基于类间方差和形态学的一类生物特征识别  

Biometrics based on the variance between clusters and morphology

作　　者：田沛[1] 范瑾[1] 李亮[1] 张兆祥[1] 

机构地区：[1]华北电力大学控制科学与工程学院,保定071003

出　　处：《清华大学学报（自然科学版）》2007年第z2期1747-1750,共4页Journal of Tsinghua University(Science and Technology)

摘　　要：足迹是刑侦工作中经常用到的生物特征。针对足迹照片存在噪声干扰大,边缘不清晰,人工识别受主观因素影响等问题,提出了一种基于最大类间方差(Otsu)和形态学滤波的足迹特征识别方法。利用最大类间方差法将图像二值化,得到鞋底各部分受力情况的粗略估计;同时结合形态学滤波和阈值面积消除法抑制噪声,并自适应地确定特征识别门限值。该方法运算简单,能充分利用图像的梯度和灰度信息,有效消除噪声,提高特征区域边缘检测的准确性,为刑侦工作的足迹自动识别提供了新途径。Tread feature recognition is one of the most important biometrics in criminal investigations.A scheme was developed to correctly reproduce distinct,continuous edges and reduce manual intervention based on the maximum variance between clusters method and a morphological filter.The method is used to separate the heavy pressure surface from the image,then the morphological filter and area threshold removal are used to filter the noise,with an adaptive method used to select the area extraction threshold.Test results show that the method reproduces accurate,smooth edges through use of the gradient and gray information,providing an accurate method for automatic tread feature recognition.

关 键 词：图像处理 自动识别 生物特征识别 最大类间方差 形态学滤波 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]