AUTHORS: W. Panomram, W. Ieosanurak, W. Klongdee

Download as PDF

ABSTRACT: This paper proposes a novel method for face classification based on principal component analysis (PCA) of a grayscale image. The proposed method classifies image by using the minimum distance between vertices of a triangle and the tested image. Vertices of a triangle are created from three distinct points obtained from the combination of a number of images per class. The recognition rate compares the proposed method with the nearest feature line (NFL), the shortest feature line segment (SFLS), the restricted nearest feature line with ellipse (RNFLE), and the shortest distance with the centroid of the triangle (SDC). The experimental results on the Grimace and faces94 databases show that the proposed method has recognition rate over 90%. For Grimace database, the proposed algorithm outperforms the other methods.

KEYWORDS: - face classification, triangle, vertices, minimum distance

REFERENCES:

[1] X. He, S. Yan,Y. Hu, P. Niyogi and H.J. Zhang, “Face recognition using laplacianfaces,” IEEE T. Pattern. Anal., vol. 27, no.3, pp. 1–13, 2005.

[2] T. Cove and, P. Hart, “Nearest neighbor pattern classification,” IEEE Trans. Inf. Theory., vol. 13, pp. 21–27, Jan 1967.

[3] S.Z. Li and J. Lu, “Face recognition using the nearest future line method,” IEEE Trans Neural Netw., vol. 10, no. 2, pp. 439-43, Mar 1999.

[4] D.Q. Han, C.Z. Han and Y. Yang, “A novel classifier based on shortest feature line segment,” Pattern Recognit. Lett., vol. 32, pp. 485–493, 2011.

[5] Q. Feng, J. Pan and L. Yan, “ Restricted nearest feature line with ellipse for face,” J. Inf. Hiding and Multimedia Signal Proc., vol. 3, pp. 297–305, 2012.

[6] W. Klongdee and W. Ieosanurak, “Face Classification based on PCA by Using the Centroid of a Triangle,” International Journal of Circuits, Systems and Signal Processing, Vol. 12, pp. 526-531, 2018.

[7] Q. Feng, J.S. Pan, and L. Yan, “Nearest feature centre classifier for face recognition,” J. Electr. Lett., vol. 48, no. 18, pp. 1120-1120, 2012.

[8] Y. Zhou, C. Zhang and J. Wang, “Extended nearest feature line classifier,” in Proc. 8th Pacific Rim Int. Conf. Artif. Intell. Trends Artif. Intell. Berlin, Heidelberg, pp. 183–190, 2004.

[9] H. Tameem, “Face recognition by using nearest feature midpoint algorithm,” J. of ALQadisiyah for comp. Sci. Math., vol. 9, no.1 pp. 144-152, 2017.

[10] L. Spacek, Description of the collection of facial images, (2008). Available: http://cswww.essex.ac.uk/mv/allfaces/.