Apakah kombinasi power lbp dan fourier descriptor dapat digunakan untuk klasifikasi citra kerang?
DOI:
https://doi.org/10.26594/teknologi.v6i2.768Abstract
ABSTRAK
Permasalahan pengklasifikasian secara manual biasanya terletak pada hasil akurasi dan waktu klasifikasi. Pengklasifikasi citra kerang pada umumnya dilakukan berdasarkan pada karakteristik bentuk dan tekstur cangkang kerang. Pengembangan perangkat lunak untuk pengklasifikasian secara otomatis diharapkan dapat meningkatkan hasil akurasi dan memperbaiki waktu klasifikasi. Pada penelitian ini bertujuan untuk mengkombinasikan fitur tekstur berbasis metode Power LBP dan fitur bentuk berbasis metode fourier descriptor yang digunakan untuk klasifikasi citra kerang.
Citra input yang digunakan, sebelumnya telah melalui praproses dan segmentasi untuk memisahkan objek dengan background. Citra objek yang sudah terpisah ditransformasi menjadi citra biner dan citra grayscale untuk proses ekstraksi fitur. Hasil dari kedua fitur yang sudah diperoleh akan dilakukan kombinasi dengan mempertimbangkan bobot masing-masing fitur yang kemudian dilakukan normalisasi. Dengan mengkombinasikan fitur tekstur dan fitur bentuk diharapkan memperoleh fitur yang signifikan yang dapat meningkatkan akurasi sebuah klasifikasi.
Uji coba dilakukan pada 3 jenis dataset kerang yakni kerang darah, kerang pasir dan kerang bulu dengan menggunakan SVM cross validation dengan k=2 . Hasil uji coba menunjukkan bahwa ada keterkaitan antara mengkombinasikan fitur tekstur dan fitur bentuk pada permasalahan klasifikasi citra kerang dapat diperbaiki dengan hasil akurasi klasifikasi yang diperoleh sebesar 99,39% dengan fitur tekstur lebih dominan daripada fitur yang lainnya.
Kata Kunci: citra kerang, ekstraksi fitur, fourier descriptor, klasifikasi, power LBP.
ABSTRACT
Shells image classification are generally conducted based on the characteristics of the shape and texture of the shells. The problems of classification usually occur results of accuracy and timing classification. The software development for classification is expected to increase the yield of accuracy result and optimize the time of classification. In this study, we combine extracting texture features based Power LBP method and extracting shape features based Fourier Descriptor method for shells image classification.
The used input images had been conducted preprocessing and segmentation to separate object and background using Otsu methods. The objects images that had been separated are transformed into a binary image and grayscale image for feature extraction process. Texture features are extracted using Power LBP (PLBP) method and grayscale image as input. Shape features are extracted using Fourier Descriptor (FD) method and binary image as input. The results of these two features will be combined by considering the weight of each feature and then normalized. Combines texture features and shape features, we expect to obtain significant features that can improve the accuracy of classification.
Tests was performed on three types of shells dataset that is blood clams, mussels and scallops feather sand by using SVM cross validation with k = 2 fold. The results show that there is a link between features combine texture and shape features on the image classification problems that can be solved with the results obtained classification accuracy of 99.39% with a texture feature more dominant than the other features.
Keywords: classification, feature extraction, Fourier Descriptor , Power LBP, Shellfish image.
References
T. Ojala, M. Pietikainen and T. Maenpaa, "Multiresolution gray-scale and rotation invariant texture classification with local binary patterns," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 7, pp. 971-987, 2002.
M. Pietikäinen, T. Ojala and Z. Xu, "Rotation-invariant texture classification using feature distributions," Pattern Recognition, vol. 33, no. 1, p. 43–52, 2000.
Z. Guo, L. Zhang and D. Zhang, "A completed modeling of local binary pattern operator for texture classification," IEEE Transactions on Image Processing, vol. 19, no. 6, pp. 1657-1663, 2010.
Y. Zhao, W. Jia, R.-X. Hu and H. Min, "Completed robust local binary pattern for texture classification," Neurocomputing, vol. 106, no. April, pp. 68-76, 2013.
B. Smolka and K. Nurzynska, "Power LBP: A Novel Texture Operator for Smiling and Neutral Facial Display Classification," Procedia Computer Science, vol. 51, no. 2015, pp. 1555-1564, 2015.
Z. Chen and S.-K. Sun, "A Zernike moment phase-based descriptor for local image representation and matching," IEEE Transactions on Image Processing, vol. 19, no. 1, pp. 205-219, 2010.
M. Ghosh, J. Mukherjee and R. Parekh, "Fish Shape Recognition using Multiple Shape Descriptors," International Journal of Computer Applications, vol. 73, no. 16, pp. 14-19, 2013.
A. Aakif and M. F. Khan, "Automatic classification of plants based on their leaves," Biosystems Engineering, vol. 139, no. November, pp. 66-75, 2015.
D. Zhang and G. Lu, "Shape-based image retrieval using generic Fourier descriptor," Signal Processing: Image Communication, vol. 17, no. 10, pp. 825-848, 2002.
A. Kadir, "Leaf identification using Fourier descriptors and other shape features," Gate to Computer Vision and Pattern Recognition, vol. 1, no. 1, pp. 3-7, 2015.
M. Mentari, Y. A. Sari and R. K. Dewi, "Deteksi Kanker Kulit Melanoma dengan Linear Discriminant Analysis-Fuzzy k-Nearest Neigbhour Lp-Norm," Register: Jurnal Ilmiah Teknologi Sistem Informasi, vol. 2, no. 1, pp. 34-39, 2016.
A. S. Nugroho, A. B. Witarto and D. Handoko, "Support Vector Machine - Teori dan Aplikasinya dalam Bioinformatika," 16 Maret 2005. [Online]. Available: http://www.komputasi.lipi.go.id/utama.cgi? tampilpublikasi&1014224403&1110939371 . [Accessed 2016 Juli 1].
Downloads
Published
Issue
Section
License
Please find the rights and licenses in Teknologi: Jurnal Ilmiah Sistem Informasi. By submitting the article/manuscript of the article, the author(s) agree with this policy. No specific document sign-off is required.
1. License
The non-commercial use of the article will be governed by the Creative Commons Attribution license as currently displayed on Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
2. Author(s)' Warranties
The author warrants that the article is original, written by stated author(s), has not been published before, contains no unlawful statements, does not infringe the rights of others, is subject to copyright that is vested exclusively in the author and free of any third party rights, and that any necessary written permissions to quote from other sources have been obtained by the author(s).
3. User/Public Rights
Register's spirit is to disseminate articles published are as free as possible. Under the Creative Commons license, Register permits users to copy, distribute, display, and perform the work for non-commercial purposes only. Users will also need to attribute authors and Register on distributing works in the journal and other media of publications. Unless otherwise stated, the authors are public entities as soon as their articles got published.
4. Rights of Authors
Authors retain all their rights to the published works, such as (but not limited to) the following rights;
Copyright and other proprietary rights relating to the article, such as patent rights,
The right to use the substance of the article in own future works, including lectures and books,
The right to reproduce the article for own purposes,
The right to self-archive the article (please read out deposit policy),
The right to enter into separate, additional contractual arrangements for the non-exclusive distribution of the article's published version (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal (Register: Jurnal Ilmiah Teknologi Sistem Informasi).
5. Co-Authorship
If the article was jointly prepared by more than one author, any authors submitting the manuscript warrants that he/she has been authorized by all co-authors to be agreed on this copyright and license notice (agreement) on their behalf, and agrees to inform his/her co-authors of the terms of this policy. Register will not be held liable for anything that may arise due to the author(s) internal dispute. Register will only communicate with the corresponding author.
6. Royalties
Being an open accessed journal and disseminating articles for free under the Creative Commons license term mentioned, author(s) aware that Register entitles the author(s) to no royalties or other fees.
7. Miscellaneous
Register will publish the article (or have it published) in the journal if the article’s editorial process is successfully completed. Register's editors may modify the article to a style of punctuation, spelling, capitalization, referencing and usage that deems appropriate. The author acknowledges that the article may be published so that it will be publicly accessible and such access will be free of charge for the readers as mentioned in point 3.
