کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
408431 679027 2016 13 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Introducing locally affine-invariance constraints into lunar surface image correspondence
ترجمه فارسی عنوان
معرفی محدودیت های غیر انعطاف پذیری محلی به سطح مکعب تصویر ماه
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر هوش مصنوعی
چکیده انگلیسی

This paper aims to solve the keypoint correspondence problem in lunar surface images, a typical correspondence task under point ambiguity. Point ambiguity may be caused by repetitive patterns, cluttered scenes, and outliers in the images, which makes the local descriptors less discriminative. In this paper we introduce locally affine-invariance constraints on graphs to tackle the keypoint correspondence problem under point ambiguity. The key idea is that each point can be represented with the affine combination of its neighbors. It is suitable for our problem because it is not only invariant to scale and rotational change, but also more resistant to outliers. Specifically, we introduce the locally affine-invariance constraints into the subgraph matching problem and the common subgraph matching problem. The locally affine-invariance constraint is not directly applicable on common subgraph matching due to its dependency on awareness of selected keypoints. This problem is approximately addressed by solving a series of reliable matching identification and rematching problems. In the experiments, we first apply the proposed method on standard graph matching datasets to evaluate its effectiveness on general correspondence problem under point ambiguity, and second validate the applicability on the lunar surface image dataset.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Neurocomputing - Volume 186, 19 April 2016, Pages 258–270
نویسندگان
, , , , ,