一种平面数字图像最小外接矩形的提取算法

An Extracting Algorithm for Minimum Enclosing Rectangle of Target Image

在数字图像分类与识别算法研究中,目标图像几何特征的提取通常需要计算目标图像的最小面积的外接矩形,以获得目标图像的长、宽等属性。针对该特点,本文提出并实现一种利用旋转扫描线方式的线扫描法计算目标图像最小面积外接矩形的算法,并对算法优化以提高算法的执行效率。

Geometric features extraction from image is an crucial step in image classification and recognition algorithms.It requires to calculate the Minimum Enclosing Rectangle （MER） of the image to get some attributes,such as length andwidth.This paper proposes an algorithm based on the rotary scanning to extract MER from image,and the algorithm is improvedto improve operation efficiency.