Recognition of Images Degraded by Gaussian Blur

In this paper, we propose a new theory of invariants to Gaussian blur. We introduce a notion of a primordial image as a canonical form of all Gaussian blur-equivalent images. The primordial image is defined in spectral domain by means of projection operators. We prove that the moments of the primordial image are invariant to Gaussian blur and we derive recursive formulas for their direct computation without actually constructing the primordial image itself. We show how to extend their invariance also to image rotation. The application of these invariants is in blur-invariant image comparison and recognition. In the experimental part, we perform an exhaustive comparison with two main competitors: 1) the Zhang distance and 2) the local phase quantization.

[1]  Zhengwu Zhang,et al.  Gaussian Blurring-Invariant Comparison of Signals and Images , 2013, IEEE Transactions on Image Processing.

[2]  Rama Chellappa,et al.  A Blur-Robust Descriptor with Applications to Face Recognition , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  A. Carasso.  THE APEX METHOD IN IMAGE SHARPENING AND THE USE OF LOW EXPONENT LÉVY STABLE LAWS , 2002 .

[4]  Wai-kuen Cham,et al.  Single-Image Refocusing and Defocusing , 2012, IEEE Transactions on Image Processing.

[5]  Qian Liu,et al.  Image recognition by combined affine and blur Tchebichef moment invariants , 2011, 2011 4th International Congress on Image and Signal Processing.

[6]  Ying Zhang,et al.  Determination of blur and affine combined invariants by normalization , 2002, Pattern Recognit..

[7]  Huazhong Shu,et al.  Combined Invariants to Similarity Transformation and to Blur Using Orthogonal Zernike Moments , 2011, IEEE Transactions on Image Processing.

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

[9]  Y. Bentoutou,et al.  A 3-D space-time motion detection for an invariant image registration approach in digital subtraction angiography , 2005, Comput. Vis. Image Underst..

[10]  J. Lu,et al.  Blurred image recognition based on phase invariants , 1999 .

[11]  Steven W. Zucker,et al.  Local Scale Control for Edge Detection and Blur Estimation , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Jan Flusser,et al.  On the independence of rotation moment invariants , 2000, Pattern Recognit..

[13]  LunBo Li,et al.  Optimizing the Performance of Probabilistic Neural Networks Using PSO in the Task of Traffic Sign Recognition , 2008, ICIC.

[14]  Jan Flusser,et al.  Registration of Images With $N$ -Fold Dihedral Blur , 2015, IEEE Transactions on Image Processing.

[15]  Eric C. Larson,et al.  Most apparent distortion: full-reference image quality assessment and the role of strategy , 2010, J. Electronic Imaging.

[16]  Li Li,et al.  A two-stage registration algorithm for oil spill aerial image by invariants-based similarity and improved ICP , 2011 .

[17]  Jan Flusser,et al.  Estimation of camera planar motion from blurred images , 2002, Proceedings. International Conference on Image Processing.

[18]  R. Paramesran,et al.  Derivation of blur-invariant features using orthogonal Legendre moments , 2007 .

[19]  Min Liu,et al.  Combined invariants to blur and rotation using Zernike moment descriptors , 2010, Pattern Analysis and Applications.

[20]  Y. Bentoutou,et al.  Automatic extraction of control points for digital subtraction angiography image enhancement , 2003, 2003 IEEE Nuclear Science Symposium. Conference Record (IEEE Cat. No.03CH37515).

[21]  Jin Liu,et al.  Recognition of the blurred image by complex moment invariants , 2005, Pattern Recognit. Lett..

[22]  Kidiyo Kpalma,et al.  An automatic image registration for applications in remote sensing , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[23]  Jan Flusser,et al.  Degraded Image Analysis: An Invariant Approach , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  Jan Flusser,et al.  Image features invariant with respect to blur , 1995, Pattern Recognit..

[25]  Babak Mahdian,et al.  Detection of Near-Duplicated Image Regions , 2008, Computer Recognition Systems 2.

[26]  Jan Flusser,et al.  A new wavelet-based measure of image focus , 2002, Pattern Recognit. Lett..

[27]  Rama Chellappa,et al.  Blurring-invariant Riemannian metrics for comparing signals and images , 2011, 2011 International Conference on Computer Vision.

[28]  J Flusser,et al.  Recognition of blurred images by the method of moments , 1996, IEEE Trans. Image Process..

[29]  Hexin Chen,et al.  Combining blur and affine moment invariants in object recognition , 2003, International Symposium on Instrumentation and Control Technology.

[30]  Jan Flusser,et al.  Blur Invariant Translational Image Registration for $N$-fold Symmetric Blurs , 2013, IEEE Transactions on Image Processing.

[31]  Barmak Honarvar,et al.  Image reconstruction from a complete set of geometric and complex moments , 2014, Signal Process..

[32]  Alan C. Bovik,et al.  A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms , 2006, IEEE Transactions on Image Processing.

[33]  Barmak Honarvar Shakibaei and Jan Flusser.  Image Deconvolution in the Moment Domain , 2014 .

[34]  S.X. Hu,et al.  Accurate point matching based on combined moment invariants and their new statistical metric , 2007, 2007 International Conference on Wavelet Analysis and Pattern Recognition.

[35]  Yaacob Sazali,et al.  A simple sign language recognition system using affine moment blur invariant features , 2010 .

[36]  J. Flusser,et al.  Moments and Moment Invariants in Pattern Recognition , 2009 .

[37]  Ville Ojansivu,et al.  Blur Insensitive Texture Classification Using Local Phase Quantization , 2008, ICISP.

[38]  Stan Z. Li,et al.  The HFB Face Database for Heterogeneous Face Biometrics research , 2009, 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[39]  Xiao Jing Shen,et al.  Monocular Visual Servoing Based on Image Moments(Image) , 2004 .

[40]  Babak Mahdian,et al.  Detection of copy-move forgery using a method based on blur moment invariants. , 2007, Forensic science international.

[41]  Ville Ojansivu,et al.  Blur invariant pattern recognition and registration in the Fourier domain , 2009 .

[42]  Ying Zhang,et al.  Estimation of motion parameters from blurred images , 2000, Pattern Recognit. Lett..

[43]  Chen Guangsheng,et al.  Dynamic wood slice recognition using image blur information , 2012 .

[44]  Timo Ahonen,et al.  Recognition of blurred faces using Local Phase Quantization , 2008, 2008 19th International Conference on Pattern Recognition.

[45]  YANI ZHANG,et al.  Neural Network Based Classification Using Blur Degradation and Affine Deformation Invariant Features , 2001, Int. J. Artif. Intell. Tools.

[46]  Huazhong Shu,et al.  Blurred Image Recognition by Legendre Moment Invariants , 2010, IEEE Transactions on Image Processing.

[47]  Ville Ojansivu,et al.  Image Registration Using Blur-Invariant Phase Correlation , 2007, IEEE Signal Processing Letters.

[48]  Guangfu Ma,et al.  Recognition of Degraded Traffic Sign Symbols Using PNN and Combined Blur and Affine Invariants , 2008, 2008 Fourth International Conference on Natural Computation.

[49]  Jiangtao Cui,et al.  Combined blur, translation, scale and rotation invariant image recognition by Radon and pseudo-Fourier-Mellin transforms , 2012, Pattern Recognit..

[50]  Jan Flusser,et al.  Combined Invariants to Linear Filtering and Rotation , 1999, Int. J. Pattern Recognit. Artif. Intell..

[51]  Hongzhi Song,et al.  Identification Algorithm of Winged Insects Based on Hybrid Moment Invariants , 2007, 2007 1st International Conference on Bioinformatics and Biomedical Engineering.

[52]  J. Flusser,et al.  Invariant-based registration of rotated and blurred images , 1999, IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 (Cat. No.99CH36293).

[53]  Dong Yi,et al.  Face Matching Between Near Infrared and Visible Light Images , 2007, ICB.

[54]  Yongtian Wang,et al.  Blur Invariant Phase Correlation in X-Ray Digital Subtraction Angiography , 2007, 2007 IEEE/ICME International Conference on Complex Medical Engineering.

[55]  Peng Zhao,et al.  Dynamic timber cell recognition using two-dimensional image measurement machine. , 2011, The Review of scientific instruments.

[57]  Hongqing Zhu,et al.  Degraded image analysis using Zernike moment invariants , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[58]  Esa Rahtu,et al.  Rotation invariant local phase quantization for blur insensitive texture analysis , 2008, 2008 19th International Conference on Pattern Recognition.

[59]  Jan Flusser,et al.  Blur Invariants Constructed From Arbitrary Moments , 2011, IEEE Transactions on Image Processing.

[60]  Jan Flusser,et al.  Multichannel blind iterative image restoration , 2003, IEEE Trans. Image Process..

[61]  Thierry Blu,et al.  A Novel SURE-Based Criterion for Parametric PSF Estimation , 2015, IEEE Transactions on Image Processing.

[62]  Jan Flusser,et al.  Recognition of Images Degraded by Linear Motion Blur without Restoration , 1994, Theoretical Foundations of Computer Vision.

[63]  Timo Ahonen,et al.  Local phase quantization for blur-insensitive image analysis , 2012, Image Vis. Comput..

[64]  Jan Flusser,et al.  Invariants to convolution with circularly symmetric PSF , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[65]  Jan Flusser,et al.  Projection Operators and Moment Invariants to Image Blurring , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[66]  Jan Flusser,et al.  On the recognition of wood slices by means of blur invariants , 2013 .

[67]  Huazhong Shu,et al.  Blurred Image Registration by Combined Invariant of Legendre Moment and Harris-Laplace Detector , 2010, 2010 Fourth Pacific-Rim Symposium on Image and Video Technology.

[68]  Ville Ojansivu,et al.  A Method for Blur and Affine Invariant Object Recognition Using Phase-Only Bispectrum , 2008, ICIAR.

[69]  Jan Flusser,et al.  Combined blur and affine moment invariants and their use in pattern recognition , 2003, Pattern Recognit..

[70]  Limin Luo,et al.  M-SIFT: a new descriptor based on Legendre moments and SIFT , 2012, Other Conferences.

[71]  Y. Bentoutou,et al.  An invariant approach for image registration in digital subtraction angiography , 2002, Pattern Recognit..

[72]  Huazhong Shu,et al.  Image recognition by combined invariants of legendre moment , 2010, The 2010 IEEE International Conference on Information and Automation.