Template Matching Using Improved Rotations Fourier Transform Method

• Autorzy: Wijaya Marvin Chandra

Identyfikatory

DOI

10.24425/ijet.2022.143898

• Języki publikacji: EN

Abstrakty

EN

Template matching is a process to identify and localize a template image on an original image. Several methods are commonly used for template matching, one of which uses the Fourier transform. This study proposes a modification of the method by adding an improved rotation to the Fourier transform. Improved rotation in this study uses increment rotation and three shear methods for the template image rotation process. The three shear rotation method has the advantage of precise and noisefree rotation results, making the template matching process even more accurate. Based on the experimental results, the use of 10°angle increments has increased template matching accuracy. In addition, the use of three shear rotations can improve the accuracy of template matching by 13% without prolonging the processing time.

Słowa kluczowe

EN

template matching; Fourier transform; three shear rotations; image rotation

• Wydawca: Polish Academy of Sciences, Committee of Electronics and Telecommunication
• Czasopismo: International Journal of Electronics and Telecommunications
• Rocznik: 2022
• Tom: Vol. 68. No. 4
• Strony: 881--888
• Opis fizyczny: Bibliogr. 25 poz., fot., rys., tab., wykr.

Twórcy

autor

Wijaya Marvin Chandra

• Computer Engineering Departement, Maranatha Christian University, Bandung, Indonesia

Bibliografia

• [1] R. Susik, S. Grabowski, K. Fredriksson, ”Revisiting Multiple Pattern Matching”, Computing and Informatics, 2019, vol. 38, no. 4, pp. 937-962, https://doi.org/10.31577/cai20194937.
• [2] H. Schweitzer, J. W. Bell, F. Wu, ”Very fast template matching”, Lecture Notes Computer Science, vol. 2353, no. 009741, 2002, pp. 358-372, 2002, https://doi.org/10.1007/3-540-47979-1 24.
• [3] M. Che, M. Che, Z. Chao, X. Cao, ”Traffic Light Recognition for Real Scenes Based on Image Processing and Deep Learning”, Computing and Informatics, 2020, vol. 39, no. 3, pp. 439–463, 2020, https://doi.org/10.31577/cai 2020 3 439.
• [4] N. Roshanbin, J. Miller, ”A comparative study of the performance of local feature-based pattern recognition algorithms”, Pattern Analysis and Applications, 2017, vol. 20, no. 4, pp. 1145-1156, https://doi.org/10.1007/s10044-016-0554-y.
• [5] W. Q. Huang, M. Z. Huang, Y. M. Wang, “Detecting objects using Rolling Convolution and Recurrent Neural Network,” International Journal Electronics and Telecommunication, vol. 65, no. 2, pp. 293-301, 2019, https://doi.org/10.24425/ijet.2019.126313.
• [6] K. S. Yadav, K. A. Monsley, R. H. Laskar, S. Misra, M. K. Bhuyan, T. Khan, ”A selective region-based detection and tracking approach towards the recognition of dynamic bare hand gesture using deep neural network”, Multimedia Systems, 2022, in press, https://doi.org/10.1007/s00530-022-00890-1.
• [7] C. V ́azquez, M. Ghazal, A. Amer, ”Feature-based detection and correction of occlusions and split of video objects”, Signal, Image and Video Processing, 2009, vol. 3, pp. 13-25, https://doi.org/10.1007/s11760-008-0055-6.
• [8] P. H. Chien, G. C. Lee, ”A template-based method for identifying input regions in survey forms”, Pattern Recognition and Image Analysis volume, 2011, vol. 21, pp. 469-472, https://doi.org/10.1134/S1054661811020210.
• [9] G. Du, M. Zhou, C. Yin, Z. Wu, W. Shui, ”Classifying fragments of terracotta warriors using template-based partial matching”, Multimedia Tools and Applications, 2018, vol. 77, no. 15, pp. 19171-19191, https://doi.org/10.1007/s11042-017-5396-0.
• [10] H. Weber, ”Numerical computation of the fourier transform using Laguerre functions and the Fast Fourier Transform”, Numerische Mathematik, 1980, vol. 36, pp. 197-209, https://doi.org/10.1007/BF01396758.
• [11] E. Liflyand, ”Fourier transform versus Hilbert transform”, Journal of Mathematical Sciences, 2012, vol. 187, pp. 49-56, https://doi.org/10.1007/s10958-012-1048-0.
• [12] T. Ai, X. Cheng, P. Liu, M. Yang, ”A shape analysis and template matching of building features by the Fourier transform method”, Computers, Environment and Urban Systems, 2013, vol. 41, pp. 219-233, https://doi.org/10.1016/j.compenvurbsys.2013.07.002.
• [13] D. M. Tsai, C. K. Huang, ”Defect Detection in Electronic Surfaces Using Template-Based Fourier Image Reconstruction”, IEEE Transactions on Components, Packaging and Manufacturing Technology, 2019, vol. 9, no. 1, pp. 163-172, https://doi.org/10.1109/TCPMT.2018.2873744.
• [14] A. Mukherjeea, A. Khanb, ”A Fourier series based Template Matching Approach to Detect the Splitting of Second Heart Sound”, IOSR Journal of VLSI and Signal Processing, 2014, vol. 4, no. 4, pp. 9-13, https://doi.org/10.9790/4200-04430913.
• [15] P. Elangovan, M. K. Nath, “A Review: Person Identification using Retinal Fundus Images,” International Journal Electronics and Telecommunication, vol. 65, no. 4, pp. 585-596, 2019, https://doi.org/10.24425/ijet.2019.129817.
• [16] M. Sabaghi, S. R. Hadianamrei, M. Fattahi, M. R. Kouchaki, A. Zahedi, ”Retinal Identification System Based on the Combination of Fourier and Wavelet Transform”, Journal of Signal and Information Processing, 2012, vol. 3, no. 1, pp. 35-38, https://doi.org/10.4236/jsip.2012.31005.
• [17] M. Uenohara, T. Kanade, ”Use of Fourier and Karhunen-Loeve decomposition for fast pattern matching with a large set of templates”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, vol. 19, no. 8, pp. 891-898, https://doi.org/10.1109/34.608291.
• [18] G. Zhang, M. Lei, X. Liu, ”Novel template matching method with sub-pixel accuracy based on correlation and Fourier-Mellin transform”, Optical Engineering, 2009, vol. 48, no. 4, p. 055001, https://doi.org/10.1117/1.3125425.
• [19] Y. Liu, Q. Zou, S. Luo, ”GPU Accelerated Fourier Cross Correlation Computation and Its Application in Template Matching”, Communications in Computer and Information Science (ICHCC 2011), 2011, p. 163, https://doi.org/10.1007/978-3-642-25002-6 68.
• [20] A. M. Grigoryan, A. John, S. S. Agaian, ”A Novel Color Image Enhancement Method by the Transfor- mation of Color Images to 2-D Grayscale Images”, International Journal of Signal Processing and Analysis, 2017, vol. 2, no. 2, pp. 1-18, https://doi.org/10.35840/2631-5114/3502.
• [21] T. Ahonen, J. Matas, C. He, M. Pietik ̈ainen, ”Rotation Invariant Image Description with Local Binary Pattern Histogram Fourier Features”, in Scandinavian Conference on Image Analysis, 2009, pp. 61-70, https://doi.org/10.1007/978-3-642-02230-2 7.
• [22] M. V. Noskov, V. S. Tutatchikov, ”Modification of a two-dimensional fast Fourier transform algorithm with an analog of the Cooley-Tukey algorithm for image processing”, Pattern Recognition and Image Analysis, 2017, vol. 27, no. 1, pp. 110-113, https://doi.org/10.1134/S1054661817010096.
• [23] Y. Mei, M. N. Omidvar, X. Li, X. Yao, ”A Competitive Divide-and-Conquer Algorithm for Unconstrained Large-Scale Black-Box Optimization”, ACM Transactions on Mathematical Software, 2016, vol. 42, no. 2, pp. 1-24, https://doi.org/10.1145/2791291.
• [24] V. Sukhoy, A. Stoytchev, ”Generalizing the inverse FFT off the unit circle”, 2019, Scientific reports, vol. 4, no. 14443, pp. 1-12, https://doi.org/10.1038/s41598-019-50234-9.
• [25] T. Y. Goh, S. N. Basah, H. Yazid, M. J. A. Safar, F. S. A. Saad, ”Performance analysis of image thresholding: Otsu technique”, Measurement: Journal of the International Measurement Confederation, 2018, vol. 114, no. 1, pp. 298-307, https://doi.org/10.1016/j.measurement.2017.09.052.

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).