Spatial-Frequency Features Extracting for Facial Image Retrieval from a Big Image Database

Authors

Faculty of Computer and IT Engineering, Shahrood University of Technology, Shahrood, Iran

Abstract

In this paper, a new method is presented to feature extraction from facial images. The main purpose of this paper is probe image retrieval from a big database. By increasing the size of the database, the similarities between people increases and the separation capability decreases. The proposed method increases the distance between peoples in feature space by extracting appropriate features. This method is based on properties of the human vision system and sequentially extracts features in top-down manner. For this purpose, spatial- frequency features are used. In this method, by applying concentric windows in different size on the facial image, the content of each window are mapped to frequency space. The change of frequency components in different windows forms the feature space of image. Then frequency component with high separation capability between face images is remained by appropriate filter.  In the end, the final image is retrieved from database by Euclidean distance criterion. In this paper the FERET database is used. Recognition rate compared with the best current method in similar size of database, with 2% improvement reached to 99%. By increasing database size to 990 classes, 90.4% of recognition rate is achieved.

Keywords


[1] Stan Z. Li and Anil K.. Jain, , Handbook of Face Recognition, Edition 2, Springer Publishing,  2011.
[2] شفیع‌پور یوردشاهی، سیدعربی و آقاگل‌زاده، « بازشناسی چهره بر اساس ظاهر در رشته‌های ویدئویی»، مجله مهندسی برق دانشگاه تبریز، جلد 45، شماره 2، صفحات 75-83، تابستان 1394.
[3] L. Lenc and P. Kral, Face Recognition under Real-world Conditions,  ICAART(2), pp. 250-256, 2013.
[4] صادقی، آیت‌اللّهی و راعی، « بازشناسی حالت چهره با استفاده از نرمالیزاسیون هندسی و تبدیل موجک مختلط Dual-Tree»، مجله مهندسی برق دانشگاه تبریز، جلد 45،اره 3، صفحات 79-87، پاییز 1394.
[5] M. Turk and A. Pentland, “Eigenfaces for recognition", Journal of Cognitive Neuroscience, Vol. 3, no. 1, pp.71-86, 1991.
[6] T. Ahonen, A. Hadid and M. Pietikainen, "Face recognition with local binary patterns", Computer Vision - ECCV, Vol. 302, pp.469-481, 2004.
[7] S. Liao, X. Zhu, Z. Lei, L. Zhang and Stan Z. Li, "Learning multi-scale block local binary patterns for face recognition", Advances in Biometrics, Vol. 4642, pp. 828-837, 2007.
[8] D. H. Wang and P. Conilione, "Machine learning approach for face image retrieval", Neural Computing and Applications, Vol. 21, no. 4, pp.683-694, 2012.
[9] M. J. Er, W. Chen and S. Wu, "High-speed face recognition based on discrete cosine transform and RBF neural networks", IEEE Transactions on Neural Networks , Vol. 16, no. 3, pp. 679-691, 2005.
[10] J. Luo, Y. Ma, E. Takikawa , S. Lao, M. Kawade and B. Lu, "Person-specific SIFT features for face recognition", IEEE International Conference on Acoustics, Speech and Signal Processing, Vol. 2, pp. II-593, 2007.
[11] L. Lenc and P. Král , "A combined SIFT/SURF descriptor for automatic face recognition", Sixth International Conference on Machine VisionVol. 9067, pp. 90672C-90672C, 2013.
[12] M. Zhou , H. Wei and S. Maybank, "Gabor wavelets and AdaBoost in feature selection for face verification", Workshop in application of computer vision, pp.101-109, 2006.
[13] H. Cho, R. Roberts, B. Jung, O. Choi  and S. Moon, "An efficient hybrid face recognition algorithm using PCA and GABOR wavelets", International Journal of Advanced Robotic Systems, Vol. 11, p.59, 2014.
[14] R. Varun, Y. VivekanandKini, K. Manikantan and S. Ramachandran, "Face recognition using hough transform based feature extraction", Procedia Computer Science,Vol. 46, pp.1491-1500, 2015.
[15] T. M. Abhishree, J.  Latha, K.  Manikantan and S.  Ramachandran, "Face recognition using gabor filter based feature extraction with anisotropic diffusion as a pre-processing technique", Procedia Computer Science, Vol. 45, pp. 312-321, 2015.
[16] C. Ma, J. Y. Jung, S. W. Kim and J. S. Ko, "Random projection-based partial feature extraction for robust face recognition", Neurocomputing, Vol. 149, pp. 1232-1244, 2015.
[17] S. Wang and P.Liu, "A new feature extraction method based on the information fusion of entropy matrix and covariance matrix and its application in face recognition", entropy, Vol. 17, no. 7, pp. 4664-4683, 2015.
[18] X. Xie and K. M. Lam, "Face recognition using elastic local reconstruction based on a single face image", Pattern Recognition, Vol. 41, no. 1, pp. 406–417, 2008.
[19] Y. Gao, Y. Qi, "Robust visual similarityretrieval in single model face databases", Pattern Recognition, Vol. 38, no. 7, pp. 1009-1020, 2005.
[20] J. Haddadnia, K. Faez and M. Ahmadi, "A fuzzy hybrid learning algorithm for radial basis function neural network with application in human face recognition", Pattern Recognition, Vol. 36, no. 5, pp. 1187–1202, 2003.
[21] J. Lu, X. Yuan and T. Yahagi, "A method of face recognition based on fuzzy c-means clustering and associated Sub-NNs", IEEE Transactions On Neural Networks, Vol. 18, no. 1, pp. 150 – 160, 2007.
[22] P. Viola and M. Jones,"Rapid object detection using a boosted cascade of simple features", In Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Vol. 1, pp. I-I, 2001.
[23] K. K. Paliwal and L. D. Alsteris, "On The usefulness of STFT phase spectrom in human listening tests", Speech Communication, Vol. 45, no. 2, pp. 153-170, 2004.