Adaptive Pixel Resizing for Multiscale Recognition and Reconstruction

Marc Rodríguez,Gaëlle Largeteau-Skapin,Eric Andres

COMBINATORIAL IMAGE ANALYSIS, PROCEEDINGS（2009）

引用 8|浏览0

暂无评分

摘要

This paper present an adaptive pixel resizing method based on a parameter space approach. The pixel resizing is designed for both multiscale recognition and reconstruction purposes. The general idea is valid in any dimension. In this paper we present an illustration of our method in 2D. Pixels are resized according to the local curvature of the curve to control the local error margin of the reconstructed Euclidean object. An efficient 2D algorithm is proposed.

查看译文

关键词

adaptive pixel,reconstruction purpose,multiscale recognition,local curvature,pixel resizing,reconstructed euclidean object,local error margin,adaptive pixel resizing,parameter space approach,general idea,parameter space

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要