2D/3D rotation-invariant detection using equivariant filters and kernel weighted mapping

In many vision problems, rotation-invariant analysis is necessary or preferred. Popular solutions are mainly based on pose normalization or brute-force learning, neglecting the intrinsic properties of rotations. In this paper, we present a rotation invariant detection approach built on the equivariant filter framework, with a new model for learning the filtering behavior. The special properties of the harmonic basis, which is related to the irreducible representation of the rotation group, directly guarantees rotation invariance of the whole approach. The proposed kernel weighted mapping ensures high learning capability while respecting the invariance constraint. We demonstrate its performance on 2D object detection with in-plane rotations, and a 3D application on rotation-invariant landmark detection in microscopic volumetric data.

[1]  Ioannis A. Kakadiaris,et al.  Landmark/image-based deformable registration of gene expression data , 2011, CVPR 2011.

[2]  Thomas Brox,et al.  Fast Rotation Invariant 3D Feature Computation Utilizing Efficient Local Neighborhood Operators , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Reiner Lenz,et al.  Group Theoretical Methods in Image Processing , 1990, Lecture Notes in Computer Science.

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

[5]  Thomas Brox,et al.  ViBE-Z: a framework for 3D virtual colocalization analysis in zebrafish larval brains , 2012, Nature Methods.

[6]  Edward H. Adelson,et al.  The Design and Use of Steerable Filters , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Thomas S. Huang,et al.  Image Classification Using Super-Vector Coding of Local Image Descriptors , 2010, ECCV.

[8]  Giovanni Jacovitti,et al.  Multiresolution circular harmonic decomposition , 2000, IEEE Trans. Signal Process..

[9]  Hans-Peter Seidel,et al.  A Higher-Order Structure Tensor , 2009 .

[10]  Qing Wang,et al.  Rotational Invariance Based on Fourier Analysis in Polar and Spherical Coordinates , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Hans Burkhardt,et al.  Harmonic Filters for Generic Feature Detection in 3D , 2009, DAGM-Symposium.

[12]  Tomás Werner,et al.  A Linear Programming Approach to Max-Sum Problem: A Review , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Vincent Lepetit,et al.  Fast Keypoint Recognition Using Random Ferns , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Luc Van Gool,et al.  Hough Transform and 3D SURF for Robust Three Dimensional Classification , 2010, ECCV.

[15]  Ah Chung Tsoi,et al.  Face recognition: a convolutional neural-network approach , 1997, IEEE Trans. Neural Networks.

[16]  M. E. Rose.  Elementary Theory of Angular Momentum , 1957 .

[17]  Anne E Carpenter,et al.  Visualization of image data from cells to organisms , 2010, Nature Methods.

[18]  Hans Burkhardt,et al.  General-purpose object recognition in 3D volume data sets using gray-scale invariants - classification of airborne pollen-grains recorded with a confocal laser scanning microscope , 2002, Object recognition supported by user interaction for service robots.

[19]  Hans Burkhardt,et al.  Spherical Tensor Calculus for Local Adaptive Filtering , 2009, Tensors in Image Processing and Computer Vision.

[20]  Bernt Schiele,et al.  Robust Object Detection with Interleaved Categorization and Segmentation , 2008, International Journal of Computer Vision.

[21]  Kun Liu,et al.  3D Rotation-Invariant Description from Tensor Operation on Spherical HOG Field , 2011, BMVC.

[22]  Francesc Moreno-Noguer,et al.  Efficient rotation invariant object detection using boosted Random Ferns , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[23]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[24]  Matthew B. Blaschko,et al.  Learning equivariant structured output SVM regressors , 2011, 2011 International Conference on Computer Vision.

[25]  Vladimir Pekar,et al.  Full orientation invariance and improved feature selectivity of 3D SIFT with application to medical image analysis , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[26]  Tobias Höllerer,et al.  Improving Keypoint Orientation Assignment , 2011, BMVC.

[27]  Hans Burkhardt,et al.  Equivariant Holomorphic Filters for Contour Denoising and Rapid Object Detection , 2008, IEEE Transactions on Image Processing.