Partially Occluded Face Recognition using Dynamic Time Wrapping

  • Authors

    • Ashish Kumar
    • P Shanmugavadivu
    2018-04-20
    https://doi.org/10.14419/ijet.v7i2.22.11804
  • Partial Occlusion, Face Recognition, Dynamic Time Wrapping, Maximally Stable External Regions (MSER).
  • It is evident that the research contributions in the domain of partially occluded image are quite sparse. This paper presents a novel method, termed as Partially Occluded Face Recognition (POFR) using Maximally Stable External Regions (MSER) feature sets and Dynamic Time Wrapping (DTW). This proposed system works in two phases: Phase-I, creates an annotated database using the non-occluded images, and Phase-II focuses on the detection and recognition of partially occluded probe image, which is also annotated using the mechanism of phase-I. Hence, POFR selectively and dynamically calibrates the annotated database as per the annotation of the probe image. Further, the similarity between the feature sets of the annotated database images and the probe image is computed, using the principle of DTW. The POFR is tested on the face images from University of Stirling dataset and the average accuracy of face recognition is recorded as 88%. This method promises a computational advantage for partially occluded face recognition without any prior reconstruction or synthesis. The POFR finds direct applications in surveillance and security systems.

     

     

  • References

    1. [1] Zhao W, R. Chellappa R, Rosenfeld A, and Phillips PJ “Face Recognition: A Literature Surveyâ€, ACM Computing Surveys (CSUR), Vol. 35, (2003), pp. 399-458

      [2] Sobottka K and Pitas I, “A Novel Method for Automatic Face Segmentation, Face Feature Extraction and Tracking,†Signal Processing: Image Communication, Vol. 12(3), (1998), pp. 263-281

      [3] Zhan B, Monekosso D, Remagnino P and Xu LQ, “Crowd Analysis: A Survey Machine Vision and Applications,†Machine Vision and Applications Vol. 19(5-6), (2008), pp. 345-357

      [4] Cheddad A, Condell J, Curran K, and Mc Kevitt P, “A Skin Tone Detection Algorithm for an Adaptive Approach to Steganography,†Int. J. Signal Processing, Vol. 89(1), (2009), pp. 2465-2478

      [5] Luo Y, Zhang L, Chen Y and Jiang W, “Facial Expression Recognition Algorithm Based on Reverse Co-Salient Regions (RCSR) Features,†4th Int. Conf. on Information Science and Control Engineering (ICISCE), (2017), pp. 326 – 329

      [6] Turk M, and Pentland A, “Eigenfaces for Recognition,†Journal of Cognitive Neuroscience, Vol. 3(1), (1991), pp. 71–86

      [7] Belhumeur P, Hespanha J and Kriegman D, “Eigenfaces Vs. Fisherfaces: Recognition using Class Speciï¬c Linear Projection,†IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19(7), (1997), pp. 711–720

      [8] Pentland A, Moghaddam B and Starner T, “View-based and Modular Eigenspaces for Face Recognition,†Proceedings of IEEE Int. Conf. Computer Vision and Pattern Recognition, (1994), pp. 84–91

      [9] Timo A, Abdenour H and Matti P, “Face Recognition with Local Binary Patterns,†Proceedings of European Conference on Computer Vision, (2004), pp. 469–481

      [10] Chen W, Er MJ and Wu S, “PCA and LDA in DCT Domain,†Pattern Recognition Letters, Vol. 26(15), (2005), pp. 2474–2482

      [11] Ekenel HK, and Stiefelhagen R, “Analysis of Local Appearance-based Face Recognition: Effects of Feature Selection and Feature Normalization,†Proceedings of CVPR Biometrics Workshop, (2006), pp. 34-40

      [12] Liu Z, and Liu C, "Robust Face Recognition using Color Information," Advances in Biometrics, Vol. 5558, (2009) pp. 122–131

      [13] Su Y, Shan S, Chen X and Gao W, “Hierarchical Ensemble of Global and Local Classiï¬ers for Face Recognition,†IEEE Trans. on Image Processing, Vol. 18(8), (2009), pp. 1885–1896

      [14] Fang Y, Tan T and Wang Y, "Fusion of Global and Local Features for Face Veriï¬cation," Proc. of IEEE International Conference on Pattern Recognition, (2002), pp. 382–385

      [15] Wiskott L, Fellous JM, Kruger N and Malsburg CVD, "Face Recognition by Elastic Bunch Graph Matching," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19(7), (1997), pp. 775–779

      [16] Zhang W, Shan S, Gao W and Chen X, "Local Gabor Binary Pattern Histogram Sequence (LGBPHS): A Novel Non-Statistical Model for Face Representation and Recognition," Proc. of IEEE International Conference on Computer Vision, (2005), pp. 786–791

      [17] Reynolds D and Heck L, "An Overview of Automatic Speaker Recognition Technology," Proc. of a Sym. on Humans, Computers and Speech, (2002), pp. 4072-4075

      [18] Muller M, "Dynamic Time Wrapping," Information Retrieval for Music and Motion, XVI, 318, (2007), pp. 69-84, ISBN: 978-3-540-74047-6

      [19] Sakoe H, and Chiba S, “Dynamic Programming Algorithm Optimization for Spoken Word Recognition,†Transactions on Acoustics, Speech and Signal Processing, vol. 26, (1978), pp. 43-49

      [20] Faundez-Zanuy M, “On-Line Signature Recognition Based on VQ-DTW,†Pattern Recognition, vol. 40, (2007), pp. 981-992

      [21] Standley DM, Toh H and Nakamura H, “Detecting Local Structure Similarity in Proteins by Maximizing Number of Equivalent Residues,†Proteins: Structure Function, and Bioinformatics, vol. 57, (2004), pp. 381-391

      [22] Salvoder S, and Chan P, “Towards Accurate Dynamic Time Wrapping in Linear Time Space,†Intelligent Data Analysis, vol. 11, (2007), pp. 561-580

      [23] Berndt D and Clifford J, “Using Dynamic Time Wrapping to find Patterns in Time Series,†AAAI-94 Workshop on Knowledge Discovery in Databases, 1994.

      [24] Kovacs-Vajna ZM, “A Fingerprint Verification System Based on Triangular Matching and Dynamic Time Wrapping,†IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 22, No. 11, (2000)

      [25] Chen X, Wang S and uan X, "Recognition of Partially Ocluded Face by Error Detection with Logarithmic Operator and KPCA," Int. Conf. On Image and Signal Processing, Bio-Medical Engineering and Informatics (CISP-BMIE 2016), (2016), pp.404-464

      [26] Xu Z, XLi V, Liu B, Bi J, Li R and Rui Mao, "Semi-supervised learning in large scale text categorization," Journal of Shanghai Jiaotong University (Science), Vol. 22(3), (2017, pp. 291–302)

      [27] Keogh E. “Exact indexing of dynamic time warping,†Proc. of the 28th VLDB Conference, 2002

      [28] Shanmugavadivu P. and Ashish K, “Rapid Face Detection and Annotation with Loosely Face Geometry,†2nd International Conference on Contemporary Computing and Informatics (IC3I), (2016), pp. 594- 597

      [29] Matas J, Chum O, Urba M, and Pajdla T, "Robust wide baseline stereo from maximally stable extremal regions," Proc. of British Machine Vision Conf., (2002), pp. 384-396

      [30] http://pics.stir.ac.uk/2D_face_sets.htm.

  • Downloads

  • How to Cite

    Kumar, A., & Shanmugavadivu, P. (2018). Partially Occluded Face Recognition using Dynamic Time Wrapping. International Journal of Engineering & Technology, 7(2.22), 31-34. https://doi.org/10.14419/ijet.v7i2.22.11804