Feature points’ matching is a popular method in dealing with object recognition and image matching problems. However, variations of images, such as shift, rotation, and scaling, influence the matching correctness. Therefore, a feature point matching system with a distinctive and invariant feature point detector as well as robust description mechanism becomes the main challenge of this issue. We...

Pattern descriptors invariant to rotation, scaling, and translation represents an important direction in the elaboration of real time object recognition systems. In this article, new kinds based on chord transformation are presented. There described methods image presentation - Central Logarithmic Image Chord Transformations (CICT LCICT). It is shown that CICToperation makes it possible achieve...

301 We describe a method of constructing higher-order neural networks that respond invariantly under geometric transformations on the input space. By requiring each unit to satisfy a set of constraints on the interconnection weights, a particular structure is imposed on the network. A network built using such an architecture maintains its invariant performance independent of the values the weig...

This paper introduces variations on the template matching theme that extend its usefulness by providing invariance to mean intensity-level variations, certain geometric transformations and partial obscura-tions of the target object in the image. First order statistics of the pixel by pixel diierences between the template and the image are used as a match measure in order to provide invariance t...

We present in this paper a novel approach for shape description based on kernel principal component analysis (KPCA). The strength of this method resides in the similarity (rotation, translation and particularly scale) invariance of KPCA when using a family of triangular conditionally positive definite kernels. Beside this invariance, the method provides an effective way to capture non-lineariti...

In this paper we propose a novel method for the construction of textural features which are invariant with respect to 2D Euclidean motion and strictly increasing grey scale transformations. Our approach is based on a group averaging technique with relational kernel functions. In order to allow for comparison the evaluation of our approach was done on two image data sets taken from the Brodatz a...

A neural classiier of planar trajectories is presented. There already exist a large variety of classi-ers that are specialized on particular invariants contained in a trajectory classiication task such as position-invariance, rotation-invariance, size-invariance, .... That is, there exist classiiers specialized on recognizing trajectories e.g. independently of their position. The neural classii...

Interest points extraction and matching is a common task in many computer vision based application, which are used in different domains, such as 3D reconstruction, object recognition, or tracking. We present an evaluation of current state of the art about interest point extraction algorithms to measure several parameters, such as detection quality, invariance to rotation and scale transformatio...

We present and compare three different approaches to generate random points on the N -sphere: A simple Monte Carlo algorithm, a coordinate-by-coordinate strategy and a method based on the rotation invariance the normal distribution. The latter algorithm is the fastest.