Shape Matching Using Multiscale Integral Invariants
- Authors
- Hong, Byung-Woo; Soatto, Stefano
- Issue Date
- Jan-2015
- Publisher
- IEEE COMPUTER SOC
- Keywords
- Shape matching; shape descriptor; integral invariant; scale invariant; Wasserstein distance
- Citation
- IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, v.37, no.1, pp 151 - 160
- Pages
- 10
- Journal Title
- IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
- Volume
- 37
- Number
- 1
- Start Page
- 151
- End Page
- 160
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/10009
- DOI
- 10.1109/TPAMI.2014.2342215
- ISSN
- 0162-8828
1939-3539
- Abstract
- We present a shape descriptor based on integral kernels. Shape is represented in an implicit form and it is characterized by a series of isotropic kernels that provide desirable invariance properties. The shape features are characterized at multiple scales which form a signature that is a compact description of shape over a range of scales. The shape signature is designed to be invariant with respect to group transformations which include translation, rotation, scaling, and reflection. In addition, the integral kernels that characterize local shape geometry enable the shape signature to be robust with respect to undesirable perturbations while retaining discriminative power. Use of our shape signature is demonstrated for shape matching based on a number of synthetic and real examples.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Software > Department of Artificial Intelligence > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/10009)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.