Volume 9, Issue 5 (May 2022), Pages: 69-74

----------------------------------------------

 Technical Note

 Title: Substantiation of location image classification model using projective template matching and convolutional neural network

 Author(s): Jin-Wook Jang ^1, *, Dong-Wook Lee ²

 Affiliation(s):

 ¹Digital Transformation, Agricultural Cooperative University, Goyang City, South Korea
 ²Intelligence Mobile Systems, Jacobs University Bremen, Bremen, Germany

  Full Text - PDF          XML

 * Corresponding Author. 

  Corresponding author's ORCID profile: https://orcid.org/0000-0002-3605-9157

 Digital Object Identifier: 

 https://doi.org/10.21833/ijaas.2022.05.008

 Abstract:

This study first attempts to observe the action of the CNN and then compares it to test Projective Template Matching and Object Detection as new approaches. In the final model selection, the accuracy of the prediction model and the computational processing time was mainly compared. At last, the combination of the Object Detection model and CNN was selected as a final location classification model with a prediction accuracy of 61%. This final model shows the optimal prediction result by first attempting to detect the common feature regions of the location image and then analyzing the overall feature characteristic. The fact is that CNN is good for training image data with common overall features for classification. This being so, we expect that training several fundamental ROIs can more efficiently train the CNN model than training the pure location images. 

 © 2022 The Authors. Published by IASE.

 This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

 Keywords: Location image search, Projective template matching, Convolutional neural network, Object detection

 Article History: Received 16 December 2021, Received in revised form 27 February 2022, Accepted 4 March 2022

 Acknowledgment 

This research was supported by the National Research Foundation of Korea in 2022(No. NRF-2020R1G1A1005872).

 Compliance with ethical standards

 Conflict of interest: The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

 Citation:

 Jang JW and Lee DW (2022). Substantiation of location image classification model using projective template matching and convolutional neural network. International Journal of Advanced and Applied Sciences, 9(5): 69-74

 Permanent Link to this page

 Figures

 Fig. 1 Fig. 2 Fig. 3 Fig. 4 Fig. 5 Fig. 6 Fig. 7 Fig. 8 Fig. 9 

 Tables

 No Table 

----------------------------------------------    

 References (9)

1. Brownlee J (2019a). A gentle introduction to the rectified linear unit (ReLU). Machine Learning Mastery, 6. Available online at: https://machinelearningmastery.com/rectified-linear-activation-function-for-deep-learning-neural-networks/
2. Brownlee J (2019b). A gentle introduction to pooling layers for convolutional neural networks. Machine Learning Mastery, 22. Available online at: https://machinelearningmastery.com/pooling-layers-for-convolutional-neural-networks/
3. Chatterjee M (2020). What is TensorFlow? The machine learning library explained. Available online at: https://www.mygreatlearning.com/blog/what-is-tensorflow-machine-learning-library-explained/
4. Cho JH, Ahn CW, and Jun JH (2014). A feature point tracking method by using template matching and buffer. The Journal of the Institute of Internet, Broadcasting and Communication, 14(4): 173-179. https://doi.org/10.7236/JIIBC.2014.14.4.173   [Google Scholar]
5. Daftry S, Ridge B, Seto W, Pham TH, Ilhardt P, Maggiolino G, and Detry R (2021). Machine vision based sample-tube localization for Mars sample return. In the 2021 IEEE Aerospace Conference (50100), IEEE, Big Sky, USA: 1-12. https://doi.org/10.1109/AERO50100.2021.9438364   [Google Scholar]
6. Oh S and Park CS (2014). Vehicle license plate recognition system using image binarization and template matching. Journal of the Semiconductor and Display Technology, 13(2): 7-12.   [Google Scholar]
7. Prabhu R (2018). Understanding of convolutional neural network (CNN)-Deep learning. A Medium Corporation, San Francisco, USA.   [Google Scholar]
8. Tensorflow (2020). Customization basics: Tensors and operations. Available online at: https://www.tensorflow.org/tutorials/customization/basics
9. Zhang C and Akashi T (2016). Robust projective template matching. IEICE Transactions on Information and Systems, 99(9): 2341-2350. https://doi.org/10.1587/transinf.2016EDP7038   [Google Scholar]