Supporting exact indexing of arbitrarily rotated shapes and periodic time series under Euclidean and warping distance measures

Abstract

Shape matching and indexing is important topic in its own right, and is a fundamental subroutine in most shape data mining algorithms. Given the ubiquity of shape, shape matching is an important problem with applications in domains as diverse as biometrics, industry, medicine, zoology and anthropology. The distance/similarity measure for used for shape matching must be invariant to many distortions, including scale, offset, noise, articulation, partial occlusion, etc. Most of these distortions are relatively easy to handle, either in the representation of the data or in the similarity measure used. However, rotation invariance is noted in the literature as being an especially difficult challenge. Current approaches typically try to achieve rotation invariance in the representation of the data, at the expense of discrimination ability, or in the distance measure, at the expense of efficiency. In this work, we show that we can take the slow but accurate approaches and dramatically speed them up. On real world problems our technique can take current approaches and make them four orders of magnitude faster, without false

Speeding up the cyclic edit distance using LAESA with early abandon

“…The MAP using the CED, in this database, is 64.00 and using the ED is 22.81. We have to say that in this task the results of the CED are much better because we solve a different problem [7] than the one of the digits database. In the digits database, we reduce the error of choosing as the beginning of the contour the upper leftmost point.…”

Efficient Rotation-Invariant Boundary Image Matching Using the Envelope-based Lower Bound

“…또한, 최근에는 필 기체 인식 [5], 이미지 매칭 [6,7], 바이오 시퀀스 매칭 [8] [17]. 객체의 외부 윤곽선 추출 방법에는 Chain Code [18], Polygon [19], CSS(curvature scale space) [20], CCD(centroid contour distance) [6,7,9,16] […”

A Heuristic Based on the Intrinsic Dimensionality for Reducing the Number of Cyclic DTW Comparisons in Shape Classification and Retrieval Using AESA

“…heuristic methods to obtain this invariance, they are not suitable in most of the domains. Therefore, the literature accepts that to obtain a good starting point we must make the comparison between every possible starting point of the sequence [2,3,9,4]. Hence the necessity to use cyclic sequences and then CDTW (Cyclic DTW) arises.…”

“…In [9], the authors, using a method similar to their previous work with DTW [11], try to speed up the CDTW as well. In this work, they do not use the algorithm of [10], but they make clusters of sequences based on their similarity, treating every possible starting point as a different sequence and using indexing methods with lower bounds of these clusters.…”