形状的全尺度可视化表示与识别

目的视觉目标的形状特征表示和识别是图像领域中的重要问题。在实际应用中,视角、形变、遮挡和噪声等干扰因素造成识别精度较低,且大数据场景需要算法具有较高的学习效率。针对这些问题,本文提出一种全尺度可视化形状表示方法。方法在尺度空间的所有尺度上对形状轮廓提取形状的不变量特征,获得形状的全尺度特征。将获得的全部特征紧凑地表示为单幅彩色图像,得到形状特征的可视化表示。将表示形状特征的彩色图像输入双路卷积网络模型,完成形状分类和检索任务。结果通过对原始形状加入旋转、遮挡和噪声等不同干扰的定性实验,验证了本文方法具有旋转和缩放不变性,以及对铰接变换、遮挡和噪声等干扰的鲁棒性。在通用数据集上进行形状分类和形状检索的定量实验,所得准确率在不同数据集上均超过对比算法。在MPEG-7数据集上精度达到99.57%,对比算法的最好结果为98.84%。在铰接和射影变换数据集上皆达到100%的识别精度,而对比算法的最好结果分别为89.75%和95%。结论本文提出的全尺度可视化形状表示方法,通过一幅彩色图像紧凑地表达了全部形状信息。通过卷积模型既学习了轮廓点间的形状特征关系,又学习了不同尺度间的形状特征关系。本文方法...     

Planar shape matching based on binary tree shape representation

In this paper we suggest a new way of representing planar two-dimensional shapes and a shape matching method which utilizes the new representation. Through merging of the neighboring boundary runs, a shape can be partitioned into a set of triangles. These triangles are inherently connected according to a binary tree structure. Here we use the binary tree with the triangles as its nodes to represent the shape. This representation is found to be insensitive to shape translation, rotation, scaling and skewing changes due to viewer's location changes (or the object's pose changes). Furthermore, the representation is of multiresolution.

In shape matching we compare the two trees representing two given shapes node by node according to the breadth-first tree traversing sequence. The comparison is done from top of the tree and moving downward, which means that we first compare the lower resolution approximations of the two shapes. If the two approximations are different, the comparison stops. Otherwise, it goes on and compares the finer details of the two shapes. Only when the two shapes are very similar, will the two corresponding trees be compared entirely. Thus, the matching algorithm utilizes the multiresolution characteristic of the tree representation and appears to be very efficient.     

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.     

Object detection,shape recovery,and 3D modelling by depth-encoded hough voting

Detecting objects, estimating their pose, and recovering their 3D shape are critical problems in many vision and robotics applications. This paper addresses the above needs using a two stages approach. In the first stage, we propose a new method called DEHV – Depth-Encoded Hough Voting. DEHV jointly detects objects, infers their categories, estimates their pose, and infers/decodes objects depth maps from either a single image (when no depth maps are available in testing) or a single image augmented with depth map (when this is available in testing). Inspired by the Hough voting scheme introduced in [1], DEHV incorporates depth information into the process of learning distributions of image features (patches) representing an object category. DEHV takes advantage of the interplay between the scale of each object patch in the image and its distance (depth) from the corresponding physical patch attached to the 3D object. Once the depth map is given, a full reconstruction is achieved in a second (3D modelling) stage, where modified or state-of-the-art 3D shape and texture completion techniques are used to recover the complete 3D model. Extensive quantitative and qualitative experimental analysis on existing datasets [2], [3], [4] and a newly proposed 3D table-top object category dataset shows that our DEHV scheme obtains competitive detection and pose estimation results. Finally, the quality of 3D modelling in terms of both shape completion and texture completion is evaluated on a 3D modelling dataset containing both in-door and out-door object categories. We demonstrate that our overall algorithm can obtain convincing 3D shape reconstruction from just one single uncalibrated image.     

Fast facial shape recovery from a single image with general, unknown lighting by using tensor representation

In this paper, we propose a fast 3-D facial shape recovery algorithm from a single image with general, unknown lighting. In order to derive the algorithm, we formulate a nonlinear least-square problem with two parameter vectors which are related to personal identity and light conditions. We then combine the spherical harmonics for the surface normals of a human face with tensor algebra and show that in a certain condition, the dimensionality of the least-square problem can be further reduced to one-tenth of the regular subspace-based model by using tensor decomposition (N-mode SVD), which greatly speeds up the computations. In order to enhance the shape recovery performance, we have incorporated prior information in updating the parameters. In the experiment, the proposed algorithm takes less than 0.4 s to reconstruct a face and shows a significant performance improvement over other reported schemes.     

Efficient morphological shape representation by varying overlapping levels among representative disks

The morphological skeleton transform, the morphological shape decomposition, and the overlapped morphological shape decomposition are three basic morphological shape representation schemes. In this paper, we propose a new way of generalizing these basic representation algorithms to improve representational efficiency. In all three basic algorithms, a fixed overlapping policy is used to control the overlapping relationships among representative disks of different sizes. In our new algorithm, different overlapping policies are used to generate shape components that have different overlapping relationships among themselves. The overlapping policy is selected dynamically according to local shape features. Experiments show that compared to the three basic algorithms, our algorithm produces more efficient representations with lower numbers of representative points.     

基于多尺度形状分析的叶形识别系统

叶形自动识别系统使用一种改进了的边界跟踪算法检测叶片边界,应用多尺度形状分析技术有效地提取出规范锯齿长度和曲率尺度空间图像极大值点集两个曲率特征。综合叶片的离心率、似圆率和这两个边界曲率特征来检索叶片数据库,进行形状匹配,实现叶片自动分类。实验结果表明,该系统使用的技术能大幅提高叶形识别的精确率和检索率。     

A general shape context framework for object identification

A general shape context framework is proposed for object/image retrieval in occluded and cluttered environment with hundreds of models as the potential matches of an input. The approach is general since it does not require separation of input objects from complex background. It works by first extracting consistent and structurally unique local neighborhood information from inputs or models, and then voting on the optimal matches. Its performance degrades gracefully with respect to the amount of structural information that is being occluded or lost. The local neighborhood information applicable to the system can be shape, color, texture feature, etc. Currently, we employ shape information only. The mechanism of voting is based on a novel hyper cube based indexing structure, and driven by dynamic programming. The proposed concepts have been tested on database with thousands of images. Very encouraging results have been obtained.     

Object recognition by grasping

In this paper, we describe a method for recognizing both the three-dimensional pattern and the size of objects by grasping them with multijointed fingers equipped with tactile sensors. First, the bending data of the joint is sorted out by analyzing the distribution pattern of the sensors in contact. Then the appropriate pattern is determined by calculating the values of the several linear discriminant functions provided for each contact pattern. Classification of the size of an object is achieved by applying a linear machine with a maximum-value selector to the bending form of the joints. The results of the experiments show that the most useful discriminant function is a linear one. Its percentage of total correctness is highest for the pattern recognition of an object.     

Spectra of shape contexts: An application to symbol recognition

The pixel-level constraint (PLC) histograms are known for robustness and invariance in symbol recognition but limited in O(N³) complexity. This paper proves that matching two PLC histograms can approximately be solved as matching the power spectra of the corresponding shape contexts. As a result, spectra of shape contexts (SSC) inherit robustness and invariance from PLC while the computational cost can be reduced. Moreover, a maximum clique based scheme is proposed for outlier rejection. The theoretical and experimental validation justifies that SSC possesses the desired properties for symbol recognition, that is, robustness, invariance, and efficiency. It outperforms PLC in terms of robustness and time efficiency, and shape context in terms of rotation invariance.     

Learning to generate novel views of objects for class recognition

Multi-view object class recognition can be achieved using existing approaches for single-view object class recognition, by treating different views as entirely independent classes. This strategy requires a large amount of training data for many viewpoints, which can be costly to obtain. We describe a method for constructing a weak three-dimensional model from as few as two views of an object of the target class, and using that model to transform images of objects from one view to several other views, effectively multiplying their value for class recognition. Our approach can be coupled with any 2D image-based recognition system. We show that automatically transformed images dramatically decrease the data requirements for multi-view object class recognition.     

基于形状特征的叶片图像识别算法比较研究

植物是生命的主要形态之一,其种类已达40多万种,对其进行分类识别在生物多样性保护,生态农业,生物安全中有着重要的意义。不同的种类的植物一般有着不同的叶片形状,因此叶片的形状特征在植物分类中扮演着重要的角色。作为计算机视觉的一个重要应用的植物叶片图像识别,近些年来受到了学者们的关注,产生了大量的研究成果。但由于植物种类巨大,叶片图像存在的类内差异大、类间差异小和叶片的自遮挡等问题等诸多问题,使得叶片图像的识别仍然是目前计算机视觉应用研究的一个热点。对近些年来的基于形状特征的叶片图像识别算法进行了综述和比较,对现有的算法进行了分类,对目前各类最先进的识别算法进行了分析和比较。此外,还介绍了常用的叶片图像测试集和性能评估方法,并将各类算法进行了实验结果的比较研究。研究工作既为现有的植物叶片识别算法的实际应用提供了指导,又为今后进一步研究新的高性能的识别算法提出了努力的方向。     

Object detection by global contour shape

We present a method for object class detection in images based on global shape. A distance measure for elastic shape matching is derived, which is invariant to scale and rotation, and robust against non-parametric deformations. Starting from an over-segmentation of the image, the space of potential object boundaries is explored to find boundaries, which have high similarity with the shape template of the object class to be detected. An extensive experimental evaluation is presented. The approach achieves a remarkable detection rate of 83-91% at 0.2 false positives per image on three challenging data sets.     

Bayesian shape model for facial feature extraction and recognition

A facial feature extraction algorithm using the Bayesian shape model (BSM) is proposed in this paper. A full-face model consisting of the contour points and the control points is designed to describe the face patch, using which the warping/normalization of the extracted face patch can be performed efficiently. First, the BSM is utilized to match and extract the contour points of a face. In BSM, the prototype of the face contour can be adjusted adaptively according to its prior distribution. Moreover, an affine invariant internal energy term is introduced to describe the local shape deformations between the prototype contour in the shape domain and the deformable contour in the image domain. Thus, both global and local shape deformations can be tolerated. Then, the control points are estimated from the matching result of the contour points based on the statistics of the full-face model. Finally, the face patch is extracted and normalized using the piece-wise affine triangle warping algorithm. Experimental results based on real facial feature extraction demonstrate that the proposed BSM facial feature extraction algorithm is more accurate and effective as compared to that of the active shape model (ASM).     

A stochastic graph grammar for compositional object representation and recognition

This paper illustrates a hierarchical generative model for representing and recognizing compositional object categories with large intra-category variance. In this model, objects are broken into their constituent parts and the variability of configurations and relationships between these parts are modeled by stochastic attribute graph grammars, which are embedded in an And-Or graph for each compositional object category. It combines the power of a stochastic context free grammar (SCFG) to express the variability of part configurations, and a Markov random field (MRF) to represent the pictorial spatial relationships between these parts. As a generative model, different object instances of a category can be realized as a traversal through the And-Or graph to arrive at a valid configuration (like a valid sentence in language, by analogy). The inference/recognition procedure is intimately tied to the structure of the model and follows a probabilistic formulation consisting of bottom-up detection steps for the parts, which in turn recursively activate the grammar rules for top-down verification and searches for missing parts. We present experiments comparing our results to state of art methods and demonstrate the potential of our proposed framework on compositional objects with cluttered backgrounds using training and testing data from the public Lotus Hill and Caltech datasets.