ENHANCEMENT OF TRIANGLE COORDINATES FOR TRIANGLE FEATURES FOR BETTER CLASSIFICATION


(Received: 2015-11-25, Revised: 2016-01-14 , Accepted: 2016-01-27)
Recently, the triangle features have been applied in digit recognition by adopting the angle as a part of the features. Most of the studies in digit recognition area which applied these features have given impressive results. However, the issue of big gap values that occurred between angles, ratios and gradients has shown a strong impact on the accuracy of the results. Therefore, we introduce our proposed method which is data normalization that has adopted the nature of triangle geometry in order to resolve this issue. Besides, we have applied other techniques, such as Z-score, Minimax and LibSVM function in the experiment. There are four digit datasets used which are HODA, MNIST, IFHCDB and BANGLA. The results of classification have shown that our proposed method has given better results compared to other techniques

[1] G. Gartner, L. Meng and M. P. Peterson, Digital Terrain Modelling, Lecture Notes in Geoinformation and Cartography, 2007.

[2] G. N. Clements, The Geometry of Phonological Features, Cambridge University Press, vol. 2, pp. 225–252, 1985.

[3] M. L. T. Cossio, L. F. Giesen, G. Araya, M. L. S. Pérez-Cotapos, R. L. VERGARA, M. Manca, R. A. Tohme, S. D. Holmberg, T. Bressmann, D. R. Lirio, J. S. Román, R. G. Solís, S. Thakur, S. N. Rao, E. L. Modelado, A. D. E. La, C. Durante, U. N. A. Tradición, M. En, E. L. Espejo, D. E. L. A. S. Fuentes, U. A. De Yucatán, C. M. Lenin, L. F. Cian, M. J. Douglas, L. Plata and F. Héritier, Uma ética para quantos?, vol. XXXIII, no. 2, pp. 81–87, 2012.

[4] E. W. Weisstein, "Triangle," Wolfram Research, Inc., 1999-2016.

[5] "Math Open Reference Citations," [Online], Available: http://www.mathopenref.com/site/cite.html,[Accessed: 19-Nov-2015].

[6] C. Lin and K. Fan, "Human Face Detection Using Geometric Triangle Relationship," Proc. 15th Int. Conf. Pattern Recognition (ICPR-2000), vol. 2, pp. 941–944, 2000.

[7] Moh'd Sanusi Azmi, Khairuddin Omar, M. F. Nasrudin and A. K. Muda, Fitur Baharu Dari Kombinasi Geometri Segitiga Dan Pengezonan Untuk Paleografi Jawi Digital, Ph.D. dissertation, Universiti Kebangsaan Malaysia, 2013.

[8] L. Gao and Y. Xu, "Face Orientation Recognition Based on Multiple Facial Feature Triangles," in Proc. of the 2012 Int. Conf. Control Eng. Commun. Technol. (ICCECT 2012), pp. 928–932, 2012.

[9] Z. Liu and J. An, "A New Algorithm of Global Feature Matching Based on Triangle Regions for Image Registration," pp. 1248–1251, 2010.

[10] X. Chen, J. Tian, X. Yang and Y. Zhang, "An Algorithm for Distorted Fingerprint Matching Based on Local Triangle Feature Set," IEEE Transactions on Information Forensics and Security, vol. 1, issue. 2, pp. 169–177, 2006.

[11] Z. Zhang, S. Wang and A. I. Morphing, "Multi-feature Facial Synthesis Based on Triangle Coordinate System," Proc. of the IEEE 2nd International Conference on Computer Science and Network Technology (ICCSNT 2012), no. 2, pp. 141–145, 2012.

[12] M. M. M. Tin and M. M. Sein, "Multi-Triangle Based Automatic Face Recognition System By Using 3D Geometric Face Feature," in IEEE International Instrumentation and Measurement Technology Conference (I2MTC 2009), Singapore, pp. 895–899, 5-7 May 2009.

[13] P. Tang, R. Jiang and M. Zhao, "Feature Selection and Design Olintrusion Detection System Based on k-means and Triangle Area Support Vector Machine," Proc. of the IEEE 2nd International Conference on Future Networks, 2010. (ICFN’10), pp. 144–148, 2010.

[14] A. Haselhoff and A. Kummert, "A Vehicle Detection System Based on Haar and Triangle Features," in Intelligent Vehicles Sysmposium, pp. 261–266, 2009.

[15] S. Mozaffari, K. Faez and V. Margner, Application of Fractal Theory for On-Line and Off-Line FarsiDigit Recognition, Chapter: Machine Learning and Data Mining in Pattern Recognition, Vol. 4571 of the series Lecture Notes in Computer Science, pp. 868–882, 2007.

[16] R. Ebrahimpour, A. Esmkhani and S. Faridi, "Farsi Handwritten Digit Recognition Based on Mixture of RBF Experts," IEICE Electron Express, vol. 7, no. 14, pp. 1014–1019, 2010.

[17] M. S. Azmi, K. Omar, M. F. Nasrudin, B. Idrus and K. Wan Mohd Ghazali, "Digit Recognition for Arabic/Jawi and Roman Using Features from Triangle Geometry," AIP Conf. Proc., vol. 1522, pp. 526–537, 2013.

[18] M. S. Azmi, K. Omar, C. Wan and S. Bahri, "Exploiting Features from Triangle Geometry for Digit Recognition," Proc. of the IEEE 2013 International Conference on Control, Decision and Information Technologies (CoDIT), Hammamet, Tunisia, pp. 876 - 880, 6-8 May 2013.

[19] Norm Matloff, From Algorithms to Z-Scores: Probabilistic and Statistical Modeling in Computer Science, University of California, p. 464, 2013.

[20] C.-C. Chang and C.-J. Lin, "LIBSVM: A Library for Support Vector Machines," ACM Transactions on Intelligent Systems and Technol., vol. 2, pp. 27:1–27:27, 2011.

[21] H. Khosravi and E. Kabir, "Introducing a Very Large Dataset of Handwritten Farsi Digits and a Study on Their Varieties," Pattern Recognition Letters, vol. 28, no. 10, pp. 1133–1141, 2007.

[22] S. Mozaffari and H. Soltanizadeh, "ICDAR 2009 Handwritten Farsi/Arabic Character Recognition Competition," Proc. of the IEEE 10th International Conference on Document Analaysis and Recognition (ICDAR), pp. 1413–1417, 2009.

[23] Y. LeCun and C. Cortes, MNIST Handwritten Digit Database, 1992.

[24] U. Bhattacharya and B. B. Chaudhuri, "Handwritten Numeral Databases of Indian Scripts and Multistage Recognition of Mixed Numerals," IEEE Transactions on Pattern Analaysis and Machine Intelligence, vol. 31, issue 3, pp. 444–457, 2009.

[25] M. S. Azmi, K. Omar, M. F. Nasrudin and A. K. Muda, "Features Extraction of Arabic Calligraphy Using Extended Triangle Model for Digital Jawi Paleography Analysis," International Journal of Computer Information Systems and Industrial Management Applications, vol. 5, pp. 696–703, 2013.

[26] P. Smith, D. B. Reid, C. Environment, L. Palo, P. Alto and P. L. Smith, "A Threshold Selection Method from Gray-Level Histograms," IEEE Transactions on Systems, Man and Cybernetics, vol. 9, issue 1, pp. 62–66, Jan. 1979.

[27] M. S. Azmi, K. Omar, M. F. Nasrudin, A. Abdullah and K. Wan Mohd Ghazali, "Features Extraction of Arabic Calligraphy Using Extended Triangle Model for Digital Jawi Paleography Analysis," International Journal of Computer Information Systems and Industrial Management Applications, vol. 5, pp. 696-703, 2013.

[28] M. S. Azmi, N. A. Arbain, A. K. Muda, Z. Abal Abas and Z. Muslim, "Data Normalization for Triangle Features by Adapting Triangle Nature for Better Classification," 2015 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT), pp. 1–6, 3-5 Nov. 2015.