Araştırma Makalesi
BibTex RIS Kaynak Göster

Su Altı Görüntü Sınıflandırma için HOG Özellik Çıkarıcı ve KNN Tabanlı Bir Yöntem

Yıl 2024, Cilt: 3 Sayı: 1, 1 - 10, 29.02.2024
https://doi.org/10.62520/fujece.1443818

Öz

Su altındaki çöpler deniz canlılarının yaşamı ve tüm ekosistemi etkilemektedir. Su altındaki çöplerin tespit edilmesi önemli bir araştırma alanıdır. Bu çalışmada su altındaki çöplerin tespit edilebilmesi için bir yöntem önerilmiştir. Önerilen yöntemin uygulanması için erişime açık Trash-ICRA19 veri seti kullanılmıştır. Veri seti kırpma işlemi uygulanmış ve toplamda 11060 görüntüden oluşan bir veri seti elde edilmiştir. Bu görüntüler ön işleme kullanılarak 200×200 piksele dönüştürülmüştür. Yönlü Gradyan Histogramı (HOG) algoritması uygulanılarak, 11060×900 öznitelik vektörleri elde edilmiştir. Elde edilen öznitelik vektörleri daha sonra KNN (K En Yakın Komşu Algoritması), DT (Karar Ağacı), LD (Linear Discriminant), NB (Naive Bayes) ve SVM (Destek Vektör Makinesi) sınıflandırıcıları kullanılarak sonuçlar hesaplanmıştır. Elde edilen sonuçlar KNN sınıflandırıcının bu yöntemde kullanılması durumunda %97.78 doğruluk elde edilmiştir. Önerilen yöntemde sadece özellik çıkarıcı ve sınıflandırıcı kullanılması, yöntemin hafifsıklet olduğunu göstermektedir. Literatürdeki mevcut çalışmalara kıyasla düşük hesapsal karmaşıklığa sahiptir. Ayrıca performans sonuçlarına göre literatürdeki yöntemlerden başarılıdır.

Kaynakça

  • M. Fulton, J. Hong, M. J. Islam and J. Sattar, “Robotic detection of marine litter using deep visual detection models”, Proc. IEEE Int. Conf. Robot. Autom, ss. 5752-5758, May 2019.
  • F. Han, J. Yao, H. Zhu and C. Wang, “Underwater image processing and object detection based on deep CNN method”, J. Sens., vol. 2020, pp. 20, May 2020.
  • X. Li, M. Tian, S. Kong, L. Wu and J. Yu, “A modified YOLOv3 detection method for vision-based water surface garbage capture robot”, Int. J. Adv. Robot. Syst., vol. 17, no 3, pp. 1-11, 2020.
  • G. Tata, S.-J. Royer, O. Poirion and J. Lowe, “A Robotic Approach towards quantifying epipelagic bound plastic using deep visual models”, ss. 1-8, 2021.
  • M. S. A. Bin Rosli, I. S. Isa, M. I. F. Maruzuki, S. N. Sulaiman and I. Ahmad, “Underwater Animal Detection Using YOLOV4”, Proc. - 2021 11th IEEE Int. Conf. Control Syst. Comput. Eng. ICCSCE 2021, sy August, ss. 158-163, (2021).
  • C. M. Wu, Y. Q. Sun, T. J. Wang and Y. L. Liu, “Underwater trash detection algorithm based on improved YOLOv5s”, J. Real-Time Image Process., vol. 19, no. 5, pp. 911-920, 2022.
  • A. Li, L. Yu and S. Tian, “Underwater biological detection based on YOLOv4 combined with channel attention”, J. Mar. Sci. Eng., vol. 10, no. 4, 2022.
  • Z. Moorton, Z. Kurt and W. L. Woo, “Is the use of deep learning an appropriate means to locate debris in the ocean without harming aquatic wildlife?”, Mar. Pollut. Bull., vol. 181, pp. 1-17, 2022.
  • K. Demir and O. Yaman, “International informatics congress (IIC2022) 17-19 February 2022, Batman, Turkey Su Altı Çöp Tespiti İçin YOLOv4 Tabanlı Bir Yöntem”, vol. February, pp. 17-19, (2022).
  • V. S. Thakur and S. Forensic, “On The way towards efficient enhancement of multi-channel underwater images”, vol. September, 2015.
  • K. Iqbal, R. A. Salam, A. Osman and A. Z. Talib, “Underwater image enhancement using an integrated colour model”, vol. November, 2007.
  • E. E. Kılınç and S. Metlek, “Su altı görüntülerinden nesne tespiti”, Eur. J. Sci. Technol., vol. 23, pp. 368-375, 2021.
  • I. Quidu, L. Jaulin and J. Malkasse, “Automatic underwater image pre-processing St ´ To cite this version ”, 2010.
  • A. Shashua, Y. Gdalyahu and G. Hayun, “Pedestrian detection for driving assistance systems: Single-frame classification and system level performance”, IEEE Intell. Veh. Symp. Proc., vol. June, pp. 1-6, 2004.
  • N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection”, Proc. - 2005 IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. CVPR 2005, vol. I, pp. 886-893, 2005.
  • O. Kaynar, H. Arslan, Y. Görmez and Y. E. Işık, “Makine öğrenmesi ve öznitelik seçim yöntemleriyle saldırı tespiti”, Bilişim Teknol. Derg., pp 175-185, 2018.
  • C. Iwendi, G. Srivastava, S. Khan and P. K. R. Maddikunta, “Cyberbullying detection solutions based on deep learning architectures”, Multimed. Syst., 2020.
  • M. Baygin, O. Yaman, T. Tuncer, S. Dogan, P. D. Barua and U. R. Acharya, “Automated accurate schizophrenia detection system using Collatz pattern technique with EEG signals”, Biomed. Signal Process. Control, vol. 70, no. May, pp. 102936, 2021.

A HOG Feature Extractor and KNN-Based Method for Underwater Image Classification

Yıl 2024, Cilt: 3 Sayı: 1, 1 - 10, 29.02.2024
https://doi.org/10.62520/fujece.1443818

Öz

Underwater garbage affects the life of marine creatures and the entire ecosystem. Detecting underwater garbage is an important research area. In this study, a method is proposed to detect underwater garbage. The open-access Trash-ICRA19 dataset was used to implement the proposed method. The data set cropping process was applied and a data set consisting of 11060 images in total was obtained. These images were converted to 200×200 pixels using preprocessing. By applying the Directed Gradient Histogram (HOG) algorithm, 11060×900 feature vectors were obtained. The resulting feature vectors were then calculated using KNN (K Nearest Neighbor Algorithm), DT (Decision Tree), LD (Linear Discriminant), NB (Naive Bayes), and SVM (Support Vector Machine) classifiers. The results obtained showed that 97.78% accuracy was obtained when the KNN classifier was used in this method. The use of only feature extractors and classifiers in the proposed method shows that the method is lightweight. It has low computational complexity compared to existing studies in the literature. Moreover, according to its performance results, it is more successful than the methods in the literature.

Destekleyen Kurum

TÜBİTAK, FÜBAP

Teşekkür

This study was supported by the Scientific Technology and Research Council of Turkey (TÜBİTAK) 2210/C Domestic Priority Areas Graduate Scholarship Program with project number 1649B022204832 and project number 1649B022204832. This thesis was supported by the Fırat University Scientific Research Projects Coordination Unit (FÜBAP) with the protocol number TEKF.22.01.

Kaynakça

  • M. Fulton, J. Hong, M. J. Islam and J. Sattar, “Robotic detection of marine litter using deep visual detection models”, Proc. IEEE Int. Conf. Robot. Autom, ss. 5752-5758, May 2019.
  • F. Han, J. Yao, H. Zhu and C. Wang, “Underwater image processing and object detection based on deep CNN method”, J. Sens., vol. 2020, pp. 20, May 2020.
  • X. Li, M. Tian, S. Kong, L. Wu and J. Yu, “A modified YOLOv3 detection method for vision-based water surface garbage capture robot”, Int. J. Adv. Robot. Syst., vol. 17, no 3, pp. 1-11, 2020.
  • G. Tata, S.-J. Royer, O. Poirion and J. Lowe, “A Robotic Approach towards quantifying epipelagic bound plastic using deep visual models”, ss. 1-8, 2021.
  • M. S. A. Bin Rosli, I. S. Isa, M. I. F. Maruzuki, S. N. Sulaiman and I. Ahmad, “Underwater Animal Detection Using YOLOV4”, Proc. - 2021 11th IEEE Int. Conf. Control Syst. Comput. Eng. ICCSCE 2021, sy August, ss. 158-163, (2021).
  • C. M. Wu, Y. Q. Sun, T. J. Wang and Y. L. Liu, “Underwater trash detection algorithm based on improved YOLOv5s”, J. Real-Time Image Process., vol. 19, no. 5, pp. 911-920, 2022.
  • A. Li, L. Yu and S. Tian, “Underwater biological detection based on YOLOv4 combined with channel attention”, J. Mar. Sci. Eng., vol. 10, no. 4, 2022.
  • Z. Moorton, Z. Kurt and W. L. Woo, “Is the use of deep learning an appropriate means to locate debris in the ocean without harming aquatic wildlife?”, Mar. Pollut. Bull., vol. 181, pp. 1-17, 2022.
  • K. Demir and O. Yaman, “International informatics congress (IIC2022) 17-19 February 2022, Batman, Turkey Su Altı Çöp Tespiti İçin YOLOv4 Tabanlı Bir Yöntem”, vol. February, pp. 17-19, (2022).
  • V. S. Thakur and S. Forensic, “On The way towards efficient enhancement of multi-channel underwater images”, vol. September, 2015.
  • K. Iqbal, R. A. Salam, A. Osman and A. Z. Talib, “Underwater image enhancement using an integrated colour model”, vol. November, 2007.
  • E. E. Kılınç and S. Metlek, “Su altı görüntülerinden nesne tespiti”, Eur. J. Sci. Technol., vol. 23, pp. 368-375, 2021.
  • I. Quidu, L. Jaulin and J. Malkasse, “Automatic underwater image pre-processing St ´ To cite this version ”, 2010.
  • A. Shashua, Y. Gdalyahu and G. Hayun, “Pedestrian detection for driving assistance systems: Single-frame classification and system level performance”, IEEE Intell. Veh. Symp. Proc., vol. June, pp. 1-6, 2004.
  • N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection”, Proc. - 2005 IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. CVPR 2005, vol. I, pp. 886-893, 2005.
  • O. Kaynar, H. Arslan, Y. Görmez and Y. E. Işık, “Makine öğrenmesi ve öznitelik seçim yöntemleriyle saldırı tespiti”, Bilişim Teknol. Derg., pp 175-185, 2018.
  • C. Iwendi, G. Srivastava, S. Khan and P. K. R. Maddikunta, “Cyberbullying detection solutions based on deep learning architectures”, Multimed. Syst., 2020.
  • M. Baygin, O. Yaman, T. Tuncer, S. Dogan, P. D. Barua and U. R. Acharya, “Automated accurate schizophrenia detection system using Collatz pattern technique with EEG signals”, Biomed. Signal Process. Control, vol. 70, no. May, pp. 102936, 2021.
Toplam 18 adet kaynakça vardır.

Ayrıntılar

Birincil Dil İngilizce
Konular Bilgisayar Yazılımı
Bölüm Research Articles
Yazarlar

Kübra Demir 0000-0003-0793-5039

Orhan Yaman 0000-0001-9623-2284

Yayımlanma Tarihi 29 Şubat 2024
Gönderilme Tarihi 27 Şubat 2024
Kabul Tarihi 28 Şubat 2024
Yayımlandığı Sayı Yıl 2024 Cilt: 3 Sayı: 1

Kaynak Göster

APA Demir, K., & Yaman, O. (2024). A HOG Feature Extractor and KNN-Based Method for Underwater Image Classification. Firat University Journal of Experimental and Computational Engineering, 3(1), 1-10. https://doi.org/10.62520/fujece.1443818
AMA Demir K, Yaman O. A HOG Feature Extractor and KNN-Based Method for Underwater Image Classification. FUJECE. Şubat 2024;3(1):1-10. doi:10.62520/fujece.1443818
Chicago Demir, Kübra, ve Orhan Yaman. “A HOG Feature Extractor and KNN-Based Method for Underwater Image Classification”. Firat University Journal of Experimental and Computational Engineering 3, sy. 1 (Şubat 2024): 1-10. https://doi.org/10.62520/fujece.1443818.
EndNote Demir K, Yaman O (01 Şubat 2024) A HOG Feature Extractor and KNN-Based Method for Underwater Image Classification. Firat University Journal of Experimental and Computational Engineering 3 1 1–10.
IEEE K. Demir ve O. Yaman, “A HOG Feature Extractor and KNN-Based Method for Underwater Image Classification”, FUJECE, c. 3, sy. 1, ss. 1–10, 2024, doi: 10.62520/fujece.1443818.
ISNAD Demir, Kübra - Yaman, Orhan. “A HOG Feature Extractor and KNN-Based Method for Underwater Image Classification”. Firat University Journal of Experimental and Computational Engineering 3/1 (Şubat 2024), 1-10. https://doi.org/10.62520/fujece.1443818.
JAMA Demir K, Yaman O. A HOG Feature Extractor and KNN-Based Method for Underwater Image Classification. FUJECE. 2024;3:1–10.
MLA Demir, Kübra ve Orhan Yaman. “A HOG Feature Extractor and KNN-Based Method for Underwater Image Classification”. Firat University Journal of Experimental and Computational Engineering, c. 3, sy. 1, 2024, ss. 1-10, doi:10.62520/fujece.1443818.
Vancouver Demir K, Yaman O. A HOG Feature Extractor and KNN-Based Method for Underwater Image Classification. FUJECE. 2024;3(1):1-10.