Improving Image Classification using Fuzzy Neural Network and Backtracking Algorithm

Abdul Haris Rangkuti, Ayuliana Ayuliana, Muhammad Fahri

Abstract


We propose an improved image classification method using fuzzy neural network (EFNN) which describes an algorithm in order to create a class rule based on the training data image. Redundant rule on 2 or more of data training image is generated in some data processing. A solution to the problem using backtracking algorithm, which will determine the appropriate class rule, is used by one of the training data images. Thus, every rule has an image of the appropriate class. In the process of inputting the data EFNN algorithm, 7 statistical parameters are used as a representation of the image characteristics, for feature extraction using wavelet Haar 2. The image becomes more leverage and has different characteristics to the representation of the image of the other. All input from crisp number is converted into fuzzy number with 5 membership function, which are Very Low, Low, Medium, High and Very High. Here, each image is represented by 7 statistical parameters and each parameter is divided into 5 categories. Percentage of accuracy in the classification process by using algorithms EFNN is above 95 percent for all data training, especially when it is compared with the original FNN.

Keywords


Image Classification; Fuzzy Neural Network; Backtracking; Fuzzyfication; Wavelet Haar; Statistical Parameters;

Full Text:

PDF

References


Rangkuti A H, R. B. Bahaweres, and A. Harjoko,2012, "Batik image retrieval base on similarity of shape and texture characteristic," in International Conference on Advanced Computer Science and Information Systems (ICACSIS 2012), Universty of Indonesia.

Rangkuti A H, Nashrul Hakiem, Rizal Broer Bahaweres, Agus Harjoko, 2012, “Analysis of image similarity with CBIR concept using wavelet transform and threshold algorithm”, IEEE Symposium on Computers & Informatics.

Rangkuti A H, Agus Harjoko,Agfianto Eko Putro, “Content Based batik Image retrieval, Jurnal of Computer science, 2015” page 925 – 934, 2014.

Ali, N., Bajwa, K. B., Sablatnig, R., Chatzichristofis, S. A., Iqbal, Z., Rashid, M., & Habib, H. A. (2016). A novel image retrieval based on visual words integration of SIFT and SURF. PloS one, 11(6), e0157428.

Pratama, A. A., Suciati, N., & Purwitasari, D. (2012). Implementasi Fuzzy C-Means untuk Pengelompokan Citra Batik Berdasarkan Motif dengan Fitur Tekstur. JURNAL TEKNIK POMITS Vol.1, No.1.

Meccasia, K., Hidayat, B., & Sunarya, U. (2015). Klasifikasi Motif Batik Banyuwangi Menggunakan Metode Ekstraksi Ciri Wavelet Dan Metode Klasifikasi Fuzzy Logic. eProceedings of Engineering, 2(2).

Wahyudi, Azurat A, Manurung M, and Murni A, 2009, “Batik Image Reconstruction Based On Codebook and Keyblock Framework”, University of Indonesia.

Sanabila HR and Manurung R, 2009, “Recognition of Batik Motifs using the Generalized Hough Transform”, University of Indonesia.

Pratikaningtyas D dkk, 2010, “Klasifikasi Batik Mengunakan Metode Transformasi Wavelet ”, Paper Skirpsi, UNDIP.

Balamurugan V and Anandhakumar P, “Neuro-Fuzzy Based Clustering Approach For Content Based Image Retrieval Using 2D-Wavelet Transform”, International Journal of Recent Trend in Engineering vol.1 No.1 May,2009.

Ajay KS, Tiwari S, VP Shukla,2012, ”Wavelet Base Multi Class Image Classification using Neural Network”,International Journal of Computer Applica. ”, vol 37 – No.4

Bhardwaj, A., & Siddhu, K. K. (2013). An Approach to Medical Image Classification Using Neuro Fuzzy Logic and ANFIS Kelasifier. International Journal of Computer Trends and Technology- volume4 issue3

Pourghassem H, Ghassemian H, 2011, “Content-based medical image classification using a new hierarchical merging scheme” Comput Med Imaging Graph. 2011 Pub. Dec;32(8):651-61

Celso A Franca, Adilson Gonzaga,2010, “Classification of wood plates by neural networks and Fuzzy logic”, University Federal at Sao Carlos.

Kulkarni and Sara MC Caslin,”Fuzzy Neural Network Models For Multispectral Image Analysis”, Circuit System, Electronics control, Signal Processing, USA, Nov. 2006

M. Kokare, P. K. Biswas, and B. N. Chatterji, "Texture image retrieval using rotated wavelet filters," Pattern Recogn. Lett., vol. 28, pp. 1240- 1249, 2007.

Hazra D et al., 2011, “Texture Recognition with combined GLCM, Wavelet and Rotated Wavelet Features”, International Journal of Computer and Electrical Engineering, Vol.3, No.1, February, 201

Margaretha E, Azurat A, Manurung R, and Murni A, 2009, “ContentBased Information Retrieval System for Batik Application”. University of Indonesia.

Joseph B, P. Darwin, 2012, “Multi Wavelet for Image Retrieval Based On Using Texture and Color Querys”, IOSR Journal of Computer Engineering (IOSRJCE) ISSN: 2278-0661, ISBN: 2278-8727Volume 6, Issue 6 (Nov. - Dec. 2012), PP 10-1.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

ISSN: 2180-1843

eISSN: 2289-8131