Signature Detection and Matching for Document Image Retrieval

As one of the most pervasive methods of individual identification and document authentication, signatures present convincing evidence and provide an important form of indexing for effective document image processing and retrieval in a broad range of applications. However, detection and segmentation of free-form objects such as signatures from clustered background is currently an open document analysis problem. In this paper, we focus on two fundamental problems in signature-based document image retrieval. First, we propose a novel multiscale approach to jointly detecting and segmenting signatures from document images. Rather than focusing on local features that typically have large variations, our approach captures the structural saliency using a signature production model and computes the dynamic curvature of 2D contour fragments over multiple scales. This detection framework is general and computationally tractable. Second, we treat the problem of signature retrieval in the unconstrained setting of translation, scale, and rotation invariant nonrigid shape matching. We propose two novel measures of shape dissimilarity based on anisotropic scaling and registration residual error and present a supervised learning framework for combining complementary shape information from different dissimilarity metrics using LDA. We quantitatively study state-of-the-art shape representations, shape matching algorithms, measures of dissimilarity, and the use of multiple instances as query in document image retrieval. We further demonstrate our matching techniques in offline signature verification. Extensive experiments using large real-world collections of English and Arabic machine-printed and handwritten documents demonstrate the excellent performance of our approaches.     

Similarity assessment of 3D mechanical components for design reuse

Duplicate designs consume a significant amount of resources in most new product development. Search of similar parts for a given query part is the key to avoid this problem by facilitating design reuse. Most search algorithms convert the CAD model into a shape signature and compute the similarity between two models according to a measure function of their signatures. However, each algorithm defines the shape signature in a different way, and thus has its own limitations in discriminating 3D parts. This paper proposes a search scheme that successfully complements various shape signatures in similarity assessment of 3D mechanical components. It considers form-feature, topological, and geometric information in component comparison. Such an integrated approach can effectively solve the feature intersection problem, inherited in any feature-based approaches, and capture the user's intent more precisely in the search, which geometry-based methods fail to accomplish. We also develop a set of algorithms that performs the component comparison in a polynomial time. The proposed scheme is implemented in a product design environment consisting of commercial CAD and PDM systems. The result demonstrates the practicality of this work in automatic search of similar mechanical components for design reuse.     

Benchmarking shape signatures against human perceptions of geometric similarity

Manual indexing of large databases of geometric information is both costly and difficult. Because of this, research into automated retrieval and indexing schemes has focused on the development of methods for characterising 3D shapes with a relatively small number of parameters (e.g. histograms) that allow ill-defined properties such as “geometric similarity” to be computed. However although many methods of generating these so called shape signatures have been proposed, little work on assessing how closely these measures match human perceptions of geometric similarity has been reported. This paper details the results of a trial that compared the part families identified by both human subjects and three published shape signatures.To do this a similarity matrix for the Drexel benchmark datasets was created by averaging the results of twelve manual inspections. Three different shape signatures (D2 shape distribution, spherical harmonics and surface portioning spectrum) were computed for each component in the dataset, and then used as input to a competitive neural network that sorted the objects into numbers of “similar” clusters. Comparison of human and machine generated clusters (i.e. families) of similar components allows the effectiveness of the signatures at duplicating human perceptions of shapes to be quantified.The work reported makes two contributions. Firstly the results of the human perception test suggest that the Drexel dataset contains objects whose perceived similarity levels ranged across the recorded spectrum (i.e. 0.1 to 0.9); Secondly the results obtained from benchmarking the three shape signatures against human perception demonstrate a low rate of false positives for all three signatures and a false negative rate that varied almost linearly with the amount of perceived similarity. In other words the shape signatures studied were reasonably effective at matching human perception in that they returned few wrong results and excluded parts in direct proportion to the level of similarity demanded by the user.     

Characterization of individual tree crowns using three-dimensional shape signatures derived from LiDAR data

Three-dimensional (3D) shape signatures based on the distance distribution of random point pairs are introduced and the effectiveness evaluated using computer simulations and samples of oak and Douglas fir crowns selected from Light Detection and Ranging (LiDAR) point clouds and Digital Surface Models (DSMs). The results suggest that comparison of 3D crown shapes can be effectively reduced to the comparison of frequency distributions of distances between random points, and that it is more computationally efficient when shape signatures are derived from raster surfaces. The results also suggest that the statistically based 3D shape signatures are relatively insensitive to noise and other small local variations, which is important for crown shape analysis in real-world environments.     

基于颜色和形状特征的彩色图像显示与检索技术

提出了一种有效用于抽取特征、索引和检索彩色图像的技术途径,通过提取图像的颜色不变量,建立相应的色度直方图（hue histogram）来表示图像的颜色分布特征,为了描述图像中对象的位置及方向特征,首先计算图像的色度轮廓并对其进行Radon变换,然后计算相应的“空间直方图”,由此,得到了一种基于图像的颜色分布特征和形状特征的新的图像表示方法,为了计量图像的全局相似度,基于“累积距离”和“基于向量的距离”定义了两种图像的距离度量,并分别讨论了距离度量的选取与归一化、不同子特征的组合等CBIR所涉及的关键问题,实验结果表明,文中提出的方法能获得满意的检索性能,其检索结果能较好地接近于人的视觉感和结果。     

Pictorial recognition of objects employing affine invariance in thefrequency domain

Describes an efficient approach to pose invariant pictorial object recognition employing spectral signatures of image patches that correspond to object surfaces which are roughly planar. Based on singular value decomposition (SVD), the affine transform is decomposed into slant, tilt, swing, scale, and 2D translation. Unlike previous log-polar representations which were not invariant to slant, our log-log sampling configuration in the frequency domain yields complete affine invariance. The images are preprocessed by a novel model-based segmentation scheme that detects and segments objects that are affine-similar to members of a model set of basic geometric shapes. The segmented objects are then recognized by their signatures using multidimensional indexing in a pictorial dataset represented in the frequency domain. Experimental results with a dataset of 26 models show 100 percent recognition rates in a wide range of 3D pose parameters and imaging degradations: 0-360° swing and tilt, 0-82° of slant, more than three octaves in scale change, window-limited translation, high noise levels (0 dB), and significantly reduced resolution (1:5)     

CM-BOF: visual similarity-based 3D shape retrieval using Clock Matching and Bag-of-Features

Content-based 3D object retrieval has become an active topic in many research communities. In this paper, we propose a novel visual similarity-based 3D shape retrieval method (CM-BOF) using Clock Matching and Bag-of-Features. Specifically, pose normalization is first applied to each object to generate its canonical pose, and then the normalized object is represented by a set of depth-buffer images captured on the vertices of a given geodesic sphere. Afterwards, each image is described as a word histogram obtained by the vector quantization of the image’s salient local features. Finally, an efficient multi-view shape matching scheme (i.e., Clock Matching) is employed to measure the dissimilarity between two models. When applying the CM-BOF method in non-rigid 3D shape retrieval, multidimensional scaling (MDS) should be utilized before pose normalization to calculate the canonical form for each object. This paper also investigates several critical issues for the CM-BOF method, including the influence of the number of views, codebook, training data, and distance function. Experimental results on five commonly used benchmarks demonstrate that: (1) In contrast to the traditional Bag-of-Features, the time-consuming clustering is not necessary for the codebook construction of the CM-BOF approach; (2) Our methods are superior or comparable to the state of the art in applications of both rigid and non-rigid 3D shape retrieval.     

A multiresolution descriptor for deformable 3D shape retrieval

In this paper, we present a spectral graph wavelet framework for the analysis and design of efficient shape signatures for nonrigid 3D shape retrieval. Although this work focuses primarily on shape retrieval, our approach is, however, fairly general and can be used to address other 3D shape analysis problems. In a bid to capture the global and local geometry of 3D shapes, we propose a multiresolution signature via a cubic spline wavelet generating kernel. The parameters of the proposed signature can be easily determined as a trade-off between effectiveness and compactness. Experimental results on two standard 3D shape benchmarks demonstrate the much better performance of the proposed shape retrieval approach in comparison with three state-of-the-art methods. Additionally, our approach yields a higher retrieval accuracy when used in conjunction with the intrinsic spatial partition matching.     

Deformation similarity measurement in quasi-conformal shape space

This paper presents a novel approach based on the shape space concept to classify deformations of 3D models. A new quasi-conformal metric is introduced which measures the curvature changes at each vertex of each pose during the deformation. The shapes with similar deformation patterns follow a similar deformation curve in shape space. Energy functional of the deformation curve is minimized to calculate the geodesic curve connecting two shapes on the shape space manifold. The geodesic distance illustrates the similarity between two shapes, which is used to compute the similarity between the deformations. We applied our method to classify the left ventricle deformations of myopathic and control subjects, and the sensitivity and specificity of our method were 88.8% and 85.7%, which are higher than other methods based on the left ventricle cavity, which shows our method can quantify the similarity and disparity of the left ventricle motion well.     

Fractal indexing with the joint statistical properties and its application in texture image retrieval

Fractal image coding is a block-based scheme that exploits the self-similarity hiding within an image. Fractal parameters generated by the block-based scheme are quantitative measurements of self-similarity, and therefore they can be used to construct image signatures. By combining fractal parameters and collage error, a set of new statistical fractal signatures, such as histogram of collage error (HE), joint histogram of contrast scaling and collage error (JHSE), and joint histogram of range block mean and contrast scaling and collage error (JHMSE) is proposed. These fractal signatures effectively extract and reflect the statistical properties intrinsic in texture images. Hence, they provide new statistical features for use in texture image retrieval and identification. Furthermore, in order to reduce computational complexity of the JHMSE signature, the JHMSE signature is simplified to HM (histogram of range block mean) tJHSE and HM t HS (histogram of contrast scaling) tHE, based on the independence and distance equivalence. Mathematical analysis of the simplification scheme is also carried out. The proposed fractal signatures are compared with the existing fractal signatures. Experimental results show that the proposed signatures, HM t JHSE and HM t HS t HE, achieve a higher retrieval rate with a lower computational complexity.     

融合特征描述符约束的3维等距模型对应关系计算

目的 为了更准确地构建3维等距模型之间的对应关系,本文提出了一种基于热核签名与波核签名的融合特征描述符计算3维等距模型对应关系的方法。方法 首先计算3维模型Laplace算子获得模型的特征向量和特征值;然后将所得到特征值和特征向量作为基参数分别计算源模型与目标模型的热核签名和波核签名,并将热核签名与波核签名融合为一个新的特征描述符。融合特征描述符作为模型上随机均匀采样点的约束,通过最小值匹配算法得到源模型和目标模型之间的对应关系。结果 实验结果表明,利用融合特征描述符约束进行计算得到的对应关系正确匹配率比热核签名约束计算得到的对应关系匹配率平均提高19.429%,比波核签名约束计算得到的对应关系匹配率平均提高4.857%。结论 本文提出的融合特征描述符适用于计算3维等距模型或近似等距的3维模型之间的对应关系,与单一使用热核签名或波核签名特征描述符相比,可以得到更加准确的对应关系。     

视频镜头分割方法综述

视频序列的镜头分割亦称镜头变化检测是视频检索中的关键技术之一.对五种常用的视频分割算法作了综述,包括像素法、直方图法、X2直方图法、X2直方图分块法、边缘轮廓变化率法,并详细介绍了各种算法中的帧差异值的计算以及介绍了了他们的优缺点,并且通过实验分析对各种算法进行了比较,五种算法的优缺点实验中得到了很好的体现.     

结合拓扑持续性和热扩散理论的3维模型分割

目的 针对已有的3维模型分割方法人为设定过多参数的问题,提出了一种基于拓扑持续性和热亲和度矩阵的3维模型分割方法,只需给定分割部件数即可自动完成分割。方法 首先通过拓扑持续性处理3维模型的热核签名,选取生存期最长的几个特征点作为模型被分割部件的显著特征点,对于模型躯干等无法通过生长周期选取特征点的部件,则选取热核签名的最小值所对应的顶点作为显著特征点,从而获得模型的初始聚类中心;然后使用不同的扩散时间所对应的热亲和度矩阵进行k-means聚类,并根据聚类中心的偏移距离等参数筛选聚类结果,从而获得3维模型的分割结果。结果 选取人体模型进行分割实验,并与其他方法进行对比分析。结果表明,所提出的热亲和度的计算时间明显优于常用的测地距离和幂指数核;相比基于拓扑持续性和基于测地距离的聚类,本文方法可以正确分割模型的各个部件并获得恰当的分割边界。此外,本文方法针对姿态不同的同一非刚体3维模型可以取得一致性的分割结果,而且对模型表面噪声具有较好的鲁棒性。结论 和已有方法相比,本文的基于拓扑持续性和热亲和度矩阵的3维模型分割方法可以在给定分割部件的前提下自动选定聚类中心并获得恰当的分割边界,并广泛适用于常见动物模型的分割。     

3D Shape Matching and Inspection Using Geometric Features and Relational Learning

In this paper we consider the problem of matching 3D sensed data with models and inspection for defects where the correspondence between models and data needs to be solved in robust and efficient ways. We explore the use of machine learning (in particular, relational learning) as an efficient method for solving correspondence (and so, pose estimation) as well as automatically generating rules for acceptable shape variations from training data. As an additional but necessary issue, we also consider the use of view-independent covariance methods for the extraction of surface features used to determine shape signatures which correspond to curvature-like surface attributes. Such features are utilized in the relational learning model.