一种二值图象边界提取算法

文中提出了一种新的二值图象边界提取算法。通过分析边界象素的特征,归纳出一个边界象素提取算子,该算子最多只需要计算象素的4邻域象素,运算量小,速度快,运用他能直接提取出二值图象的边界象素,得到单象素宽的边界。实验结果表明,该算法要优于传统的二值图象边界提取算法,实用性强。     

图象边界的遗传算法规整

为了使检测的图象边界更符合有效的理想边界结构,同时能滤除边界图象中的噪声干扰,提出了一种基于遗传算法在图象边界规整方法。该方法首先将已经检测得到的边界图象编码为两维二值码串个体,并根据理想边界模板集来计算每个个体的适应度;然后通过交叉、变异和选择等遗传运算对被检测出的非理想边界进行规整。在遗传算法收敛时,该算法不仅能得到最适合有效理想边界结构的边界图象,并能有效地滤除边界图象中的噪声。     

基于边界特征的一维最大熵图像分割算法的研究与实现

本文提出了一种新的图象分割算法，该算法首先检测边缘，在边界图象的基础上进行图象二值化，保留了边界特征，而且能自适应地选择阈值，克服了一维最大熵阈值方法进行图象分割时丢失边界特征的缺点。大量实验表明该算法取得了很好的效果，而且可以处理低质量或边缘模糊的图象，具有一定的推广实用价值。     

基于边界特征的一维最大熵图像分割算法的研究与实现

本文提出了一种新的图象分割算法，该算法首先检测边缘，在边界图象的基础上进行图象二值化，保留了边界特征，而且能自适应地选择阈值，克服了一维最大熵阈值方法进行图象分割时丢失边界特征的缺点。大量实验表明该算法取得了很好的效果，而且可以处理低质量或边缘模糊的图象，具有一定的推广实用价值。     

二值图象广义边界编码压缩方法

本文提出一种与游程相关的二值图象广义边界概念和及对编码方法，并给出实现算法的恢复方法，最后通过对几幅二值图象压缩结果与游程编码，二维自适应跳白块编码方法进行比较和分析，表明本文提出了的广义边界编码压缩方法的压缩性能比另两种压缩方法优越，是一种易于实现的高效率的二值图象压缩方法。     

基于控制点的二值图像边界矢量化算法

提出一种二值图像边界矢量化算法,实现从图像到图形的自动转换.先通过边界跟踪算法获取二值图像的边界,并利用SUSAN方法计算出边界上的角点,根据距离关系计算角点间的普通控制点,最后运用角点和这些普通控制点的3次B样条曲线拟合边界.实验结果表明算法有效实现了图像矢量化,解决了边界矢量化问题,具有较强的实用性.     

图象中一种不规则边界圆的参数求取方法

文章提出了一种基于曲线拟合法求取图象中不规则边界圆的参数的求取方法。在进行图象的预处理得到一个不规则边界圆的边界数据点集的基础上,该算法首先引入替代变量,使圆方程拟合法求圆参数成为可能;然后进行圆参数的多次迭代拟合,边拟合边剔除拟合点集中的不规则圆边界点,直到符合终止条件为止,成功地求出了圆参数的最佳估值。试验证明,和传统的广义Hough变换相比,该算法具有运算速度快、自动求取的突出优点,在不规则边界点所占整个圆边界点比例较小时能取得很好的结果。     

一种基于差分图象的多运动目标检测算法

运动目标的检测是计算机视觉和图象编码研究的主要内容之一,在许多领域有着广泛的应用.本文提出一种基于差分图象的多运动目标检测算法.对于视频图象序列,首先运用自适应阈值技术得到二值差分图象,经形态滤波提取运动变化区域,然后结合当前帧的边界信息确定运动目标的边界,最后由形态操作和区域填充得到连通的运动目标区域并检测运动目标,检测结果以目标的外接矩形表示.实验结果表明,该方法能快速有效地检测出运动目标并具有较好的鲁棒性.     

基于损失函数的微弱图象边界检测

将图象边界检测转化为一个优化问题，首先求出图象几何点集合，再定义损失函数，选择合适的边界曲线方程参数矢量使得损失函数最小，从而求出最优化的边界曲线，这种方法允许边界上的几何点只占几何点集合２０％以下，因此适合下强噪声下微弱图象边界的检测。     

一种区域边界的识别和区域标记算法与应用

本文介绍了一种区域边界的识别算法和一种区域标记的算法,前者在有若干区域的多条边界相交及存在边界公用的情况下,通过直线生成的方法能寻找出每一个最小区域的完整的区域边界;后者则能在识别出区域边界的基础上进行区域的标记,把区域分割出来,这两个算法已用于电脑刺绣编程系统的图象预处理系统,效果良好。文中并通过实例说明了这两个算法的特点。     

A robust recognition system for a drawing superimposed on a map

A robust and efficient drawing recognition system that is based on a representation technique using accurate shape and topological line information for an input drawing image is described. This representation supports primitive decomposition and object extraction that enable accurate automatic interpretation even for low-quality drawings. The system, which is adapted to an underground electric cable diagram, has been implemented on a workstation     

Hypercolumn-array based image representation and its application to shape-based object detection

Biological and psychological evidence increasingly reveals that high-level geometrical and topological features are the keys to shape-based object recognition in the brain. Attracted by the excellent performance of neural visual systems, we simulate the mechanism of hypercolumns in the mammalian cortical area V1 that selectively responds to oriented bar stimuli. We design an orderly-arranged hypercolumn array to extract and represent linear or near-linear stimuli in an image. Each unit of this array covers stimuli of various orientations in a small area, and multiple units together produce a low-dimensional vector to describe shape. Based on the neighborhood of units in the array, we construct a graph whose node represents a short line segment with a certain position and slope. Therefore, a contour segment in the image can be represented with a route in this graph. The graph converts an image, comprised of typically unstructured raw data, into structured and semantic-enriched data. We search along the routes in the graph and compare them with a shape template for object detection. The graph greatly upgrades the level of image representation, remarkably reduces the load of combinations, significantly improves the efficiency of object searching, and facilitates the intervening of high-level knowledge. This work provides a systematic infrastructure for shape-based object recognition.     

Object representation and recognition in shape spaces

In this paper, we describe a shape space based approach for invariant object representation and recognition. In this approach, an object and all its similarity transformed versions are identified with a single point in a high-dimensional manifold called the shape space. Object recognition is achieved by measuring the geodesic distance between an observed object and a model in the shape space. This approach produced promising results in 2D object recognition experiments: it is invariant to similarity transformations and is relatively insensitive to noise and occlusion. Potentially, it can also be used for 3D object recognition.     

Robust Object Detection with Interleaved Categorization and Segmentation

This paper presents a novel method for detecting and localizing objects of a visual category in cluttered real-world scenes. Our approach considers object categorization and figure-ground segmentation as two interleaved processes that closely collaborate towards a common goal. As shown in our work, the tight coupling between those two processes allows them to benefit from each other and improve the combined performance. The core part of our approach is a highly flexible learned representation for object shape that can combine the information observed on different training examples in a probabilistic extension of the Generalized Hough Transform. The resulting approach can detect categorical objects in novel images and automatically infer a probabilistic segmentation from the recognition result. This segmentation is then in turn used to again improve recognition by allowing the system to focus its efforts on object pixels and to discard misleading influences from the background. Moreover, the information from where in the image a hypothesis draws its support is employed in an MDL based hypothesis verification stage to resolve ambiguities between overlapping hypotheses and factor out the effects of partial occlusion. An extensive evaluation on several large data sets shows that the proposed system is applicable to a range of different object categories, including both rigid and articulated objects. In addition, its flexible representation allows it to achieve competitive object detection performance already from training sets that are between one and two orders of magnitude smaller than those used in comparable systems.     

Vision-based global localization for mobile robots with hybrid maps of objects and spatial layouts

This paper presents a novel vision-based global localization that uses hybrid maps of objects and spatial layouts. We model indoor environments with a stereo camera using the following visual cues: local invariant features for object recognition and their 3D positions for object pose estimation. We also use the depth information at the horizontal centerline of image where the optical axis passes through, which is similar to the data from a 2D laser range finder. This allows us to build our topological node that is composed of a horizontal depth map and an object location map. The horizontal depth map describes the explicit spatial layout of each local space and provides metric information to compute the spatial relationships between adjacent spaces, while the object location map contains the pose information of objects found in each local space and the visual features for object recognition. Based on this map representation, we suggest a coarse-to-fine strategy for global localization. The coarse pose is estimated by means of object recognition and SVD-based point cloud fitting, and then is refined by stochastic scan matching. Experimental results show that our approaches can be used for an effective vision-based map representation as well as for global localization methods.     

Octree creation via C.S.G. definition

The common method for generating the octrees of complex objects, is based upon generating the octrees of several pre-defined primitives and applying Boolean operations on them. Regardless how the octrees representing the primitives are generated (top-down or bottom-up) the octree of a desired object is obtained by performing Boolean operations among the primitives comprising the object according to the object's CSG (constructive solid Geometry) representation. When carrying out this procedure, most of the computing and memory resources are used for generating and storing the octants comprising the primitives. However, the majority of those octants are not required for the representation of the final object. In this paper the extention of the top-down approach to the CSG level (i.e., generating the octree of an object directly from its CSG representation) is proposed. With this method there is no need to generate the octrees of the primitives comprising the object nor to perform Boolean operations on them. Moreover, only these octants which belong to the final object are generated.     

Planar shape representation and matching under projective transformation

This paper introduces a new representation for planar objects which is invariant to projective transformation. Proposed representation relies on a new shape basis which we refer to as the conic basis. The conic basis takes conic-section coefficients as its dimensions and represents the object as a convex combination of conic-sections. Pairs of conic-sections in this new basis and their projective invariants provides the proposed view invariant representation. We hypothesize that two projectively transformed versions of an object result in the same representation. We show that our hypothesis provides promising recognition performance when we use the nearest neighbor rule to match projectively deformed objects.     

三维物体的形态图表达方法

三维物体的表达方法是计算机视觉中的关键问题之一，现有的各种三维物体表达方法虽然在各自的识别中得到应用，但都存在各自的局限性，用形态图表达三维物体是一种以视点为中心的表达方法，由于它列举了一个物体所有可能的“定性”形象，即它可使用最少的二维投影线图（特征视图）来表达一个完整的三维物体，因此使三维物体识别转化为2D与2D的匹配，该文首先定义了二维线图拓扑结构等价的判别准则，然后给出了构造透明物体形态图的方法，最后根据拓扑结构等价准则来得到不透明物体的形态图和特征图，并用圆锥与圆柱相交的实例进行了验证。     

Visual learning and recognition of 3D objects using two-dimensional principal component analysis: A robust and an efficient approach

Inspired by the conviction that the successful model employed for face recognition [M. Turk, A. Pentland, Eigenfaces for recognition, J. Cogn. Neurosci. 3(1) (1991) 71-86] should be extendable for object recognition [H. Murase, S.K. Nayar, Visual learning and recognition of 3-D objects from appearance, International J. Comput. Vis. 14(1) (1995) 5-24], in this paper, a new technique called two-dimensional principal component analysis (2D-PCA) [J. Yang et al., Two-dimensional PCA: a new approach to appearance based face representation and recognition, IEEE Trans. Patt. Anal. Mach. Intell. 26(1) (2004) 131-137] is explored for 3D object representation and recognition. 2D-PCA is based on 2D image matrices rather than 1D vectors so that the image matrix need not be transformed into a vector prior to feature extraction. Image covariance matrix is directly computed using the original image matrices, and its eigenvectors are derived for feature extraction. The experimental results indicate that the 2D-PCA is computationally more efficient than conventional PCA (1D-PCA) [H. Murase, S.K. Nayar, Visual learning and recognition of 3-D objects from appearance, International J. Comput. Vis. 14(1) (1995) 5-24]. It is also revealed through experimentation that the proposed method is more robust to noise and occlusion.