This paper presents an effective texture descriptor invariant to translation, scaling, and rotation for texture-based image retrieval applications. In order to find the minimal matching distance between two descriptors, existing frequency-layout descriptors require a lot of distance calculations with every possible combination of scaling and rotation values because they are not invariant to geo...

This paper proposes an automated system for rotation and scale invariant color logo recognition. Colored logo images are recognized using one shape feature namely Moments Invariant and a color feature namely Color Moments. Shape of the logo is modeled using the first two central normalized Hu's invariant moments while color is modeled using the mean, standard deviation, skewness and kurtos...

A simple scheme is presented for modifying geometric moments to use geodesic distances. This provides a set of global shape descriptors that are invariant to bending as well as rotation, translation and scale.

This correspondence addresses the problem of rotation, scale, and translation invariant recognition of images. A new set of Manuscript received August 29, 1988; revised October 13, 1989. Recommended for acceptance by C. Y. Suen. This work was supported in part by the Defense Advanced Research Projects Agency under Grant MDAA. Khotanzad is with the Image Processing and Analysis Laboratory, Depar...

problem statement: Digital image watermarking is the most popular method for image authentication, copyright protection and content description. Zernike moments are the most widely used moments in image processing and pattern recognition. The magnitudes of Zernike moments are rotation invariant so they can be used just as a watermark signal or be further modified to carry embedded data. The com...

This paper introduces a robust image watermark based on an invariant image feature vector. Normalized Zernike moments of an image are used as the vector. The watermark is generated by modifying the vector. Watermark signal is designed with Zernike moments. The signal is added to the cover image in the spatial domain after the reconstruction process. We extract the feature vector from the modifi...

In this paper, we express the Newman–Penrose constants in terms of the Geroch–Hansen multipole moments for stationary spacetimes. These expressions are translation-invariant combinations of the multipole moments up to quadrupole order, which do not normally vanish.

Image registration is an important and fundamental task in image processing used to match two different images. Given two or more different images to be registered, image registration estimates the parameters of the geometrical transformation model that maps the sensed images back to its reference image. A feature-based approach to automated imageto-image registration is presented. The characte...

Moment invariants have found wide application in pattern recognition since it was proposed. The main difficulty in the application of moment invariants is the computation of the moment invariants. The presented paper is devoted to elaboration of new methods of image invariant recognition in Eucledian and non–Eucledian 2– dimensional spaces, based on the the theory of hypercomplex numbers that a...

In this paper a combination of a rotation invariant method with a method which utilizes rotation normalization is proposed. Both methods used are based on 2D/3D Krawtchouk moments. The first method is an extension of that which was originally introduced in [1] and utilizes 2D Krawtchouk moments while the second method was originally introduced in [2] and utilizes 3D Krawtchouk moments.1