Focus-of-attention from local color symmetries

Abstract

Abstract-In this paper, a continuous valued measure for local color symmetry is introduced. The new algorithm is an extension of the successful gray value-based symmetry map proposed by Reisfeld et al. The use of color facilitates the detection of focus points (FPs) on objects that are difficult to detect using gray-value contrast only. The detection of FPs is aimed at guiding the attention of an object recognition system; therefore, FPs have to fulfill three major requirements: stability, distinctiveness, and usability. The proposed algorithm is evaluated for these criteria and compared with the gray value-based symmetry measure and two other methods from the literature. Stability is tested against noise, object rotation, and variations of lighting. As a measure for the distinctiveness of FPs, the principal components of FP-centered windows are compared with those of windows at randomly chosen points on a large database of natural images. Finally, usability is evaluated in the context of an object recognition task.

Robust Content Based Watermarking Algorithm Using Singular Value Decomposition of Radial Symmetry Maps

“…This transform is called radial symmetry transform and it presents very good robustness against image transformations and nosing. The radial symmetry transform is originally used to detect image features [16], [17] and we use it in this work to support the robustness of the scheme and to detect pixels which care the mark bits.…”

A Content Based Watermarking Scheme Using Radial Symmetry Transform and Singular Value Decomposition

“…This transform is called radial symmetry transform and it presents very good robustness against image transformations and nosing. The radial symmetry transform is originally used to detect image features [16], [17].…”

Using Local Symmetry for Landmark Selection

“…In earlier work, for instance, Marola [16] used symmetry for detection and localization of objects in planar images. Symmetry has furthermore been used to control the gaze of artificial vision systems [17,18] Heidemann [19] showed that interest points detected with color symmetry are robust to noise and 3D object rotation. Moreover, he showed that symmetry detection results in points that are more robust to changing light conditions than Harris corners and that these points are more unique compared to other locations in the image.…”

“…Reisfeld et al [20], for instance, developed a mirror-symmetry operator by comparing the gradients of neighboring pixels. Heidemann [19] extended this work to the color domain. Reisfeld et al also proposed a radial-symmetry operator that promotes patterns that are symmetric in multiple symmetry axes.…”