Frequency and orientation sensitive texture measures using linear symmetry

An efficient method for computing texture features based on dominant local orientation is introduced. The features are computed as a Laplacian pyramid is built. At each level of the Laplacian pyramid, the linear symmetry feature is computed. This feature is anisotropic and estimates the optimal local orientation in the Least Square Error (LSE) sense. It is complex valued and hence consists of two components, the local orientation estimate and its confidence measure based on the error. The algorithm is based on convolutions with simple separable filters and pixel-wise non-linear arithmetic operations. These properties allow highly parallel implementation, for example on a pyramid machine, yielding real time applications. Compara­ tive experimental results are presented using the feature for unsupervised segmentation on test images of natural aerial image textures. Zusammenfassung. Es wird eine effiziente Methode zur Berechnung von Textur-Merkmalen eingefiihrt, die auf einer lokalen Orientierung basiert. Die Merkmale werden entsprechend dem Bau einer Laplace-Pyramide berechnet. Auf jeder Stufe der Laplace-Pyramide werden die Iinearen Symmetrie-Merkmale ermittelt. Solche Merkmale sind anisotrop und schiitzen die optimale lokale Orientierung im Sinne des kleinsten quadratischen Fehlers (LSE). Sie sind komplexwertig und bestehen daher aus zwei Komponenten, dem Schiitzwert der lokalen Orientierung und seinem auf dem Pehler basierenden Vertrauensmafl. Der Algorithm us basiert auf Faltungen mit Hilfe separierbarer Filter und pixelweiser nichlinearer arithmetischer Operiltionen. Diese Eigenschaften erlauben ein hohes Mafl paralleler Implementierung, zum Beispiel auf einer Pyramide-Maschine, und eroffnen die Moglichkeit der Echtzeit-Verarbeitung. Vergleichende experimentelle Resultate werden wiedergegeben, die von den Eigenschaften der 'unsupervised' Segmentierung von Testbildern und natiirlichen Texturen von Luftaufnahmen Gebrauch machen.

[1]  James D. Broffitt,et al.  6 Nonparametric classification , 1982, Classification, Pattern Recognition and Reduction of Dimensionality.

[2]  Peter J. Burt,et al.  Smart sensing within a pyramid vision machine , 1988, Proc. IEEE.

[3]  P. J. Burt,et al.  Fast Filter Transforms for Image Processing , 1981 .

[4]  Dennis Gabor,et al.  Theory of communication , 1946 .

[5]  Ruzena Bajcsy,et al.  Texture gradient as a depth cue , 1976 .

[6]  Peter J. Rousseeuw,et al.  Robust regression and outlier detection , 1987 .

[7]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[8]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  J. Bigun,et al.  Optimal Orientation Detection of Linear Symmetry , 1987, ICCV 1987.

[10]  E. Wigner On the quantum correction for thermodynamic equilibrium , 1932 .

[11]  Michael Spann,et al.  A quad-tree approach to image segmentation which combines statistical and spatial information , 1985, Pattern Recognit..

[12]  C Blakemore,et al.  On the existence of neurones in the human visual system selectively sensitive to the orientation and size of retinal images , 1969, The Journal of physiology.

[13]  Michael Unser,et al.  Sum and Difference Histograms for Texture Classification , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  D H Hubel,et al.  Brain mechanisms of vision. , 1979, Scientific American.

[15]  Béla Julesz,et al.  Visual Pattern Discrimination , 1962, IRE Trans. Inf. Theory.

[16]  A. Grossmann,et al.  DECOMPOSITION OF HARDY FUNCTIONS INTO SQUARE INTEGRABLE WAVELETS OF CONSTANT SHAPE , 1984 .

[17]  Johan Wiklund,et al.  Multidimensional Orientation Estimation with Applications to Texture Analysis and Optical Flow , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  K. Laws Textured Image Segmentation , 1980 .

[19]  G. Granlund In search of a general picture processing operator , 1978 .

[20]  M. Unser Local linear transforms for texture measurements , 1986 .

[21]  David J. Fleet,et al.  Hierarchical Construction of Orientation and Velocity Selective Filters , 1989, IEEE Trans. Pattern Anal. Mach. Intell..