Using Multi-Scale Gaussian Derivatives for Appearance-Based Recognition

Abstract:

This paper addresses a novel global appearance-based approach to recognize objects in images by using multi-scale Gaussian derivatives (GDs). Because the GDs distributions of filtered images are almost picked, this obstacles obtaining discriminative binned distributions for each image. For this reason, we execute k-means clustering on each scale of pooled Gaussian derivative set of the instances come from all classes to yield k-cluster centroids for partitioning feature space, thus generating normalized binned marginal distributions for all training and testing samples, which are holistically adaptive to underlying distributions. On similarity matching, we identify each image with a point of product multinomial manifold with boundary, and use the direct sum of geodesic distance metric for sets of binned marginal densities. The promising experimental results on Zurich buildings database (ZuBuD) validate the feasibility and effectiveness of our approach.

• Periodical: Applied Mechanics and Materials (Volumes 513-517)
• Pages: 1561-1564
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.513-517.1561
• Online since: February 2014
• Authors: Yue Zhang*, Chuan Cai Liu, Jian Zou
• Keywords: Appearance-Based Recognition, Gaussian Derivatives (GDs), K-Mean, Multinomial Geometry

References

[1] Sungho Kim, Kuk-Jin Yoon, In-So Kweon. Object recognition using a generalized robust invariant feature and Gestalt's law of proximity and similarity [J]. Pattern Recognition, 2007 41 (2) 726-741.

DOI: 10.1109/cvprw.2006.146

[2] Peter M Roth, Martin Winter. Comparison of appearance based Methods for generic object recognition [J]. Pattern Recognition and Image Analysis, 2004 14 (1) 255-261.

[3] Jian Zou, Chuan-Cai Liu, Yue Zhang, Gui-Fu Lu. Object recognition using Gabor co- occurrence similarity [J]. Pattern Recognition, 2013 46 (1) 434–448.

DOI: 10.1016/j.patcog.2012.06.018

[4] Tony Lindeberg. Scale-Space Theory in Computer Vision [M]. Kluwer Academic Publishers, Boston, (1994).

[5] S. Ravela, R. Manmatha. Gaussian Filtered Representations of Images [M]. Encyclopedia of Electrical and Electronic Engineering, John Webster (Editor), John Wiley, (1999).

DOI: 10.1002/047134608x.w2418

[6] Subhajit Karmakar, Kuntal Ghosh, Sandip Sarkar, Swapan Sen. Design of a low-pass filter by multi-scale even order Gaussian derivatives [J]. Signal Processing, 2006 86 (12) 3923-3933.

DOI: 10.1016/j.sigpro.2006.07.005

[7] Boris Escalante-Ramírez, José Luis Silván-Cárdenas. Advanced modeling of visual information processing: A multi-resolution directional-oriented image transform based on Gaussian derivatives [J]. Signal Processing: Image Communication, 2005 20 (10) 801-812.

DOI: 10.1016/j.image.2005.05.009

[8] R. Brunelli and O. Mich. Histograms analysis for image retrieval [J]. Pattern Recognition, 2001 34 (8) 1625-1637.

DOI: 10.1016/s0031-3203(00)00054-6

[9] C. M. Bishop, Pattern Recognition and Machine Learning [M]. Springer, (2006).

[10] Guy Lebanon. Riemannian geometry and statistical machine learning [D]. Carnegie Mellon University, (2005).