Advanced Feature-Based Facial Expression Recognition from Image Sequences Using SVMS

Authors(1) :-Dr. M. Raja Sekar

This examination mentions a new facial illustration discovery technique constructed on improved Support Vector Machine (SVM) by adapting advanced kernels. The operator physically places certain pixels to the face exhibited at the first framework. The crisscross adjustment scheme pathways the full crisscross as the facial illustration develops through time, consequently yielding a crisscross that resembles to the countless concentration of the facial illustration as presented in the final frame. Suitable pixels that are complicated into creating the Facial Units (FUs) movements are chosen. Their geometrical dislocation data, expressed as the co-ordinates variance between the final and the main frame, is obtained to be the input to a bank of SVM. The outcomes display an identification precision of nearly 94% and 95% for straight and FU built facial appearance detection, correspondingly. The clue is to elaborate the three-dimensional movements about the dividing border exterior, by a conformal plotting, such that the reparability between courses is amplified. Illustrations are assumed exclusively for adapting histogram intersection kernels. Replication outcomes for both artificial and real data display extraordinary development of simplification faults, supporting our awareness.

Authors and Affiliations

Dr. M. Raja Sekar
Professor, CSE Department VNRVJIET, Hyderabad, India

SVMs, Facemask appearance Appreciation, Histogram intersection kernel and Riemannian structure.

  1. S. Jaeger, A.Karargyris, S. Antani, and G.Thomas , "Detecting tube -culosis in radiographs  using combined  lung masks", Proc. Int. IEEE Eng. Med. Biol. Soc., vol.34  pp. 89-99, 2014.
  2. G. Coppini, M. Miniati, S. Monti, M. Paterni,R.Favilla, and E.M. Fer- deghini, " A computer-aided diagnosis approach for emphysema recognition  in chest radiography", Med. Eng.Phy., vol. 35, pp. 63-73, 2013.
  3. S. Candermir, S.Jaeger, K. Palaniappan, S.Antani, and  G.Thoma, "Graph-cut based automatic lung boundary  detection in chest radio-graphs," in IEEE Healthcare  Technol. Conf: Translat. Eng. Health Med., 2015, pp. 31- 34, 2014.
  4. B. Ginneken, M. Stegmann and M. Loog,"Segmentation of  anatomical structures in chest radiographs using supervised methods: A comparative study on public database, "Med.  Image Anal., vol. 10,  pp. 19-4, 2015.
  5. J. Lotjonen, R. Wolz, J. Koikkalainen, L.Thurfjell, G.  Waldemar, H. Soininen, and D.Rueckert, " Fast and robust  multi atlas segmentation of brain magnetic resonanceimages"NeuroImage, vol 15,pp. 45-59, 2014.
  6. T. Kim, K. Lee, and S. Lee., " Generative image Segmentation using random walks with restart",  Human  brain mapping , vol 16,  pp.78-89,  2014.
  7. M. Morel and G. Yu. Asift., "A new framework for fully affine invariant image comparison" SIAM Journal onImaging Sciences, vol 27,pp.79-85, 2015.
  8. H. Bay, T. Tuytelaars, and L. V. Gool. , "Evaluation of atlasselection strategies foratlasbased image segmentation with application", Med. Imaging, pp. 34-45, 2013.
  9. Ruecckert, Sonoda and Hayes, "Non rigid registration using free form deformation",Application to breast MR images,vol. 45, pp.89-92, 2014.
  10. Sederberg and  T.W. Parry,"Free form deformation and  solid geometric models",Computer Graphics, vol. 23, pp.452-465, 2013.
  11. Rohlfing and Maurer, "Evaluation of atlas  selection  strategies for atlas-based image segmentation with application to confocal  microscopic images of bee brains", Med Imag, vol.23, pp.56-76, 2014.  vol.23,  pp.56-76, 2014. microscopic images of bee brains", Med Imag, vol.23,  pp.56-76, 2014.
  12. X. G. Zhang, "Using class-center vectors to build support vector ma- chines," presented at the IEEE Proc. Neural Net. Signal Processing IX, Aug. 1999.

Publication Details

Published in : Volume 2 | Issue 6 | November-December 2017
Date of Publication : 2017-12-31
License:  This work is licensed under a Creative Commons Attribution 4.0 International License.
Page(s) : 957-962
Manuscript Number : CSEIT1725195
Publisher : Technoscience Academy

ISSN : 2456-3307

Cite This Article :

Dr. M. Raja Sekar, "Advanced Feature-Based Facial Expression Recognition from Image Sequences Using SVMS", International Journal of Scientific Research in Computer Science, Engineering and Information Technology (IJSRCSEIT), ISSN : 2456-3307, Volume 2, Issue 6, pp.957-962, November-December-2017.
Journal URL :

Article Preview