On the Orientability of Shapes

Abstract

The orientation of a shape is a useful quantity, and has been shown to affect performance of object recognition in the human visual system. Shape orientation has also been used in computer vision to provide a properly oriented frame of reference, which can aid recognition. However, for certain shapes, the standard moment-based method of orientation estimation fails. We introduce as a new shape feature shape orientability, which defines the degree to which a shape has distinct (but not necessarily unique) orientation. A new method is described for measuring shape orientability, and has several desirable properties. In particular, unlike the standard moment-based measure of elongation, it is able to differentiate between the varying levels of orientability of n-fold rotationally symmetric shapes. Moreover, the new orientability measure is simple and efficient to compute (for an n-gon we describe an O(n) algorithm).

Shape beyond recognition: Form-derived directionality and its effects on visual attention and motion perception.

“…Within the field of computer vision, the detection of a shape’s orientation is an often-used image preprocessing step applied before image registration and recognition (El-Sayed, Abdel-Kader, & Ramadan, 2010), and a number of algorithms have been developed to automatically detect the orientation and/or directionality of shapes (Cortadellas, Amat, & de la Torre, 2004; El-Sayed et al, 2010; Lin, 1996; Martinez-Ortiz & Zunic, 2010; Tzimiropoulos, Mitianoudis, & Stathaki, 2009; Zunic & Rosin, 2009; Zunic, Rosin, & Kopanja, 2006). The systematic and rapid extraction of an object’s directionality could also serve a role in human object recognition (see e.g.…”

Quantifying the shape of nanoparticles: Segmentation and elongation measure

“…Nakon segmentacije potreban je matematički alat kojim bi se kvantitativno opisali oblici. Razvijaju se brojni deskriptori oblika koji daju odgovor na pitanje koliko je neki oblik sličan odgovarajućem posmatranom obliku kao što je krug (circularity), kvadrat (squareness), elipsa (ellipticity), trougao (triangularity), pravougaonik (rectangularity) [3,[10][11][12][13][14][15][16][17][18][19][20][21][22][23]. Kako bi bio upotrebljiv svaki od deskriptora oblika treba da obezbedi da odgovarajuća mera bude invarijantna u odnosu na translaciju, rotaciju i skaliranje.…”

Aircraft Detection by Deep Convolutional Neural Networks

“…The traditional orienting method is based on the minimal geometric 1 or 2 order central moments, some new methods are based on the minimal area of including rectangle [13] or symmetric properties. The geometric central moments are easily disturbed by a small noise, the farer the noise from the central axis, the higher the weights it owned.…”