Translation, rotation, and scale-invariant object recognition

Abstract

Abstract-A method for object recognition, invariant under translation, rotation, and scaling, is addressed. The first step of the method (preprocessing) takes into account the invariant properties of the normalized moment of inertia and a novel coding that extracts topological object characteristics. The second step (recognition) is achieved by using a holographic nearest-neighbor algorithm (HNN), in which vectors obtained in the preprocessing step are used as inputs to it. The algorithm is tested in character recognition, using the 26 upper case letters of the alphabet. Only four different orientations and one size (for each letter) were used for training. Recognition was tested with 17 different sizes and 14 rotations. The results are encouraging, since we achieved 98% correct recognition. Tolerance to boundary deformations and random noise was tested. Results for character recognition in "real" images of car plates are presented as well.

An Overview of Advances of Pattern Recognition Systems in Computer Vision

“…To overcome this problem, increasingly more pattern description techniques are based on multi-scale or multiresolution representation methods (Lindeberg, 1998). Within this context, methods based on the pattern itself (Torres-Méndez et al, 2000 ;Kadyrov & Petrou, 2001 ;Belongie et al, 2002 ;Grigorescu & Petkov, 2003) exist as well as methods based on pattern contour behaviour (Matusiak & Daoudi, 1998 ;Roh & Kweon, 1998 ;Wang et al, 1999 ;Latecki et al, 2000). This study deals exclusively with methods based on the pattern contour.…”

Automatic Coin Classification and Identification

“…In general, rotational invariance is either approached via the use of geometrical moments (Hu, 1962), radial coding of features (Torres-Mendez et al, 2000), or using a mapping from Cartesian to polar coordinate representation, e.g. log-polar mapping (Kurita et al, 1998).…”

Multiscale contour description for pattern recognition

“…On Fig. 5.b, we represent the IPM function for σ, varying from 0 to 180, the IPM points indicated by (1) to (6) refer to the corresponding intersection points on Fig. 5.a.…”

“…To overcome this problem, increasingly more pattern analysis (or pattern description) techniques are based on multiscale or multiresolution representation methods [9,14]. Within this context, methods based on the pattern itself [3,6,19,20] exist as well as methods based on pattern contour behaviour [7,8,10,12,13,15,16,17,18]. This study deals exclusively with pattern contour methods.…”