基于梯度幅度直方图和类内方差的边缘提取方法
Edge Detection Based on Gradient Histogram and Variance Within Clusters
-
摘要: 针对复杂背景中目标边缘提取的问题,提出一种基于梯度幅度直方图和类内方差进行边缘提取的新方法———CAGH(cluster algorithm based on gradient histogram)算法。该算法先分析经“非最大梯度抑制”后的梯度幅度直方图的特征,确定边缘集中区域,再通过类内方差确定梯度阈值,并利用该阈值确定边缘。在车牌识别中运用该方法提取复杂背景中的车牌边缘,并与Sobel、Canny等算法进行了比较。结果表明,CAGH算法适应性强、提取效率高,提取的是连通性、独立性好的单像素边缘,有利于后续的特征提取和模式识别。Abstract: In this paper,a new method for edge detection from complex scenes based on gradient histogram and variance within clusters is proposed(cluster algorithm based on gradient histogram,CAGH).After analysing gradient histogramming by "Non-maximal suppression",edges can be extracted with the gradient threshold based on the variance within clusters.In comparision with other methods for edge detection of vehicle license plates from complex scenes,this method has better adaptability and more efficiency,which generates one pixel width edges with good connectivity and independence,is good to subsequent feature extraction and pattern recognition.
下载:
