Pengenalan Spesies Gulma Berdasarkan Bentuk dan Tekstur Daun Menggunakan Jaringan Syaraf Tiruan

https://doi.org/10.22146/ijccs.7549

Herman Herman(1*), Agus Harjoko(2)

(1) 
(2) Jurusan Ilmu Komputer dan Elektronika, FMIPA UGM, Yogyakarta
(*) Corresponding Author

Abstract


Abstrak

Gulma merupakan tanaman pengganggu yang merugikan tanaman budidaya dengan menghambat pertumbuhan tanaman budidaya. Langkah awal dalam melakukan pengendalian gulma adalah mengenali spesies gulma pada lahan tanaman budidaya. Cara tercepat dan termudah untuk mengenali tanaman, termasuk gulma adalah melalui daunnya. Dalam penelitian ini, diusulkan pengenalan spesies gulma berdasarkan citra daunnya dengan cara mengekstrak ciri bentuk dan ciri tekstur dari citra daun gulma tersebut. Untuk mendapatkan ciri bentuk, digunakan metode moment invariant, sedangkan untuk ciri tekstur digunakan metode lacunarity yang merupakan bagian dari fraktal. Untuk proses pengenalan berdasarkan ciri-ciri yang telah diekstrak, digunakan metode Jaringan Syaraf Tiruan dengan algoritma pembelajaran Backpropagation. Dari  hasil pengujian pada penelitian ini, didapatkan tingkat akurasi pengenalan tertinggi sebesar 97.22% sebelum noise dihilangkan pada citra hasil deteksi tepi Canny. Tingkat akurasi tertinggi didapatkan menggunakan 2 ciri moment invariant (moment  dan ) dan 1 ciri lacunarity (ukuran box 4 x 4 atau 16 x 16). Penggunaan 3 neuron hidden layer pada Jaringan Syaraf Tiruan (JST) memberikan waktu pelatihan data yang lebih cepat dibandingkan dengan menggunakan 1 atau 2 neuron hidden layer.

 

Kata kunci3-5 gulma, daun ,moment invariant, lacunarity, jaringan syaraf tiruan

 

Abstract

Weeds are plants that harm crops by inhibiting the growth of cultivated plants. The first step to take control of weeds is by identifying weed among the cultivating plant. The fastest and easiest way to identify plants, including weeds is by its leaves. This research proposing weed species recognition based on weeds leaf images by extracting its shape and texture features. Moment invariant method is used to get the shape and Lacunarity method for the texturel.  Neural Network with backpropagation learning algorithm are implements for the extracted features recognition proses. The result of this research achievement shows the highest level of recognition accuracy of 97.22% before the noise is eliminated in the image of the Canny edge detection. Highest level of accuracy is obtained using two features from moment invariant (moment  and  ) and 1 lacunarity’s feature (size box 4 x 4 or 16 x 16). The use of 3 neurons in the hidden layer of Artificial Neural Network (ANN) provide training time data more quickly than by using 1 or 2 hidden layer neurons.

 

Keywords weed, leaf, moment invariant, lacunarity, artificial neural network

 


Keywords


weed; leaf; moment invariant; lacunarity; artificial neural network

Full Text:

PDF


References

[1] Weis, M. dan Gerhard, R., 2007, Identification of Weeds from Digital Images. Agricultural Field Trials, Department of Weed Science, University of Hohenheim, Stuttgart, Germany.

[2] Siddiqi, M., Ahmad, I. dan Sulaiman, S., 2009, Weed Recognition Based on Erosion and Dilation Segmentation Algorithm, Education Technology and Computer, IEEE, Singapore.

[3] Solahuddin, M., Astika, I.W., Seminar, K.B. dan Buono, A., 2010, Weeds and Plants Recognition using Fuzzy Clustering and Fractal Dimension Methods for Automatic Weed Control, International Conference, The Quality Information for Competitive Agricultural Based Production System and Commerce.

[4] Ahmed, F., Kabir, H., Bhuyan, S., Bari, H. dan Hossain, E., 2012, Automated Weed Classification with Local Pattern-Based Texture Descriptors, The International Arab Journal of Information Technology, XI, 1, 87-94.

[5] Ningsih, R., 2011, Pengaruh Umur Tanaman Karet (Hevea Brasiliensis) Terhadap Komposisi Jenis Gulma Pada Jenis Tanah Latosol dan Regosol di PT. Perkebunan Nusantara (PTPN) IX Banyumas, Tesis, Fakultas Pertanian, Universitas Gadjah Mada, Yogyakarta.

[6] Tjitrosoepomo, G., 1996, Morfologi Tumbuhan, Gadjah Mada University Press, Yogyakarta.

[7] Kadir, A. dan Susanto, A., 2012, Pengolahan Citra: Teori dan Aplikasinya, Edisi Pertama, Penerbit Andi, Yogyakarta.

[8] Putra, D., 2010, Pengolahan Citra Digital, Penerbit Andi, Yogyakarta.

[9] Gonzalez, R.C. dan Woods, R.E., 2008. Digital Image Processing, Edisi ketiga, Pearson Prentice Hall, New Jersey.

[10] Hidjah, K., 2010, Sistem Biometrika Sidik Jari Dengan Ekstraksi Ciri Menggunakan Dimensi Fraktal dan Lacunarity, Tesis, Prodi S2 Ilmu Komputer, FMIPA UGM, Yogyakarta.

[11] Sutojo, T., Mulyanto, E. dan Suhartono, V., 2011, Kecerdasan Buatan, Penerbit Andi, Yogyakarta.

[12] Fausett, L., 1994, Fundamental of Neural Network.Architecture, Algorithms, and Aplication, Prentice Hall, New Jersey.

[13] Huang, Z. dan Leng, J., 2010, Analysis of Hu’s Moment Invariant on Image Scaling and Rotation, International Conference on Computer Engineering and Technology (ICCET), V7, 476-480, Chendu, China.



DOI: https://doi.org/10.22146/ijccs.7549

Article Metrics

Abstract views : 11140 | views : 10882

Refbacks

  • There are currently no refbacks.




Copyright (c) 2015 IJCCS - Indonesian Journal of Computing and Cybernetics Systems

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.



Copyright of :
IJCCS (Indonesian Journal of Computing and Cybernetics Systems)
ISSN 1978-1520 (print); ISSN 2460-7258 (online)
is a scientific journal the results of Computing
and Cybernetics Systems
A publication of IndoCEISS.
Gedung S1 Ruang 416 FMIPA UGM, Sekip Utara, Yogyakarta 55281
Fax: +62274 555133
email:ijccs.mipa@ugm.ac.id | http://jurnal.ugm.ac.id/ijccs



View My Stats1
View My Stats2