Derin Öğrenme Nesne Tanımasının Tehlikeli Köpek Irkları Üzerinde İncelenmesi

Year 2024, , 141 - 149, 30.06.2024

İclal Çetin Taş

https://doi.org/10.53501/rteufemud.1330367

Abstract

Derin öğrenme mimarileri ile yapay zeka problemlerinin çözümü için birçok derin öğrenme yaklaşımı geliştirilmiştir. Güçlü özellik çıkarma ve öğrenme yetenekleri sebebiylede nesen tanıma işlemlerinde sıkça tervih edilmektedir. günümüzde en cok tercih edilen evcil hayvanların başında gelen köpeklerin tespiti farklı amaçlarla önem arz etmektedir. Cins bazında yapılan analizlerde tercih edilmektedir. Bu makalede, derin öğrenme yöntemleri ile 3 farklı tehlikeli köpek ırkından oluşan bir veri setinde köpeğin tespiti için derin öğrenme ve segmentasyon yöntemi birlikte kullanılmıştır. Elde edilen sonuçlarda NasNetLarge öncesinde kullanılan doku bölütleme yöntemiyle doğruluk oranını %88,33'e çıkardığı görülmüştür.

Keywords

ResNet, NasNetLarge, Inceptionresnetv2, Doku segmentasyonu, Nesne tanıma

An Investigation of Deep Learning Object Recognition on Dangerous Dog Breeds

Abstract

Many deep learning approaches have been developed to solve artificial intelligence problems with deep learning architectures. Due to its powerful feature extraction and learning capabilities, it is frequently preferred in object recognition processes. Detection of dogs, which is one of the most preferred pets today, is important for different purposes. It is preferred in analyzes made on the basis of gender. In this article, deep learning methods and deep learning and segmentation methods are used together to detect the dog in a data set consisting of 3 different dangerous dog breeds. In the results obtained, it was seen that the accuracy rate increased to 88.33% with the tissue segmentation method used before NasNetLarge.

Keywords

ResNet, NasNetLarge, Inceptionresnetv2, Texture segmentation, Object recognition

References

• Alfarhood, S., Alrayeh, A., Safran, M., Alfarhood, M., and Che, D. (2023). Image-based Arabian camel breed classification using transfer learning on CNNs. Applied Sciences 2023, 13(14), 8192. https://doi.org/10.3390/APP13148192
• Bozkurt, F. (2023). Skin lesion classification on dermatoscopic images using effective data augmentation and pre-trained deep learning approach. Multimedia Tools and Applications, 82(12), 18985–19003. https://doi.org/10.1007/S11042-022-14095-1/TABLES/9
• Chen, H.C., Widodo, A.M., Wisnujati, A., Rahaman, M., Lin, J.C.W., Chen, L. and Weng, C.E. (2022). AlexNet convolutional neural network for disease detection and classification of tomato leaf. Electronics, 11(6), 951. https://doi.org/10.3390/ELECTRONICS11060951
• Dhanachandra, N., Manglem, K. and Chanu, Y.J. (2015). Image segmentation using K -means clustering algorithm and subtractive clustering algorithm. Procedia Computer Science, 54, 764–771. https://doi.org/10.1016/J.PROCS.2015.06.090
• Ferreira, C.A., Melo, T., Sousa, P., Meyer, M.I., Shakibapour, E., Costa, P. and Campilho, A. (2018). Classification of Breast Cancer Histology Images Through Transfer Learning Using a Pre-trained Inception Resnet V2. In: Image Analysis and Recognition. ICIAR 2018. Lecture Notes in Computer Science, vol 10882 (Eds.Campilho, A., Karray, F., ter Haar Romeny, B), Springer, Cham. https://doi.org/10.1007/978-3-319-93000-8_86
• Gao, Z., Shao, Y., Xuan, G., Wang, Y., Liu, Y. and Han, X. (2020). Real-time hyperspectral imaging for the in-field estimation of strawberry ripeness with deep learning. Artificial Intelligence in Agriculture, 4, 31–38. https://doi.org/10.1016/J.AIIA.2020.04.003
• Ilhan, I., Bali, E., and Karakose, M. (2022). An ımproved deepfake detection approach with NasNetLarge CNN. 2022 International Conference on Data Analytics for Business and Industry, ICDABI 2022, 598–602. https://doi.org/10.1109/ICDABI56818.2022.10041558
• Iong, J. and Chen, Z. (2021). Automatic vehicle license plate detection using K-Means clustering algorithm and CNN. Journal of Electrical Engineering and Automation (EEA). https://doi.org/10.36548/jeea.2021.1.002
• Liu, D. and Yu, J. (2009). Otsu method and K-means. Proceedings - 2009 9th International Conference on Hybrid Intelligent Systems, HIS 2009, 1(2), 344–349. https://doi.org/10.1109/HIS.2009.74
• Liu, X., Xia, T., Wang, J., Yang, Y., Zhou, F., Lin, Y., and Research, B. (2016). Fully convolutional attention networks for fine-grained recognition. arXiv,1603.06765. https://doi.org/10.48550/arXiv.1603.06765
• Özgür, A., Bozkurt Keser, S.N. and Nur, S. (2021). Meme kanseri tümörlerinin derin öğrenme algoritmaları ile sınıflandırılması. Turkish Journal of Nature and Science, 10(2), 212–222. https://doi.org/10.46810/TDFD.957618
• Murcia-Gómez, D., Rojas-Valenzuela, I. and Valenzuela, O. (2022). Impact of ımage preprocessing methods and deep learning models for classifying histopathological breast cancer ımages. Applied Sciences, 12(22), 11375. https://doi.org/10.3390/APP122211375
• Ráduly, Z., Sulyok, C., Vadászi, Z. and Zölde, A. (2018). Dog breed ıdentification using deep learning. SISY 2018 - IEEE 16th International Symposium on Intelligent Systems and Informatics, Proceedings, 271–275. https://doi.org/10.1109/SISY.2018.8524715
• Rajpal, S., Lakhyani, N., Singh, A.K., Kohli, R., and Kumar, N. (2021). Using handpicked features in conjunction with ResNet-50 for improved detection of COVID-19 from chest X-ray images. Chaos, Solitons and Fractals, 145, 110749. https://doi.org/10.1016/J.CHAOS.2021.110749
• Sahin, M.E., Tawalbeh, L. and Muheidat, F. (2022). The security concerns on cyber-physical systems and potential risks analysis using machine learning. Procedia Computer Science, 201(C), 527–534. https://doi.org/10.1016/J.PROCS.2022.03.068
• Sai Bharadwaj Reddy, A. and Sujitha Juliet, D. (2019). Transfer learning with RESNET-50 for malaria cell-image classification. Proceedings of the 2019 IEEE International Conference on Communication and Signal Processing, ICCSP 2019, 945–949. https://doi.org/10.1109/ICCSP.2019.8697909
• Salvi, M., Acharya, U.R., Molinari, F. and Meiburger, K.M. (2021). The impact of pre- and post-image processing techniques on deep learning frameworks: A comprehensive review for digital pathology image analysis. Computers in Biology and Medicine, 128, 104129. https://doi.org/10.1016/J.COMPBIOMED.2020.104129
• Sermanet, P., Frome, A. and Real, E. (2014). Attention for fine-grained categorization. arXiv, 1412.7054v3. https://doi.org/10.48550/arXiv.1412.7054
• Simon, M. and Rodner, E. (2015). Neural activation constellations: unsupervised part model discovery with convolutional networks. arXiv, 1504.08289. https://doi.org/10.48550/arXiv.1504.08289
• Sinnott, R.O., Wu, F. and Chen, W. (2019). A Mobile application for dog breed detection and recognition based on deep learning. Proceedings - 5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2018, 87–96. https://doi.org/10.1109/BDCAT.2018.00019
• URL-1, (2023). https://europeanpetfood.org/_/news/new-fediaf-facts-figures-highlights-the-growth-of-european-pet-ownership/, July 19, 2023.
• URL-2, (2023). https://www.kaggle.com/datasets/jessicali9530/stanford-dogs-dataset, May 12, 2023
• Wang, C., Wang, J., Du, Q. and Yang, X. (2020). Dog breed classification based on deep learning. Proceedings - 2020 13th International Symposium on Computational Intelligence and Design, ISCID 2020, 209–212. https://doi.org/10.1109/ISCID51228.2020.00053
• Zheng, X., Lei, Q., Yao, R., Gong, Y. and Yin, Q. (2018). Image segmentation based on adaptive K-means algorithm. Eurasip Journal on Image and Video Processing, 2018(1), 1–10. https://doi.org/10.1186/S13640-018-0309-3/FIGURES/14