Presentasi sedang didownload. Silahkan tunggu

Presentasi sedang didownload. Silahkan tunggu

Performance Comparison of Target PNN Classification for Beef and Pork Based on Gabor, PCA and LBP Features Lestari Handayani

Presentasi serupa


Presentasi berjudul: "Performance Comparison of Target PNN Classification for Beef and Pork Based on Gabor, PCA and LBP Features Lestari Handayani"— Transcript presentasi:

1 Performance Comparison of Target PNN Classification for Beef and Pork Based on Gabor, PCA and LBP Features Lestari Handayani Informatics Engineering Department UIN SUSKA RIAU

2 Introduction Issue : In Indonesia, beef demand has reached tonnes (DIT JENNAK, 2012)…(increases every year)… Sometimes vendors mix pork and beef…(more profit) How can buyers to distinguish it? Differences in color, texture, fiber, type of fat, and smell. Solution: Image recognition based on color and texture features. (a). Beef (b). Pork (c). Beef and pork mixed

3 Feature Extractions Mean of HSV = 345,45 Mean of Texture = 124,40 Color extraction Texture extraction Today, I will compare 3 texture methods in PNN classification

4 Reseach Methodology 1.Data collection : images of beef, pork and mixed 2.Data analysis : data training, data testing 3.Image identification process of beef, pork and a mix of both : HSV for color, 3 texture extraction methods (PCA, Gabor, LBP) PNN clasification 4.Design and Analysis System 5.Implementation : Java Programming Language 6.Testing

5 Implementation

6 Results and Analysis MethodsSettingsTypes of dataAverage BeefPorkMix of both Gabor+HSV+ PNN 50% of data training : 50% of data testing, spread= %94.44%92.31%92.08% PCA+HSV+ PNN All data extracted on testing, spread= % % 93.93% LBP+HSV+ PNN 90% of data training : 10% of data testing, spread= % % 91.66%

7 Conclusions The texture and color features extracted from images can be effectively used for identification of beef, pork and a mix of both. This clearly shows the superiority of PCA+HSV+PNN over LBP+HSV+PNN and Gabor+HSV+PNN. The analysis has shown enhanced classification by selection of spread values for each feature. The recognizable mix of beef and pork is very good on PCA+HSV+PNN and LBP+HSV+PNN that is equal to 100%.

8 References Abdullah Iqbal a, Nektarios A. Valous a, Fernando Mendoza a, Da-Wen Sun a, Paul Allen b. Classification of pre- sliced pork and Turkey ham qualities based on image colour and textural features and their relationships with consumer responses. Meat Science 84: p 455– Ahmad Farid Hartono, Dwijanto, Zaenal Abidin. (2012). Implementasi Jaringan Syaraf Tiruan Backpropagation Sebagai Sistem Pengenalan Citra Daging Babi dan Citra Daging Sapi. UNNES Journal of Mathematics. Al-Qur’an Surah Al-Baqarah : 173 Al-Qur’an Surah Al Maidah : 4 Alim, M. K. (2006). Uji dan Aplikasi Komputasi Paralel pada Jaringan Syaraf Probabilistik (PNN) untuk Proses Klasifikasi Mutu Buah Tomat Segar. Undergraduated thesis of Computer Science Department, Institut Pertanian Bogor. Amjad Ali, Xiaojun Jing, Nasir Saleem. GLCM-Based Fingerprint Recognition Algorithm. Proceedings of IEEE IC- BNMT Connie, T., Jin, A. T. B., Ong, M. G. K., & Ling, D. N. C. (2005). An automated palmprint recognition system. Image and Vision Computing, 23(5), 501–515. doi: /j.imavis Connie, T., Teoh, A., Goh, M., & Ngo, D. (2003). Palmprint Recognition with PCA and ICA, (November), 227–232. Ditjennak Press Release Konfrensi Pers Direktur Jenderal Peternakan dan Kesehatan Hewan Tentang Supply Demand Daging Sapi/Kerbau Sampai Dengan Desember In, 5–7 Eleyan, A., & Demirel, H. (2006). PCA and LDA Based Face Recognition Using Feedforward Neural Network Classifier, 199–206. Ella, L.P Abeigne. Bergh, F.van den. Wyk, B.J. van. A comparison of texture feature algorithms for urban settlements classification. IEEE Ford, A., & A. Roberts. (1998).” Colour Space Conversions”, 1998, 1–31. (18 Oktober 2014). Gang Liu, Robert Wang, YunKai Deng, Runpu Chen, Yunfeng Shao, and Zhihui Yuan. A New Quality Map for 2-D Phase Unwrapping Based on Gray Level Co-Occurrence Matrix. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, VOL. 11, NO Hartono, A. F., Dwijanto, & Abidin, Z. (2012). Implementasi Jaringan Syaraf Tiruan Backpropagation Sebagai Sistem Pengenalan Citra Daging Babi dan Citra Daging Sapi. Unnes Journal of Mathematics Vol.1, Issue 2. Huang, H. (2013). “Non-Destructive Detection Of Pork Intramuscular Fat Content Using Hyperspectral Imaging”, McGill University, Canada.

9 References Huang, Hui., Liu, Li., Ngadi, M.O., Gariépy, C., and Prasher, S.O. (2014). “Near-Infrared Spectral Image Analysis of Pork Marbling Based on Gabor Filter and Wide Line Detector Techniques”. Applied Spectroscopy, Vol 68, Issue 3, pp Kadir, A., & Adhi, S. (2012). Pengolahan Citra Teori dan Aplikasi. Yogyakarta: Andi. Kiswanto. (2012). Identifikasi Citra untuk Mengidentifikasi Jenis Daging Sapi Dengan Menggunakan Transformasi Wavelet Haar. Thesis of Information System Magister. Universitas Diponegoro, Malang. Indonesia L P Abeigne, Ella, Wyk B J Van, Bergh F. Van Den, And Wyk A., M. Van “A Comparison Of Texture Feature Algorithms For Urban Settlement Classication,” 1308–11. Mirzapour, Fardin. Ghassemian, Hassan. Using GLCM and Gabor Filters for Classification of PAN Images. IEEE Mishra, M., Jena, A. R., & Das, R. (2013). A Probabilistic Neural Network Approach For Classification Of Vehicle, 2(7), 367– 371. Nektarios A. Valous, Fernando Mendoza, Da-Wen Sun, Paul Allen. Texture appearance characterization of pre-sliced pork ham images using fractal metrics: Fourier analysis dimension and lacunarity. Food Research International 42 (2009) 353– Putra, I. D. (2009). Identifikasi Tanda Tangan Menggunakan Probabilistic Neural Networks (PNN) Dengan Praproses Menggunakan Transformasi WaveletIdentifikasi Tanda Tangan Menggunakan Probabilistic Neural Networks (PNN) Dengan Praproses Menggunakan Transformasi Wavelet. Undergraduated thesis of Computer Science Department, Institut Pertanian Bogor. Specht, D. F. (1990). Probabilistic Neural Networks. Neural Network Journal, Vol 3, pp T.Ojala, M.Piatik¨ainen, T.M¨aenp¨a¨ a. Multiresolution grey-scale androtation invariant texture classification with local binary pattern. IEEE Transactions on Pattern Analysis and Machine Intelligence 24: p 7971– Wahyudi, E., Kusuma, H., & Wirawan. (2011). Perbandingan Unjuk Kerja Pengenalan Wajah Berbasis Fitur Local Binary Pattern dengan Algoritma PCA dan Chi Square. Teknik Elektro, Fakultas Teknologi Industri, Institut Teknologi Sepuluh Nopember (ITS), Indonesia. Wang Zhi-Zhong and Jun-Hai Yong. Texture Analysis and Classification With Linear Regression Model Based on Wavelet Transform. IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 17, NO. 8, AUGUST 2008 Widowati, W. (2011). Perbandingan classifier untuk identifikasi citra tanaman hias. Undergraduated thesis of Computer Science Department, Institut Pertanian Bogor. Yang Bo, Chen Song Can. A comparative study on local binary pattern (LBP) based face recognition: LBP histogram versus LBP image. Neurocomputing120: p 365– Yang, J. (2011). Advanced Biometric Technologies. Yong-jun LIU, Cui-jian ZHAO, Su-jing SUN, Su-jing SUN. “Image Texture Recognition Method Research Based on Wavelet Technology

10 THANK YOU


Download ppt "Performance Comparison of Target PNN Classification for Beef and Pork Based on Gabor, PCA and LBP Features Lestari Handayani"

Presentasi serupa


Iklan oleh Google