Skip to main content

Advertisement

SpringerLink
Log in

HMOAM: hybrid multi-objective genetic optimization for facial analysis by appearance model

  • Special Issue - Regular Research Paper
  • Published:
Memetic Computing Aims and scope Submit manuscript

Abstract

Successful hybridization of single-objective evolutionary algorithm with gradient based methods has shown promising results. However, studies of hybridized Multi-Objective Evolutionary Algorithm are limited, especially in the domain of image analysis. This paper presents a novel methodology of hybridization of multi-objective genetic algorithm for the real world optimization problem of facial analysis of multiple camera images by 2.5D Appearance Model. Facial large lateral movements make acquisition and analysis of facial images by single camera inefficient. Moreover, non-convex multi-dimensional search space formed by the face search by appearance model requires an efficient optimization methodology. Currently, with wide availability of inexpensive cameras, a multi-view system is as practical as a single-view system. To manage these multiple informations, multi-objective genetic algorithm is employed to optimize the face search. To efficiently tackle the problem of non-convexity of the search space, hybridization of NSGA-II (Non-dominated Sorting Genetic Algorithm) with Gradient Descent is proposed in this paper. For this hybridization, we propose a gradient operator in NSGA-II, which computes gradients of the solutions in conjunction with the existing operator of mutation. Thus, it does not increase the computational cost of the system. Another proposition includes a unique method of calculating the relevant information of each camera in a multiple camera system which makes the hybridization procedure efficient and robust. Our proposed algorithm is applied on different facial poses of CMU-PIE database, webcam face images and synthetic face images, and the results are compared with a single view system and a non-hybrid multiple camera system. Simulation results validate the efficiency, accuracy and robustness achieved.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Cootes TF, Edwards GJ, Taylor CJ (1998) Active appearance models. In: European conference on computer vision, vol 2, pp 484–498

  2. Deb K, Agrawal S, Pratab A, Meyarivan T (2000) A fast elitist non-dominated sorting genetic algorithm for multi-objective optimization: Nsga-ii. In: Parallel problem solving from nature VI conference, pp 849–858

  3. Cootes TF, Taylor CJ (2004) Statistical models of appearance for computer vision. Technical report, Technical report from Imaging Science and Biomedical Engineering, University of Manchester

  4. Shan T, Lovell BC, Chen S (2006) Face recognition robust to head pose from one sample image. In: 18th International conference on pattern recognition (ICPR’06), pp 515–518

  5. Shenjun XIN, Haizhou AI (2005) Face alignment under various poses and expressions. In: Affective computing and intelligent interaction, 1st international conference, vol 3784. ACII 2005, Beijing

  6. Liu Y, Li Y, Tao L, Xu G (2004) Multi-view face alignment guided by several facial feature points. In: Proceedings of the 3rd international conference on image and graphics, ICIG’04, pp 238–241

  7. ShuiCheng Y, Cheng QS (2002) Multi-view face alignment using direct appearance models. In: Proceedings of the 5th IEEE international conference on automatic face and gesture recognition, FGR ’02, pp 238–241

  8. Romero M, Bobick AF (2004) Tracking head yaw by interpolation of template responses. In: Proceedings of the conference on computer vision and pattern recognition workshop (CVPRW’04), vol 5, p 83

  9. Cootes TF, Wheeler GV, Walker KN, Taylors CJ (2000) Coupled-view active appearance models. In: Proceedings of British machine vision conference, vol 1, pp 52–61

  10. Dornaika F, Ahlberg J (2003) Fast and reliable active appearance model search for 3d face tracking. In: Proceedings of mirage, INRIA Rocquencourt, France

  11. Xiao J, Baker S, Matthews I, Kanade T (2004) Real-time combined 2D + 3D active appearance models. In: Proceedings of IEEE conference on computer vision and pattern recognition, CVPR04, vol 2, pp II-535–II-542

  12. Sung J, Kim D (2004) Extension of aam with 3d shape model for facial shape tracking. In: International conference on image processing, ICIP04, vol 5, pp 3363–3366

  13. Sattar A, Aidarous Y, Le Gallou S, Seguier R (2007) Face alignment by 2.5d active appearance model optimized by simplex. In: 5th International conference of computer vision system

  14. Sattar A, Aidarous Y, Seguier R (2008) GAGM-AAM: a genetic optimization with gaussian mixtures for active appearance models. In: 15th IEEE international conference on image processing, pp 3220–3223

  15. Blanz V, Vetter T (1999) A morphable model for the synthesis of 3d faces. In: SIGGRAPH’99, pp 187–194

  16. Blanz V, Vetter T (2003) Face recognition based on fitting a 3d morphable model. IEEE Trans Pattern Anal Mach Intell 25(9): 1063–1074

    Article  Google Scholar 

  17. Hu C, Xiao J, Matthews I, Baker S, Cohn JF, Kanade T (2004) Fitting a single active appearance model simultaneously to multiple images. In: British machine vision conference

  18. Kim D, Sung J (2006) A real-time face tracking using the stereo active appearance model. In: International conference on image processing, ICIP06, pp 2833–2836

  19. Dornaika F, Sappa A (2006) Improving appearance-based 3d face tracking using sparse stereo data. In: International conference on computer vision theory and applications, VISAPP

  20. Yang R, Zhang ZY (2002) Model-based head pose tracking with stereovision. In: Proceedings of the 5th IEEE international conference on automatic face and gesture recognition, FGR’02, p 255

  21. Tu J, Huang T, Xiong Y, Rose T, Quek FKH (2006) Calibrating head pose estimation in videos for meeting room event analysis. In: International conference on image processing, ICIP06, vol 5, pp 3193–3196

  22. McIntosh C, Hamarneh G (2006) Genetic algorithm driven statistically deformed models for medical image segmentation. In: ACM workshop on medical applications of genetic and evolutionary computation workshop

  23. Ghosh P, Mitchell M (2006) Segmentation of medical images using a genetic algorithm. In: 8th Annual conference on genetic and evolutionary computation, pp 1171–1178

  24. Bosman PAN, Thierens D (2001) Exploiting gradient information in continuous iterated density estimation evolutionary algorithms. In: 13th Belgium–Netherlands artificial intelligence conference BNAIC’01, pp 69–76

  25. Smart W, Zhang M (2004) Applying online gradient descent search to genetic programming for object recognition. In: 2nd Workshop on Australasian information security, data mining and web intelligence, and software internationalisation, pp 133–138

  26. Fernandez E, Grana M, Cabello JR (2004) An instantaneous memetic algorithm for illumination correction. In: Congress on evolutionary computation, vol 1, pp 1105–1110

  27. Durand N, Alliot J-M (1999) A combined nelder-mead simplex and genetic algorithm. In: The genetic and evolutionary computation conference, pp 1–7

  28. Skinner BT, Nguyen HT, Liu DK (2007) Hybrid optimisation method using pga and sqp algorithm. In: IEEE symposium on foundations of computational intelligence, pp 73–80

  29. Alker M, Frantz S, Rohr K, Stiehl HS (2002) Hybrid optimization for 3d landmark extraction: genetic Algorithms and conjugate gradient method. Bildverarbeitung fur die Medizin, pp 314–317

  30. Zhang R, Ma S (2007) An efficient hybrid genetic algorithm for continuous optimization problems. Scientia Magna 3: 46–53

    MATH  Google Scholar 

  31. Zdansky M, Pozivil J (2002) Combination genetic/tabu search algorithm for hybrid flowshops optimization. In: Conference on scientific computing algorithms, pp 230–236

  32. Sattar A, Seguier R (2008) GGA-AAM: novel heuristic method of gradient driven genetic algorithm for active appearance models. In: IEEE international conference on digital information management

  33. Lahanas M, Baltas D, Zamboglou N (2003) A hybrid evolutionary algorithm for multi-objective anatomy-based dose optimization in high-dose-rate brachytherapy. Phys Med Biol 48: 399–415

    Article  Google Scholar 

  34. Bosman PAN, de Jong ED (2005) Exploiting gradient information in numerical multi–objective evolutionary optimization. In: Conference on genetic and evolutionary computation, pp 755–762

  35. Wanner EF, Guimaraes FG, Takahashi RHC, Lowther DA, Ramirez JA (2008) Multiobjective memetic algorithms with quadratic approximation-based local search for expensive optimization in electromagnetics. IEEE Trans Magn 44: 1126–1129

    Article  Google Scholar 

  36. Hiwa S, Hiroyasu T, Miki M (2007) Hybrid optimization using direct, ga, and sqp for global exploration. In: Congress on evolutionary computation, pp 1709–1716

  37. Martinez SZ, Coello CAC (2008) A proposal to hybridize multi-objective evolutionary algorithms with non-gradient mathematical programming techniques. In: 10th International conference on parallel problem solving from nature, pp 837–846

  38. Li G, Song G, Wu Y, Zhang J, Wang Q (2006) A multi-objective hybrid genetic based optimization for external beam radiation. In: 27th Annual international conference of the engineering in medicine and biology society, pp 7734–7737

  39. Yildiz AR, Ozturk N, Kaya N, Ozturk F (2007) Hybrid multi-objective shape design optimization using taguchis method and genetic algorithm. Struct Multidiscip Optim 34: 317–332

    Article  Google Scholar 

  40. Matthews I, Baker S (2004) Active appearance models revisited. Int J Comput Vis 60: 135–164

    Article  Google Scholar 

  41. Stegmann MB (2000) Active appearance models: theory, extensions and cases. Master’s thesis, Informatics and Mathematical Modeling

  42. Goodall C (1991) Procrustes methods in the statistical analysis of shape. J R Stat Soc 53: 285–339

    MATH  MathSciNet  Google Scholar 

  43. Gallou SL, Breton G, Garcia C, Seguier R (2006) Distance maps: a robust illumination preprocessing for active appearance models. In: VISAPP06

  44. Pareto V (1896) Cours d’Economie Politique

  45. Goldberg DE (1989) Genetic algorithms in search optimization and machine learning. Addison-Wesley, Reading

    MATH  Google Scholar 

  46. http://www.vision.caltech.edu/bouguetj/calib_doc/index.html. Camera Calibration Toolbox

  47. Pigeon S (1996) M2VTS: multi modal verification for teleservices and security applications

  48. Sim T, Baker S, Bsat M (2002) The cmu pose, illumination, and expression (pie) database. In: IEEE international conference on automatic face and gesture recognition

Download references

Author information

Authors and Affiliations

  1. SUPELEC/IETR, Avenue de la Boulaie, 35576, Cesson Sevigne, France

    Abdul Sattar & Renaud Seguier

Authors
  1. Abdul Sattar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Renaud Seguier
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Abdul Sattar.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Sattar, A., Seguier, R. HMOAM: hybrid multi-objective genetic optimization for facial analysis by appearance model. Memetic Comp. 2, 25–46 (2010). https://doi.org/10.1007/s12293-010-0038-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12293-010-0038-3

Keywords

Search

Navigation