形状的不变量特征提取与识别  

Invariant feature extraction and recognition for shapes

作　　者：徐浩然[1] 杨剑宇[1] 黄伟国[1] 尚丽[2] 

机构地区：[1]苏州大学城市轨道交通学院,苏州215000 [2]苏州市职业大学,苏州215000

出　　处：《中国图象图形学报》2017年第8期1068-1078,共11页Journal of Image and Graphics

基　　金：国家自然科学基金项目(51405320;61373098;61305020)~~

摘　　要：目的形状作为图像检索、目标识别等任务中的一种重要线索,一直是计算机视觉领域研究的重点课题。形状识别在实际应用中经常受到视角变化、非线性形变等因素的干扰,导致识别精度较低。针对这一状况,提出一种多尺度的不变量形状描述。方法方法首先在多个尺度下对形状轮廓进行计算,提取5种不变量特征,以构建对形状的有效描述,然后利用动态时间规整(DTW)算法对形状描述进行匹配,计算形状之间的相似度,以完成形状的匹配与识别。结果基于不变量多尺度的形状描述对于旋转、缩放、局部遮挡、铰接形变、类内差异,以及噪声等干扰具有很强的鲁棒性。同时,方法被用于对MPEG-7、Kimia99、Kimia216以及铰接形状数据库中的形状进行识别,取得了较高的识别精度,分别为91.79%、95.27%、91.33%,以及89.75%。此外,在MPEG-7数据库中进行形状识别的平均耗时为65 ms,优于大多数同类方法。结论提出了一种基于不变量多尺度的形状描述方法。该方法能提取形状在不同尺度下的多种不变量特征,对形状进行有效描述,提高了形状描述对几何变换和非线性形变等干扰的鲁棒性以及形状匹配识别精度,适用于大多数应用场景下的目标识别任务。尤其是在旋转、缩放、类内差异、局部遮挡和铰接变形等干扰存在的情况下也能保持较高的识别正确率。Abstract： Objective The shape of object contour is an important indication for image retrieval and object recognition; it is usually represented by a binary image. Although the binary images of objects have few features, such as color or texture, human can still recognize them only by shapes. By contrast, the shapes of objects cannot be recognized by computer di- rectly. In recent years, shape retrieval and recognition have been fundamental topics in computer vision and have been widely studied for various applications, such as character recognition, biomedical image analysis, hand gesture recogni- tion, robot navigation, and human gait recognition. To extract salient features for the representative characterization of a shape, many shape descriptors have been proposed and have reported promising results. However, the influences of viewpoint variations and nonlinear deformations, such as significant intra-elass differences, geometric transformations, and partial occlusions, are challenging problems that decrease the accuracy of shape matching and recognition. Most traditional shape descriptors utilize local or global information of shapes, which cannot solve the problems on shape deformations and intra-class variations simultaneously. The local descriptors can represent the local shape features effectively but do not consider the global shape structure. By contrast, the global descriptors are robust to local noise and deformations but ignore the detailed local shape features and cannot deal with occlusion. A novel invariant multi-scale descriptor with different types of invariant features is proposed to capture the local and semi-global features of shapes. Method The invariant multiscale descriptor is defined with five types of invariants, which capture shape features in five forms, including area, changing rate of area, arc length, changing rate of arc length, and central distance. These five types of invariants are normalized between 0 and 1 to capture the inconsistent variations adaptively within one shape a

关 键 词：特征提取 不变量 形状描述 形状匹配 目标识别 模式识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]