Saliency is an important perceptual cue that occurs at different scales of resolution. Important attributes of saliency are symmetry, continuity, and closure. Detection of these attributes is often hindered by noise, variation in scale, and incomplete information. An iterative voting method using oriented kernels is introduced for inferring saliency as it relates to symmetry or continuity. A unique aspect of the technique is in the kernel topography, which is refined and reoriented iteratively. The technique can cluster and group nonconvex perceptual circular symmetries along the radial line or sparse features along the trangential direction. It has an excellent noise immunity, and is shown to be tolerant to perturbation in scale. Applications of this approach to blobs with incomplete and noisy boundaries and to scientific images are demonstrated.