Mathematical Morphology Based on Linear Combined Metric Spaces on Z2 (Part I): Fast Distance Transforms

Mathematical Morphology (MM) is a general method for image processing based on set theory. The two basic morphological operators are dilation and erosion. From these, several non linear filters have been developed usually with polynomial complexity, and this because the two basic operators depend strongly on the definition of the structural element. Most efforts to improve the algorithm's speed for each operator are based on structural element decomposition and/or efficient codification.A new framework and a theoretical basis toward the construction of fast morphological operators (of zero complexity) for an infinite (countable) family of regular metric spaces are presented in work. The framework is completely defined by the three axioms of metric. The theoretical basis here developed points out properties of some metric spaces and relationships between metric spaces in the same family, just in terms of the properties of the four basic metrics stated in this work. Concepts such as bounds, neighborhoods and contours are also related by the same framework.The presented results, are general in the sense that they cover the most commonly used metrics such as the chamfer, the city block and the chess board metrics. Generalizations and new results related with distances and distance transforms, which in turn are used to develop the morphologic operations in constant time, in contrast with the polynomial time algorithms are also given.     

构词法在智能英汉机译系统词典库中的应用

词典库是机译系统的基础,它直接影响着整个系统的翻译质量.因此,大型机译系统中词典库的组织方式和辅助获取越来越受重视.本文概述了英语构词规律,并根据此规律以及智能英汉系统(IMTF/C)词典库的组织特点,给出了构词法在词典库中的两个应用,即由构词法辅助获取词典信息和根据构词法改进词典库的组织.最后,分析了一个试验结果.     

基于数学形态学的虹膜定位算法

针对现有的虹膜定位算法的局限性,提出了一种基于数学形态学的虹膜定位算法。内圆定位是利用二值图像形态学的方法提取瞳孔的圆心和半径。外圆的定位用形态学进行边缘提取与Hough变换相结合,确定外圆圆心及半径。实验证明了该算法的合理性和有效性。     

边界描迹算法在图像数据库的应用

本文介绍了一种优化图像数据库性能的算法－边界描迹算法,通过形态学变换减少笔迹图像的孤立点噪声,采用边界描迹的方法提取图像的基本特征,并以链码形成存储图像数据。可以大大减少图像数据的存储量,本文详细阐述了此方法的算法实现。     

A method for observing the three-dimensional morphologies of inclusions in steel

A method for observing the three-dimensional morphologies of inclusions by deeply eroding a steel sample with a kind of organic solution composed of bromine water,acetone,and HC1 (volume ratio,45∶45∶10...     

A new approach to children's footwear based on foot type classification

Current shoe designs do not allow for the comprehensive 3-D foot shape, which means they are unable to reproduce the wide variability in foot morphology. Therefore, the purpose of this study was to capture these variations of children's feet by classifying them into groups (types) and thereby provide a basis for their implementation in the design of children's shoes. The feet of 2867 German children were measured using a 3-D foot scanner. Cluster analysis was then applied to classify the feet into three different foot types. The characteristics of these foot types differ regarding their volume and forefoot shape both within and between shoe sizes. This new approach is in clear contrast to previous systems, since it captures the variability of foot morphology in a more comprehensive way by using a foot typing system and therefore paves the way for the unimpaired development of children's feet. Previous shoe systems do not allow for the wide variations in foot morphology. A new approach was developed regarding different morphological foot types based on 3-D measurements relevant in shoe construction. This can be directly applied to create specific designs for children's shoes.     

花形氧化锌纳米粒子的制备及其光催化性能

以氯化锌和氢氧化钠为原料,水为反应介质,密闭加热的条件下制备了花形ZnO纳米粒子。借助扫描电镜及X射线粉末衍射仪等仪器,对产物的形貌、结构进行了表征;对产物的生长机理做了研究,同时研究了反应条件对产物的影响,另外对产物进行了光催化测试。结果表明,花形骨架在反应初期就已经产生,反应时间增加,花形粒子变大;改变氯化锌和氢氧化钠的物质的量比,产物形貌产生了较大变化,分别生成了另一种形貌的花形粒子和片状粒子;通过光催化测试表明,所得的产物均有良好的光催化性能。     

基于小波变换的车辆牌照定位研究

车辆牌照的准确定位是智能交通中车辆牌照识别技术的关键,提出一种基于小波变换的车牌质心定位方法,该方法可以很好地解决复杂背景与光照下的车牌定位.经过小波分析的车牌图像利用数学形态学进行车牌特征提取,对特征提取后的车牌图像采用连通区域质心的方法对车牌进行定位,最终得到车牌的准确区域.实验结果表明,该方法能够实现车牌的快速准确定位,是一种有效的车牌定位方法.     

基于肤色检测的AdaBoost人脸检测算法改进

AdaBoost人脸检测算法用于嵌入式实时高清视频时检测速度缓慢.为此,提出一种改进的人脸检测算法.对图像做肤色检测,将检测到的区域进行形态学处理,并作为感兴趣区域,完成AdaBoost人脸检测,以得到检测结果.实验结果表明,该算法在嵌入式系统上运行稳定,能提高检测速度和检测正确率.     

基于形态学微分的车牌字符分割算法

提出了基于形态学微分的车牌字符分割算法。首先运用形态学微分算法获取车的边界,然后通过巧妙选择连通区域进行深度搜索即可直接获得车牌每个字符的矩形区域。本方法省去了一般车牌识别中的车牌定位部分,对有一定倾角的车牌也有一定的适应能力。