Multi-scale gist feature manifold for building recognition

Multi-scale gist (MS-gist) feature manifold for building recognition is presented in the paper. It is described as a two-stage model. In the first stage, we extract the multi-scale gist features that represent the structural information of the building images. Since the MS-gist features are extrinsically high dimensional and intrinsically low dimensional, in the second stage, an enhanced fuzzy local maximal marginal embedding (EFLMME) algorithm is proposed to project MS-gist feature manifold to low-dimensional subspace. EFLMME aims to preserve local intra-class geometry and maximize local interclass margin separability of MS-gist feature manifold of different classes at the same time. To evaluate the performance of our proposed model, experiments were carried out on the Sheffield buildings database, compared with the existing works: (a) the visual gist based building recognition model (VGBR) and (b) the hierarchical building recognition model (HBR). Moreover, EFLMME is evaluated on Sheffield buildings database compared with some linear dimensionality reduction methods. The results show that the proposed model is superior to other models in practice of building recognition and can handle the building recognition problem caused by rotations, variant lighting conditions and occlusions very well.

[1]  Dacheng Tao,et al.  Biologically Inspired Feature Manifold for Scene Classification , 2010, IEEE Transactions on Image Processing.

[2]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[3]  James M. Keller,et al.  A fuzzy K-nearest neighbor algorithm , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[4]  Luc Van Gool,et al.  Simultaneous Object Recognition and Segmentation by Image Exploration , 2004, ECCV.

[5]  Zhong Jin,et al.  Two-Dimensional Local Graph Embedding Discriminant Analysis(F2DLGEDA) with Its Application to Face and Palm Biometrics , 2009, 2009 Chinese Conference on Pattern Recognition.

[6]  Anil K. Jain,et al.  Statistical Pattern Recognition: A Review , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Xuelong Li,et al.  General Averaged Divergence Analysis , 2007, Seventh IEEE International Conference on Data Mining (ICDM 2007).

[8]  Andrew Zisserman,et al.  A Statistical Approach to Texture Classification from Single Images , 2004, International Journal of Computer Vision.

[9]  Jing Li,et al.  Subspace learning-based dimensionality reduction in building recognition , 2009, Neurocomputing.

[10]  I. Jolliffe.  Principal Component Analysis , 2002 .

[11]  Barbara Caputo,et al.  Towards robust place recognition for robot localization , 2008, 2008 IEEE International Conference on Robotics and Automation.

[12]  Antonio Torralba,et al.  Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope , 2001, International Journal of Computer Vision.

[13]  Zhonghua Liu,et al.  Two-Dimensional Local Graph Embedding Discriminant Analysis(F2DLGEDA) with Its Application to Face and Palm Biometrics , 2009 .

[14]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[15]  Shimon Ullman,et al.  Structural Saliency: The Detection Of Globally Salient Structures using A Locally Connected Network , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[16]  Antonio Torralba,et al.  Contextual Priming for Object Detection , 2003, International Journal of Computer Vision.

[17]  G. McLachlan.  Discriminant Analysis and Statistical Pattern Recognition , 1992 .

[18]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[19]  Honggang Zhang,et al.  Comments on "Globally Maximizing, Locally Minimizing: Unsupervised Discriminant Projection with Application to Face and Palm Biometrics" , 2007, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[21]  Laurent Itti,et al.  Robot steering with spectral image information , 2005, IEEE Transactions on Robotics.

[22]  Abel G. Oliva,et al.  Gist of a scene , 2005 .

[23]  Jake K. Aggarwal,et al.  Applying perceptual grouping to content-based image retrieval: building images , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[24]  Lucas Paletta,et al.  Urban Object Recognition from Informative Local Features , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[25]  A. Treisman,et al.  A feature-integration theory of attention , 1980, Cognitive Psychology.

[26]  Kenji Kawano,et al.  Global and fine information coded by single neurons in the temporal visual cortex , 1999, Nature.

[27]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[28]  A. Treisman,et al.  Representation of statistical properties , 2003, Vision Research.

[29]  Dacheng Tao,et al.  Harmonic mean for subspace selection , 2008, 2008 19th International Conference on Pattern Recognition.

[30]  Luc Van Gool,et al.  Edinburgh Research Explorer Simultaneous Object Recognition and Segmentation by Image Exploration , 2022 .

[31]  Mikhail Belkin,et al.  Laplacian Eigenmaps for Dimensionality Reduction and Data Representation , 2003, Neural Computation.

[32]  Xindong Wu,et al.  Manifold elastic net: a unified framework for sparse dimension reduction , 2010, Data Mining and Knowledge Discovery.

[33]  Cordelia Schmid,et al.  Selection of scale-invariant parts for object class recognition , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[34]  Xiaofei He,et al.  Locality Preserving Projections , 2003, NIPS.

[35]  Xuelong Li,et al.  Geometric Mean for Subspace Selection , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  Pietro Perona,et al.  Object class recognition by unsupervised scale-invariant learning , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[37]  Xuelong Li,et al.  Patch Alignment for Dimensionality Reduction , 2009, IEEE Transactions on Knowledge and Data Engineering.

[38]  Antonio Torralba,et al.  Depth Estimation from Image Structure , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[39]  Manish Kumar,et al.  Building Detection from Mobile Imagery Using Informative SIFT Descriptors , 2005, SCIA.

[40]  Yi Li,et al.  Consistent line clusters for building recognition in CBIR , 2002, Object recognition supported by user interaction for service robots.

[41]  Wei Zhang,et al.  Hierarchical building recognition , 2007, Image Vis. Comput..

[42]  Walterio Mayol-Cuevas,et al.  Building recognition for mobile devices: incorporating positional information with visual features , 2005 .

[43]  Witold Pedrycz,et al.  Face recognition using a fuzzy fisherface classifier , 2005, Pattern Recognit..

[44]  Mikhail Belkin,et al.  Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering , 2001, NIPS.

[45]  Terry Caelli,et al.  Building Detection Using Bayesian Networks , 2000, Int. J. Pattern Recognit. Artif. Intell..

[46]  Jian Yang,et al.  Globally Maximizing, Locally Minimizing: Unsupervised Discriminant Projection with Applications to Face and Palm Biometrics , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[47]  A. Oliva,et al.  Coarse Blobs or Fine Edges? Evidence That Information Diagnosticity Changes the Perception of Complex Visual Stimuli , 1997, Cognitive Psychology.

[48]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.