Review Jonas Mendonc¸a Targino
VI. C ONCLUS OES DA REVIS ˜ AO ˜
Este trabalho teve como principal objetivo analisar as abor- dagens existentes no que se refere as t´ecnicas de detecc¸˜ao e reconstruc¸˜ao de oclus˜ao facial. Avaliando os 31 estudos, foi
poss´ıvel notar que a abordagem baseada em modelos precisa ser mais estudada por meio de iniciativas a aumentar sua eficiˆencia, visto que essas t´ecnicas apresentam maior robustez quando aplicadas aos cen´arios n˜ao controlados por n˜ao ser sens´ıvel a iluminac¸˜ao.
Constatou-se nessa RS que a produc¸˜ao cient´ıfica, tratando o problema de detecc¸˜ao e reconstruc¸˜ao de oclus˜oes parciais em imagens de face, est´a estabilizada em 2,58 estudos por ano, sendo poss´ıvel enxergar tendˆencias de pesquisas na ´area. Entretanto, ´e poss´ıvel perceber que essa taxa ´e baixa e que a ´area ainda ´e pouco estudada por apresentar in´umeras variac¸˜oes de iluminac¸˜ao, pose, express˜ao e oclus˜ao. Dessa forma, esta RS contribui com o desenvolvimento da ´area ao apontar, a partir de um processo sistem´atico de an´alise da ´area, as lacunas que precisam ser investigadas e quais s˜ao as t´ecnicas, as formas de avaliac¸˜ao e comparac¸˜ao e as bases de dados existentes.
Este trabalho serve como um ponto de referˆencia para ana- lisar os objetivos, progressos e consequentemente as dificul- dades apresentadas pela comunidade pesquisadora da ´area de reconhecimento facial em ambientes de coleta n˜ao intrusivos. Com essa RS foi poss´ıvel notar que apenas 11 (35,48%) trabalhos apresentaram o algoritmo da t´ecnica proposta, sendo poss´ıvel inferir que a indisponibilidade do c´odigo e do pseu- doc´odigo podem atuar como vari´aveis que inviabilizem o pro- cesso de replicac¸˜ao da t´ecnica. Podemos ver esses resultados analisando os crit´erios de qualidade CQ05 e CQ06 presentes na tabela VIII.
REFERENCIASˆ
[1] A. Aisha, S. Muhammad, S. J. Hussain, and R. Mudassar. Face recognition invariant to partial occlusions. KSII Transactions on Internet and Information Systems (TIIS), 8(7):2496–2511, 2014.
[2] N. Alyuz, B. Gokberk, and L. Akarun. 3-d face recognition under occlusion using masked projection. IEEE Transactions on Information Forensics and Security, 8(5):789–802, 2013.
[3] N. Alyuz, B. Gokberk, and L. Akarun. Detection of realistic facial occlusions for robust 3d face recognition. In Pattern Recognition (ICPR), 2014 22nd International Conference on, pages 375–380. IEEE, 2014. [4] N. Aly¨uz, B. G¨okberk, L. Spreeuwers, R. Veldhuis, and L. Akarun.
Robust 3d face recognition in the presence of realistic occlusions. In Biometrics (ICB), 2012 5th IAPR International Conference on, pages 111–118. IEEE, 2012.
[5] W. Bellil, H. Brahim, and C. B. Amar. Gappy wavelet neural network for 3d occluded faces: detection and recognition. Multimedia Tools and Applications, 75(1):365–380, 2016.
[6] A. Bindu and C. R. Kumar. Inpainting for big data. In Signal and Image Processing (ICSIP), 2014 Fifth International Conference on, pages 62– 67. IEEE, 2014.
[7] H. Chandel and S. Vatta. Occlusion detection and handling: a review. International Journal of Computer Applications, 120(10), 2015. [8] C.-C. Chiang and Z.-W. Chen. Recognizing partially-occluded faces
by recovering normalized facial appearance. International Journal of Innovative Comp., Information and Control, 7(11):6219–6234, 2011. [9] M. De Marsico, M. Nappi, and D. Riccio. Faro: Face recognition against
occlusions and expression variations. IEEE Transactions on Systems and Cybernetics-Part A: Systems and Humans, 40(1):121–132, 2010. [10] Y. Deng, Q. Dai, and Z. Zhang. Graph laplace for occluded face
completion and recognition. IEEE Transactions on Image Processing, 20(8):2329–2338, 2011.
[11] P. Dou, L. Zhang, Y. Wu, S. K. Shah, and I. A. Kakadiaris. Pose- robust face signature for multi-view face recognition. In Biometrics Theory, Applications and Systems (BTAS), 2015 IEEE 7th International Conference on, pages 1–8. IEEE, 2015.
[12] S. Eum, J. K. Suhr, and J. Kim. Face recognizability evaluation for atm applications with exceptional occlusion handling. In Computer Vision and Pattern Recognition Workshops (CVPRW), 2011 IEEE Computer Society Conference on, pages 82–89. IEEE, 2011.
[13] T. Hosoi, S. Nagashima, K. Kobayashi, K. Ito, and T. Aoki. Restoring occluded regions using fw-pca for face recognition. In Computer Vision and Pattern Recognition Workshops (CVPRW), 2012 IEEE Computer Society Conference on, pages 23–30. IEEE, 2012.
[14] S.-M. Huang and J.-F. Yang. Subface hidden markov models coupled with a universal occlusion model for partially occluded face recognition. IET biometrics, 1(3):149–159, 2012.
[15] B. Kitchenham. Procedures for performing systematic reviews. Keele, UK, Keele University, 33(2004):1–26, 2004.
[16] J. Lai and X. Jiang. Robust face recognition using trimmed linear regression. In ICASSP, pages 2979–2983, 2013.
[17] X.-X. Li, D.-Q. Dai, X.-F. Zhang, and C.-X. Ren. Structured sparse error coding for face recognition with occlusion. IEEE transactions on image processing, 22(5):1889–1900, 2013.
[18] R. Min and J.-L. Dugelay. Inpainting of sparse occlusion in face recognition. In Image Processing (ICIP), 2012 19th IEEE International Conference on, pages 1425–1428. IEEE, 2012.
[19] G. Passalis, P. Perakis, T. Theoharis, and I. A. Kakadiaris. Using facial symmetry to handle pose variations in real-world 3d face recogni- tion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(10):1938–1951, 2011.
[20] M. Sharif, S. Mohsin, and M. Y. Javed. A survey: Face recognition techniques. Research Journal of Applied Sciences, Engineering and Technology, 4(23):4979–4990, 2012.
[21] M. Sharma, S. Prakash, and P. Gupta. An efficient partial occluded face recognition system. Neurocomputing, 116:231–241, 2013.
[22] J. Shermina and V. Vasudevan. Recognition of the face images with occlusion and expression. International Journal of Pattern Recognition and Artificial Intelligence, 26(03):1256006, 2012.
[23] M. Song, D. Tao, X. Huang, C. Chen, and J. Bu. Three-dimensional face reconstruction from a single image by a coupled rbf network. IEEE Transactions on Image Processing, 21(5):2887–2897, 2012.
[24] M. Storer, M. Urschler, and H. Bischof. Occlusion detection for icao compliant facial photographs. In Computer Vision and Pattern Recognition Workshops (CVPRW), pages 122–129. IEEE, 2010. [25] Y. Su, H. Ai, and S. Lao. Multi-view face alignment using 3d shape
model for view estimation. In International Conference on Biometrics, pages 179–188. Springer, 2009.
[26] X. Tan, S. Chen, Z.-H. Zhou, and F. Zhang. Recognizing partially occluded, expression variant faces from single training image per person with som and soft k-nn ensemble. IEEE Transactions on Neural Networks, 16(4):875–886, 2005.
[27] D. Venkatakrishnan, C. Hariram, N. Anantharaj, and A. Muthulakshmi. 3d face recognition with occlusions using fisher faces projection. Applied Mechanics & Materials, (573), 2014.
[28] X. Wei, C.-T. Li, and Y. Hu. Robust face recognition with occlusions in both reference and query images. In Biometrics and Forensics (IWBF), 2013 International Workshop on, pages 1–4. IEEE, 2013.
[29] X. Wei, C.-T. Li, Z. Lei, D. Yi, and S. Z. Li. Dynamic image-to- class warping for occluded face recognition. IEEE Transactions on Information Forensics and Security, 9(12):2035–2050, 2014.
[30] J. Wright, A. Y. Yang, A. Ganesh, S. S. Sastry, and Y. Ma. Robust face recognition via sparse representation. IEEE transactions on pattern analysis and machine intelligence, 31(2):210–227, 2009.
[31] S. Yan, H. Wang, J. Liu, X. Tang, and T. S. Huang. Misalignment-robust face recognition. IEEE transactions on image processing, 19(4):1087– 1096, 2010.
[32] M. Yang, Z. Feng, S. C. Shiu, and L. Zhang. Fast and robust face recognition via coding residual map learning based adaptive masking. Pattern Recognition, 47(2):535–543, 2014.
[33] B. Zhang, P. Cerone, and Y. Gao. Robust face recognition by hierarchical kernel associative memory models based on spatial domain gabor transforms. Journal of Multimedia, 1(4):1–10, 2006.
[34] Y. Zhang, Y. Lu, H. Wu, C. Wen, and C. Ge. Face occlusion detection using cascaded convolutional neural network. In Chinese Conference on Biometric Recognition, pages 720–727. Springer, 2016.
[35] J. Zhu, D. Cao, S. Liu, Z. Lei, and S. Z. Li. Discriminant analysis with gabor phase for robust face recognition. In Biometrics (ICB), 2012 5th IAPR International Conference on, pages 13–18. IEEE, 2012.