目标分类方法最常用的有两种，一种是基于形状信息的分类 （Shape-based Classification），它利用检测出的运动区域的形状特征进行目标分类 的方法[10]。
基于20个网页-相关网页
By applying the measures of partial smoothing and structure and shape based coarse classification, the recognition performance of DP method is highly improved.
通过采用局部平滑预处理，以及基于速记符形状特征和结构特征的粗分类措施，大大提高了动态规划识别速度和正确识别率。
And a set of features combining color, shape and topological are extracted from each object. Based on the features, a classification criterion is employed to perform the map segmentation.
通过提取对象的颜色、形状和近邻关系等特征，建立分类标准，实现地形图的自动分层。
This paper presents a classification and recognition algorithm based on shape feature.
提出了一种基于形状特征的字母手势的分类及识别算法。
应用推荐