Mohanaiah, P., Sathyanarayana, P., & GuruKumar, L. (2013). Image texture feature extraction using GLCM approach. International Journal of Scientific and Research Publications. Volume 3, Issue 5, May 2013 1, ISSN 2250-3153
• Morishige, C., & McElwee, K. (2012). At-sea detection of derelict fishing gear in the North Pacific: An overview. Marine Pollution Bulletin. 65(1–3), 1–6. https://doi.org/10.1016/j.marpolbul.2011.05.011
• Raveendran, S., Patil, M. D., & Birajdar, G. K. (2021). Underwater image enhancement: A comprehensive review, recent trends, challenges and applications. Artificial Intelligence Review. 54(7), 5413–5467. https://doi.org/10.1007/s10462-021-10025-z
• Rijkure, A., & Megnis, J. (2024). Technical methods of cleaning shipwrecks from ghost nets. Environmental and Technology Resources: Proceedings of the International Scientific and Practical Conference.( Vol. 3, pp. 253–256). https://doi.org/10.17770/etr2024vol3.8160
• Shaik, K. B., Ganesan, P., Kalist, V., Sathish, B. S., & Jenitha, J. M. M. (2015). Comparative study of skin color detection and segmentation in HSV and YCbCr color space. Procedia Computer Science. 57, 41–48. https://doi.org/10.1016/j.procs.2015.07.362
• Spirkovski, Z., Ilik-Boeva, D., Ritterbusch, D., Peveling, R., & Pietrock, M. (2019). Ghost net removal in ancient Lake Ohrid: A pilot study. Fisheries Research. 211, 46–50. https://doi.org/10.1016/j.fishres.2018.10.023
• Valdenegro-Toro, M. (2016, December). Submerged marine debris detection with autonomous underwater vehicles. In 2016 International Conference on Robotics and Automation for Humanitarian Applications (RAHA). (pp. 1–7). https://doi.org/10.1109/RAHA.2016.7931907
• Wei, C., Bai, Y., Liu, C., Zhu, Y., Wang, C., & Li, X. (2024). Unsupervised underwater shipwreck detection in side-scan sonar images based on domain-adaptive techniques. Scientific Reports. 14(1), Article 12687. https://doi.org/10.1038/s41598-024-63501-1
• Yaman, O., Yetis, H., & Karakose, M. (2020). Band reducing based SVM classification method in hyperspectral image processing. 2020 Zooming Innovation in Consumer Technologies Conference (ZINC). (pp. 21–25). https://doi.org/10.1109/ZINC50678.2020.9161813
• Yang, F.-J. (2018). An implementation of Naive Bayes classifier. 2018 International Conference on Computational Science and Computational Intelligence (CSCI). (pp. 301–306). https://doi.org/10.1109/CSCI46756.2018.00065
• Ye, X., & Wang, X. (2018, July). Deep generative network and regression network for fishing nets detection in real-time. 2018 37th Chinese Control Conference (CCC). (pp. 9466–9471). https://doi.org/10.23919/ChiCC.2018.8483142
• Yuan (Zhang), Y., Dong, Z., Zhang, K., Shu, S., Lu, F., & Chen, J. (2021, January). Illumination variation-resistant video-based heart rate monitoring using LAB color space. Optics and Lasers in Engineering. 136, Article 106328. https://doi.org/10.1016/j.optlaseng.2020.106328
• Yuh, J., & West, M. (2001, January). Underwater robotics. Advanced Robotics. 15(5), 609–639. https://doi.org/10.1163/156855301317033595
• Zhang, Y., Wang, X., Sun, L., Lei, P., Chen, J., He, J., Zhou, Y., & Liu, Y. (2024). Mask-guided deep learning fishing net detection and recognition based on underwater range gated laser imaging. Optics and Laser Technology. 171, Article 110402. https://doi.org/10.1016/j.optlastec.2023.110402
• Zhao, Y.-P., Niu, L.-J., Du, H., & Bi, C.-W. (2020). An adaptive method of damage detection for fishing nets based on image processing technology. Aquacultural Engineering. 90, Article 102071. https://doi.org/10.1016/j.aquaeng.2020.102071
• Zuzanna, K., Tomasz, U., Michał, G., & Robert, P. (2022). How high-tech solutions support the fight against IUU and ghost fishing: a review of innovative approaches, methods, and trends. IEEE Access, 10, 112539-112554. https://doi.org/10.1109/ACCESS.2022.3212384