INCEPTION SH: SAHNE GÖRÜNTÜLERININ SINIFLANDIRILMASINDA INCEPTION MODÜL TABANLI YENI BIR CNN MODELI

Year 2024, , 328 - 344, 30.06.2024

Sedat Metlek , Halit Çetiner

https://doi.org/10.21923/jesd.1372788

Cited By: 1

Abstract

Bu çalışmada otonom insansız hava araçlarında (İHA) kullanılabilecek optimum seviyede blok yapısına sahip hafif ağırlıklı bir model tasarlanmıştır. Inception V3 modeli temel alınarak geliştirilen Inception SH modeli, literatürde halka açık bir veri seti olan "Intel Image Dataset" üzerinde karşılaştırılmıştır. Karşılaştırma sonucunda Inception V3 modeli için doğruluk, kesinlik, geri çağırma ve F1 skoru metrikleri için sırasıyla 0,882, 0,883, 0,882 ve 0,882 değerleri elde edilmiştir. Inception SH modelinde ise doğruluk, kesinlik, geri çağırma ve F1 skoru metrikleri için sırasıyla 0,958, 0,957, 0,974 ve 0,967 değerleri elde edilmiştir. Bu değerlerden de anlaşılacağı üzere, önerilen Inception SH modeli, temel alınan Inception V3 modeline göre daha yüksek performans değerleri sunmaktadır. Inception SH modeli aynı veri setini kullanan literatürdeki farklı modellerle de karşılaştırılmış ve karşılaştırılan modellere göre doğruluk, kesinlik, geri çağırma ve F1 skoru metriklerinde üstünlük sağlamıştır. Elde edilen sonuçlara göre, otonom İHA'ların popülerliği de göz önünde bulundurulduğunda, Inception SH modelinin çeşitli IoT cihazlarında hafif bir model olarak kullanılabileceği öngörülmektedir.

Keywords

Derin Öğrenme, Bilgisayarla Görü, CNN, Sahne Sınıflandırma, IHA

INCEPTION SH: A NEW CNN MODEL BASED ON INCEPTION MODULE FOR CLASSIFYING SCENE IMAGES

Abstract

In this study, a light-weight model with an optimum block structure that can be used in autonomous unmanned aerial vehicles (UAVs) was designed. The Inception SH model, which was developed based on the Inception V3 model, was compared on "Intel Image Dataset", a publicly available dataset in the literature. As a result of the comparison, values of 0.882, 0.883, 0.882 and 0.882 were obtained for the accuracy, precision, recall, and F1 score metrics for the Inception V3 model, respectively. In the Inception SH model, values of 0.958, 0.957, 0.974 and 0.967 were obtained for accuracy, precision, recall and F1 score metrics, respectively. As can be seen from these values, the proposed Inception SH model offers higher performance values than the underlying Inception V3 model. The Inception SH model was compared with different models in the literature using the same data set and was superior in accuracy, precision, recall and F1 score metrics compared to the compared models. According to the results obtained, it is predicted that the Inception SH model can be used as a lightweight model in various IoT devices, considering the popularity of autonomous UAVs.

Keywords

Deep Learning, Computer Vision, CNN, Scene Classification, UAV

References

• Akbay, Tuncer. 2022. Modeling Education Studies Indexed in Web of Science Using Natural Language Processing. Instructional Technology and Lifelong Learning 3(2):129–43.
• Amarasingam, Narmilan, Arachchige Surantha Ashan Salgadoe, Kevin Powell, Luis Felipe Gonzalez, and Sijesh Natarajan. 2022. A Review of UAV Platforms, Sensors, and Applications for Monitoring of Sugarcane Crops. Remote Sensing Applications: Society and Environment 26:100712.
• Cao, Jianfang, Minmin Yan, Yiming Jia, Xiaodong Tian, and Zibang Zhang. 2021. Application of a Modified Inception-v3 Model in the Dynasty-Based Classification of Ancient Murals. EURASIP Journal on Advances in Signal Processing 2021:1–25.
• Çetiner, Halit, and Sedat Metlek. 2023. DenseUNet+: A Novel Hybrid Segmentation Approach Based on Multi-Modality Images for Brain Tumor Segmentation. Journal of King Saud University - Computer and Information Sciences 35(8):101663. doi: https://doi.org/10.1016/j.jksuci.2023.101663.
• Chollet, François. 2017. Xception: Deep Learning with Depthwise Separable Convolutions. Pp. 1251–58 in Proceedings of the IEEE conference on computer vision and pattern recognition.
• Chowdhury, Anjir Ahmed, Argho Das, Khadija Kubra Shahjalal Hoque, and Debajyoti Karmaker. 2022. A Comparative Study of Hyperparameter Optimization Techniques for Deep Learning BT - Proceedings of International Joint Conference on Advances in Computational Intelligence. Pp. 509–21 in, edited by M. S. Uddin, P. K. Jamwal, and J. C. Bansal. Singapore: Springer Nature Singapore.
• Fime, Awal Ahmed, Md Ashikuzzaman, and Abdul Aziz. 2023. Audio Signal Based Danger Detection Using Signal Processing and Deep Learning. Expert Systems with Applications 121646.
• Finnegan, Philip. 2017. World Civil Unmanned Aerial Systems Market Profile and Forecast 2017. Teal Group 1–13. Retrieved (https://tealgroup.com/images/TGCTOC/WCUAS2017TOC_EO.pdf).
• Gómez-Chova, L., D. Tuia, G. Moser, and G. Camps-Valls. 2015. Multimodal Classification of Remote Sensing Images: A Review and Future Directions. Proceedings of the IEEE 103(9):1560–84. doi: 10.1109/JPROC.2015.2449668.
• Grand View, Research. 2023. Commercial UAV Market Size, Share & Trends Analysis Report By Product (Fixed Wing, Rotary Blade, Nano, Hybrid), By Application (Agriculture, Energy, Government, Media & Entertainment, Construction), By Region, And Segment Forecasts, 2023 - 2030. Grand View Research 171. Retrieved (https://www.grandviewresearch.com/industry-analysis/commercial-uav-market).
• Guo, S., Y. Ni, K. Xing, Y. Liu, and W. Ni. 2021. MinorNet: A Lightweight Neural Network for Battlefield Scene Classification. Pp. 17–20 in 2021 14th International Symposium on Computational Intelligence and Design (ISCID).
• Hu, Fan, Gui-Song Xia, Jingwen Hu, and Liangpei Zhang. 2015. Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery. Remote Sensing 7(11):14680–707.
• Huang, Rachel, Jonathan Pedoeem, and Cuixian Chen. 2018. YOLO-LITE: A Real-Time Object Detection Algorithm Optimized for Non-GPU Computers. Pp. 2503–10 in 2018 IEEE international conference on big data (big data). IEEE.
• Li, Miao, Shuying Zang, Bing Zhang, Shanshan Li, and Changshan Wu. 2014. A Review of Remote Sensing Image Classification Techniques: The Role of Spatio-Contextual Information. European Journal of Remote Sensing 47(1):389–411. doi: 10.5721/EuJRS20144723.
• Matese, Alessandro, Piero Toscano, Salvatore F. Di Gennaro, Lorenzo Genesio, Francesco P. Vaccari, Jacopo Primicerio, Claudio Belli, Alessandro Zaldei, Roberto Bianconi, and Beniamino Gioli. 2015. Intercomparison of UAV, Aircraft and Satellite Remote Sensing Platforms for Precision Viticulture. Remote Sensing 7(3):2971–90.
• Maulik, U., and D. Chakraborty. 2017. Remote Sensing Image Classification: A Survey of Support-Vector-Machine-Based Advanced Techniques. IEEE Geoscience and Remote Sensing Magazine 5(1):33–52. doi: 10.1109/MGRS.2016.2641240.
• Menouar, H., I. Guvenc, K. Akkaya, A. S. Uluagac, A. Kadri, and A. Tuncer. 2017. UAV-Enabled Intelligent Transportation Systems for the Smart City: Applications and Challenges. IEEE Communications Magazine 55(3):22–28. doi: 10.1109/MCOM.2017.1600238CM.
• Metlek, S, and H. Çetiner. 2023. ResUNet+: A New Convolutional and Attention Block-Based Approach for Brain Tumor Segmentation. IEEE Access 11:69884–902. doi: 10.1109/ACCESS.2023.3294179.
• Metlek, Sedat, and Halit Çetiner. 2023. Classification of Poisonous and Edible Mushrooms with Optimized Classification Algorithms. Pp. 408–15 in International Conference on Applied Engineering and Natural Sciences. Vol. 1.
• Moranduzzo, T., F. Melgani, M. L. Mekhalfi, Y. Bazi, and N. Alajlan. 2015. Multiclass Coarse Analysis for UAV Imagery. IEEE Transactions on Geoscience and Remote Sensing 53(12):6394–6406. doi: 10.1109/TGRS.2015.2438400.
• Noble, William S. 2006. What Is a Support Vector Machine? Nature Biotechnology 24(12):1565–67. doi: 10.1038/nbt1206-1565.
• Nogueira, Keiller, Otávio A. B. Penatti, and Jefersson A. dos Santos. 2017. Towards Better Exploiting Convolutional Neural Networks for Remote Sensing Scene Classification. Pattern Recognition 61:539–56. doi: https://doi.org/10.1016/j.patcog.2016.07.001.
• Pan, Yuhang, Junru Liu, Yuting Cai, Xuemei Yang, Zhucheng Zhang, Hong Long, Ketong Zhao, Xia Yu, Cui Zeng, Jueni Duan, Ping Xiao, Jingbo Li, Feiyue Cai, Xiaoyun Yang, and Zhen Tan. 2023. Fundus Image Classification Using Inception V3 and ResNet-50 for the Early Diagnostics of Fundus Diseases. Frontiers in Physiology 14.
• Penatti, O. A. B., K. Nogueira, and J. A. dos Santos. 2015. Do Deep Features Generalize from Everyday Objects to Remote Sensing and Aerial Scenes Domains? Pp. 44–51 in 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).
• Quinlan, J. Ross. 1986. Induction of Decision Trees. Machine Learning 1:81–106.
• Rusiecki, A. 2019. Trimmed Categorical Cross-Entropy for Deep Learning with Label Noise. Electronics Letters 55(6):319–20. doi: https://doi.org/10.1049/el.2018.7980.
• Saran, Nurdan Ayse, Murat Saran, and Fatih Nar. 2021. Distribution-Preserving Data Augmentation. PeerJ Computer Science 7:e571.
• Şenel, Bilge, and Fatih Ahmet Şenel. 2022. Novel Neural Network Optimization Approach for Modeling Scattering and Noise Parameters of Microwave Transistor. International Journal of Numerical Modelling: Electronic Networks, Devices and Fields 35(1):e2930.
• Shabbir, Amsa, Nouman Ali, Jameel Ahmed, Bushra Zafar, Aqsa Rasheed, Muhammad Sajid, Afzal Ahmed, and Saadat Hanif Dar. 2021. Satellite and Scene Image Classification Based on Transfer Learning and Fine Tuning of ResNet50. edited by M. Maqsood. Mathematical Problems in Engineering 2021:5843816. doi: 10.1155/2021/5843816.
• Shahi, Tej Bahadur, Cheng-Yuan Xu, Arjun Neupane, and William Guo. 2023. Recent Advances in Crop Disease Detection Using UAV and Deep Learning Techniques. Remote Sensing 15(9):2450.
• Singh, Vineeta, Deeptha Girish, and Anca L. Ralescu. 2017. Image Understanding-a Brief Review of Scene Classification and Recognition. MAICS 2017:85–91.
• Sobti, Priyal, Anand Nayyar, and Preeti Nagrath. 2021. EnsemV3X: A Novel Ensembled Deep Learning Architecture for Multi-Label Scene Classification. PeerJ Computer Science 7:e557.
• Thepade, Sudeep D., and Mrunal E. Idhate. 2022. Machine Learning-Based Scene Classification Using Thepade’s SBTC, LBP, and GLCM BT - Futuristic Trends in Networks and Computing Technologies. Pp. 603–12 in, edited by P. K. Singh, S. T. Wierzchoń, J. K. Chhabra, and S. Tanwar. Singapore: Springer Nature Singapore.
• Tokmak, Mahmut. 2022. Uzun-Kısa Süreli Bellek Ağı Kullanarak Hisse Senedi Fiyatı Tahmini. Mehmet Akif Ersoy Üniversitesi Uygulamalı Bilimler Dergisi 6(2):309–22.
• Tuia, D., M. Volpi, L. Copa, M. Kanevski, and J. Munoz-Mari. 2011. A Survey of Active Learning Algorithms for Supervised Remote Sensing Image Classification. IEEE Journal of Selected Topics in Signal Processing 5(3):606–17. doi: 10.1109/JSTSP.2011.2139193.
• Wu, X., R. Liu, H. Yang, and Z. Chen. 2020. An Xception Based Convolutional Neural Network for Scene Image Classification with Transfer Learning. Pp. 262–67 in 2020 2nd International Conference on Information Technology and Computer Application (ITCA).
• Xia, Gui-Song, Jingwen Hu, Fan Hu, Baoguang Shi, Xiang Bai, Yanfei Zhong, Liangpei Zhang, and Xiaoqiang Lu. 2017. AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene Classification. IEEE Transactions on Geoscience and Remote Sensing 55(7):3965–81. doi: 10.1109/TGRS.2017.2685945.
• Yahya, Ali A., Kui Liu, Ammar Hawbani, Yibin Wang, and Ali N. Hadi. 2023. A Novel Image Classification Method Based on Residual Network, Inception, and Proposed Activation Function. Sensors 23(6).
• Yuan, C., Z. Liu, and Y. Zhang. 2015. UAV-Based Forest Fire Detection and Tracking Using Image Processing Techniques. Pp. 639–43 in 2015 International Conference on Unmanned Aircraft Systems (ICUAS).
• Zeggada, A., and F. Melgani. 2017. Multilabeling UAV Images with Autoencoder Networks. Pp. 1–4 in 2017 Joint Urban Remote Sensing Event (JURSE).
• Zhang, L., L. Zhang, and B. Du. 2016. Deep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art. IEEE Geoscience and Remote Sensing Magazine 4(2):22–40. doi: 10.1109/MGRS.2016.2540798.
• Zhu, Xianyu, Jinjiang Li, Ruchang Jia, Bin Liu, Zhuohan Yao, Aihong Yuan, Yinqiu Huo, and Zhang Haixi. 2023. LAD-Net: A Novel Light Weight Model for Early Apple Leaf Pests and Diseases Classification. IEEE/ACM Transactions on Computational Biology And Bioinformatics 20(2):1156–69.
• Zou, Q., L. Ni, T. Zhang, and Q. Wang. 2015. Deep Learning Based Feature Selection for Remote Sensing Scene Classification. IEEE Geoscience and Remote Sensing Letters 12(11):2321–25. doi: 10.1109/LGRS.2015.2475299.