Application of deep neural networks for military symbol recognition from sketch images
DOI:
https://doi.org/10.54939/1859-1043.j.mst.CSCE8.2024.55-64Keywords:
Military symbols; Sketch images; Convolutional Neural Networks.Abstract
The purpose of this research is to test the effectiveness of deep neural networks in recognizing sketch images, particularly military symbols. Sketch images are highly abstract and lack typical features of real images, such as color, background, and environmental details, making the use of deep neural networks a significant challenge. To address this issue, we implement a sketch image recognition model based on Convolutional Neural Networks (CNN). The content of the paper includes designing and describing a new CNN model optimized for symbol recognition from sketch images. We have trained this model on a dataset self-constructed by our team. The training results show that the model has high accuracy in recognizing military symbols from sketch images, confirming the potential of deep neural networks in this field.
References
[1]. N. D. Dinh, H. V. Toan, “System Design Documentation of T3BD System”, (2020).
[2]. Cục Bản đồ, “Tài liệu giới thiệu về phần mềm xây dựng văn kiện tác chiến và huấn luyện diễn tập trên nền bản đồ số”, (2017) (in Vietnamese).
[3]. D. D. Thinh, N. C. Thanh, L.V.Diep, N. D. Vuong, L. D. Ha, P. N. Hai, “A voice search engine for military symbols to enhance the drafting of operational plan documents on digital map”, Journal of Military Science and Technology, Vol. 87, pp. 40-49, (2022). DOI: https://doi.org/10.54939/1859-1043.j.mst.87.2023.40-49
[4]. Guang-Hai Liu, Jing-Yu Yang, “Content-based image retrieval using color difference histogram,” J. Pattern Recognition, Vol. 46, Issue 1, pp. 188-198, (2013). DOI: https://doi.org/10.1016/j.patcog.2012.06.001
[5]. R. Zhou, L. Chen, and L. Zhang, “Sketch-based image retrieval on a large scale database,” in Proc. 20th ACM Int. Conf. Multimedia, pp. 973–976, (2012). DOI: https://doi.org/10.1145/2393347.2396360
[6]. C. Ma, X. Yang, C. Zhang, X. Ruan, M. Yang, “Sketch retrieval via Dense stroke features,” in Proc. British Machine Vision Conference, Vol. 2, pp. 65.1–65.11, (2013). DOI: https://doi.org/10.5244/C.27.65
[7]. S.Wang, Jian Zhang, Tony X. Han, Zhenjiang Miao, “Sketch-Based Image Retrieval Through Hypothesis-Driven Object Boundary Selection With HLR Descriptor,”, IEEE Transactions on Multimedia, Vol.17, Issue 7, pp. 1045 – 1057, (2015). DOI: https://doi.org/10.1109/TMM.2015.2431492
[8]. Y. Qi et al., “Sketch-based image retrieval via Siamese convolutional neural network,” in IEEE International Conference on Image Processing, pp. 2460-2464, (2016).
[9]. Z. Zhang, Y. Zhang, R. Feng, T. Zhang and W.Fan, “Zero-Shot Sketch-based image retrieval via graph Convolution Network,” in Proc. of the AAAI Conference on Artificial Intelligence, Vol. 34 (07), pp.12943-12950, (2020). DOI: https://doi.org/10.1609/aaai.v34i07.6993
[10]. N. Kumar, R. Ahmed, Venkatesh H, V. Mayya and S. Kamath S, “Sketch-based image retrieval using Convolutional Neural Networks based on Feature Adaptation and Relevance Feedback,” in book: Advanced Techniques for IoT Applications, Proceedings of EAIT, pp.103-113, (2020). DOI: https://doi.org/10.1007/978-981-16-4435-1_12
[11]. K. O’Shea and R. Nash, “An Introduction to Convolutional Neural Network”, arXiv preprint arXiv: 1511.08458, (2015).
[12]. N. Wang, Z.Qin, L.Yan H. Zhuang, X.Wang, M.l Bendersk, M. Najork, "Rank4Class: A Ranking Formulation for Multiclass Classification", arXiv preprint arXiv: 2112.09727v1 92021, (2021).
[13]. I. J. Goodfellow, Y. Bengio and A. Courville, "Deep Learning", MIT Press, (2016).
[14]. G. Mahitha G, T. Nikshepa, K.P. Spoorthy, "Effective Method for Leukocytes Classification and Segmentation in Blood Smear Images", International Advanced Research Journal in Science, Engineering and Technology, Vol. 4, Special Issue 8, (2017).
