Lip image segmentation using fuzzy clustering incorporating an elliptic shape function

Recently, lip image analysis has received much attention because its visual information is shown to provide improvement for speech recognition and speaker authentication. Lip image segmentation plays an important role in lip image analysis. In this paper, a new fuzzy clustering method for lip image segmentation is presented. This clustering method takes both the color information and the spatial distance into account while most of the current clustering methods only deal with the former. In this method, a new dissimilarity measure, which integrates the color dissimilarity and the spatial distance in terms of an elliptic shape function, is introduced. Because of the presence of the elliptic shape function, the new measure is able to differentiate the pixels having similar color information but located in different regions. A new iterative algorithm for the determination of the membership and centroid for each class is derived, which is shown to provide good differentiation between the lip region and the nonlip region. Experimental results show that the new algorithm yields better membership distribution and lip shape than the standard fuzzy c-means algorithm and four other methods investigated in the paper.     

A method for preserving the classifiability of digital images after performing a wavelet-based compression

A measure is introduced that predicts the number of coefficients needed to be retained in the discrete wavelet transform of images in order to maintain their classifiability. The introduction of the criterion is based on the energy content of the wavelet coefficients and the order in which they are scanned. The coefficients are weighted based on their location acquired by Morton scanning of the two-dimensional transform plane. The proposed criterion has been tested on MIT-CBCL and AT&T-Olivetti face databases, Columbia Object Image Library (COIL-20) object database, the MNIST handwritten character recognition database and on Caltech-101 object image database. To demonstrate the efficiency of the proposed method, several classification experiments are conducted on each database. Simulation results show that the proposed method can maintain the same classifiability as that of uncompressed data with only a small fraction of the wavelet coefficients.     

Manifold-manifold distance and its application to face recognition with image sets

In this paper, we address the problem of classifying image sets for face recognition, where each set contains images belonging to the same subject and typically covering large variations. By modeling each image set as a manifold, we formulate the problem as the computation of the distance between two manifolds, called manifold-manifold distance (MMD). Since an image set can come in three pattern levels, point, subspace, and manifold, we systematically study the distance among the three levels and formulate them in a general multilevel MMD framework. Specifically, we express a manifold by a collection of local linear models, each depicted by a subspace. MMD is then converted to integrate the distances between pairs of subspaces from one of the involved manifolds. We theoretically and experimentally study several configurations of the ingredients of MMD. The proposed method is applied to the task of face recognition with image sets, where identification is achieved by seeking the minimum MMD from the probe to the gallery of image sets. Our experiments demonstrate that, as a general set similarity measure, MMD consistently outperforms other competing nondiscriminative methods and is also promisingly comparable to the state-of-the-art discriminative methods.     

Multi-manifold metric learning for face recognition based on image sets

In this paper, we propose a new multi-manifold metric learning (MMML) method for the task of face recognition based on image sets. Different from most existing metric learning algorithms that learn the distance metric for measuring single images, our method aims to learn distance metrics to measure the similarity between manifold pairs. In our method, each image set is modeled as a manifold and then multiple distance metrics among different manifolds are learned. With these distance metrics, the intra-class manifold variations are minimized and inter-class manifold variations are maximized simultaneously. For each person, we learn a distance metric by using such a criterion that all the learned distance metrics are person-specific and thus more discriminative. Our method is extensively evaluated on three widely studied face databases, i.e., Honda/UCSD database, CMU MoBo database and YouTube Celebrities database, and compared to the state-of-the-arts. Experimental results are presented to show the effectiveness of the proposed method.     

Automatic 3-D grayscale volume matching and shape analysis.

Recently, shape matching in three dimensions (3-D) has been gaining importance in a wide variety of fields such as computer graphics, computer vision, medicine, and biology, with applications such as object recognition, medical diagnosis, and quantitative morphological analysis of biological operations. Automatic shape matching techniques developed in the field of computer graphics handle object surfaces, but ignore intensities of inner voxels. In biology and medical imaging, voxel intensities obtained by computed tomography (CT), magnetic resonance imagery (MRI), and confocal microscopes are important to determine point correspondences. Nevertheless, most biomedical volume matching techniques require human interactions, and automatic methods assume matched objects to have very similar shapes so as to avoid combinatorial explosions of point. This article is aimed at decreasing the gap between the two fields. The proposed method automatically finds dense point correspondences between two grayscale volumes; i.e., finds a correspondent in the second volume for every voxel in the first volume, based on the voxel intensities. Mutiresolutional pyramids are introduced to reduce computational load and handle highly plastic objects. We calculate the average shape of a set of similar objects and give a measure of plasticity to compare them. Matching results can also be used to generate intermediate volumes for morphing. We use various data to validate the effectiveness of our method: we calculate the average shape and plasticity of a set of fly brain cells, and we also match a human skull and an orangutan skull.     

Radical recognition of handwritten Chinese characters using GA-based kernel active shape modelling

A key property of Chinese characters is that they are composed of fundamental parts called radicals. In this paper, a method to recognise (offline) the radicals of handwritten Chinese characters is proposed that is an extension of the authors' previous work based on active shape modelling. Three stages are involved: a set of example radicals is first described by landmarks using (mostly) automatic landmark labelling, then radicals are modelled as active shapes using kernel principal component analysis, and finally unseen radicals are matched to the reference models using a genetic algorithm to search for the optimal shape parameters. Experiments are conducted on a 430,800 character subset of the freely-available HITPU database, a collection of 751,000 loosely-constrained handwritten Chinese characters. Results show that this new method outperforms existing representative radical approaches, including the authors' own earlier work. Improvements on the previous work are made in two aspects: automatic landmark labelling, which renders this methodology more practical, and the use of a genetic algorithm which finds the optimal shape parameters more effectively, leading to the best results so far reported on this dataset.     

Two-dimensional object recognition through two-stage stringmatching

A two-stage string matching method for the recognition of two-dimensional (2-D) objects is proposed in this work. The first stage is a global cyclic string matching. The second stage is a local matching with local dissimilarity measure computing. The dissimilarity measure function of the input shape and the reference shape are obtained by combining the global matching cost and the local dissimilarity measure. The proposed method has the advantage that there is no need to set any parameter in the recognition process. Experimental results indicate that the hostage string matching approach significantly improves the recognition rates compared to the one-stage string matching method.     

Automatic gait recognition based on statistical shape analysis

Gait recognition has recently gained significant attention from computer vision researchers. This interest is strongly motivated by the need for automated person identification systems at a distance in visual surveillance and monitoring applications. The paper proposes a simple and efficient automatic gait recognition algorithm using statistical shape analysis. For each image sequence, an improved background subtraction procedure is used to extract moving silhouettes of a walking figure from the background. Temporal changes of the detected silhouettes are then represented as an associated sequence of complex vector configurations in a common coordinate frame, and are further analyzed using the Procrustes shape analysis method to obtain mean shape as gait signature. Supervised pattern classification techniques, based on the full Procrustes distance measure, are adopted for recognition. This method does not directly analyze the dynamics of gait, but implicitly uses the action of walking to capture the structural characteristics of gait, especially the shape cues of body biometrics. The algorithm is tested on a database consisting of 240 sequences from 20 different subjects walking at 3 viewing angles in an outdoor environment. Experimental results are included to demonstrate the encouraging performance of the proposed algorithm.     

Shape-based interpolation of multidimensional grey-level images

Shape-based interpolation as applied to binary images causes the interpolation process to be influenced by the shape of the object. It accomplishes this by first applying a distance transform to the data. This results in the creation of a grey-level data set in which the value at each point represents the minimum distance from that point to the surface of the object. (By convention, points inside the object are assigned positive values; points outside are assigned negative values.) This distance transformed data set is then interpolated using linear or higher-order interpolation and is then thresholded at a distance value of zero to produce the interpolated binary data set. Here, the authors describe a new method that extends shape-based interpolation to grey-level input data sets. This generalization consists of first lifting the n-dimensional (n-D) image data to represent it as a surface, or equivalently as a binary image, in an (n+1)-dimensional [(n+1)-D] space. The binary shape-based method is then applied to this image to create an (n+1)-D binary interpolated image. Finally, this image is collapsed (inverse of lifting) to create the n-D interpolated grey-level data set. The authors have conducted several evaluation studies involving patient computed tomography (CT) and magnetic resonance (MR) data as well as mathematical phantoms. They all indicate that the new method produces more accurate results than commonly used grey-level linear interpolation methods, although at the cost of increased computation.     

Multilinguistic handwritten character recognition by Bayesiandecision-based neural networks

In this paper, we present a Bayesian decision-based neural network (BDNN) for multilinguistic handwritten character recognition. The proposed self-growing probabilistic decision-based neural network (SPDNN) adopts a hierarchical network structure with nonlinear basis functions and a competitive credit-assignment scheme. Our prototype system demonstrates a successful utilization of SPDNN to the handwriting of Chinese and alphanumeric character recognition on both public databases (CCL/HCCR1 for Chinese and CEDAR for the alphanumerics) and in-house database (NCTU/NNL). Regarding the performance, experiments on three different databases all demonstrated high recognition (86-94%) accuracy as well as low rejection/acceptance (6.7%) rates. As for the processing speed, the whole recognition process (including image preprocessing, feature extraction, and recognition) consumes approximately 0.27 s/character on a Pentium-100 based personal computer, without using a hardware accelerator or coprocessor     

Ultrasound image segmentation with shape priors: application to automatic cattle rib-eye area estimation.

Automatic ultrasound (US) image segmentation is a difficult task due to the quantity of noise present in the images and the lack of information in several zones produced by the acquisition conditions. In this paper, we propose a method that combines shape priors and image information to achieve this task. In particular, we introduce knowledge about the rib-eye shape using a set of images manually segmented by experts. A method is proposed for the automatic segmentation of new samples in which a closed curve is fitted taking into account both the US image information and the geodesic distance between the evolving curve and the estimated mean rib-eye shape in a shape space. This method can be used to solve similar problems that arise when dealing with US images in other fields. The method was successfully tested over a database composed of 610 US images, for which we have the manual segmentations of two experts.     

Multi-object image retrieval based on shape and topology

We aim at developing a geometry-based retrieval system for multi-object images. We model both shape and topology of image objects including holes using a structured representation called curvature tree (CT); the hierarchy of the CT reflects the inclusion relationships between the objects and holes. To facilitate shape-based matching, triangle-area representation (TAR) of each object and hole is stored at the corresponding node in the CT. The similarity between two multi-object images is measured based on the maximum similarity subtree isomorphism (MSSI) between their CTs. For this purpose, we adapt a continuous optimization approach to solve the MSSI problem and a very effective dynamic programming algorithm to measure the similarity between the attributed nodes. Our matching scheme agrees with many recent findings in psychology about the human perception of multi-object images. Experiments on a database of 1500 logos and the MPEG-7 CE-1 database of 1400 shape images have shown the significance of the proposed method.     

基于z值的分布式密度峰值聚类算法

密度峰值聚类算法由于在发现任意形状簇且不需指定聚类个数等方面具有一定的优势而被广泛关注.但是该算法需要计算数据集中所有点的密度和点对之间的距离,因此不适合处理大规模高维数据集.为此,本文提出了一种基于z值的分布式密度峰值聚类算法,DP-z.本方法利用空间z填充曲线将高维数据集映射到一维空间上,根据数据点的z值信息对数据集分组.为了能够得到正确的结果,需要对分组间数据进行交互,然后并行计算每个点密度和斥群值.DP-z算法在分组间数据交互时采用过滤策略,减少大量无效距离计算和数据传输开销,有效提高算法的执行效率.最后,本文在云计算平台上对DP-z算法进行了验证,实验表明在保证DP-z算法与原始密度峰值聚类算法聚类结果相同的情况下有效的提高了算法执行效率.     

Co-transduction for shape retrieval

In this paper, we propose a new shape/object retrieval algorithm, namely, co-transduction. The performance of a retrieval system is critically decided by the accuracy of adopted similarity measures (distances or metrics). In shape/object retrieval, ideally, intraclass objects should have smaller distances than interclass objects. However, it is a difficult task to design an ideal metric to account for the large intraclass variation. Different types of measures may focus on different aspects of the objects: for example, measures computed based on contours and skeletons are often complementary to each other. Our goal is to develop an algorithm to fuse different similarity measures for robust shape retrieval through a semisupervised learning framework. We name our method co-transduction, which is inspired by the co-training algorithm. Given two similarity measures and a query shape, the algorithm iteratively retrieves the most similar shapes using one measure and assigns them to a pool for the other measure to do a re-ranking, and vice versa. Using co-transduction, we achieved an improved result of 97.72% (bull's-eye measure) on the MPEG-7 data set over the state-of-the-art performance. We also present an algorithm called tri-transduction to fuse multiple-input similarities, and it achieved 99.06% on the MPEG-7 data set. Our algorithm is general, and it can be directly applied on input similarity measures/metrics; it is not limited to object shape retrieval and can be applied to other tasks for ranking/retrieval.     

基于重叠动态网格和模糊隶属度的 手写汉字特征抽取

本文在基于动态网格的手写汉字特征抽取方法中引入重叠网格划分,定义了一种反映书写结构的加权点密度,并提出了一种根据密度投影计算模糊隶属度的方法,这些措施提高了特征的分类能力.各种网格划分方法提取方向线素特征进行了试验比较,结果表明本文的特征抽取方法的在识别率上优于传统的动态网格方法和采用非线性归一化预处理的静态网格方法.     

A unit decomposition technique using fuzzy logic for real-timehandwritten Chinese character recognition

The purpose of this paper is to provide a real-time compact device for inputting handwritten characters to mobile personal digital assistants (PDAs). A novel method for the recognition of online handwritten Chinese characters is presented, giving emphasis to the representation of the patterns using fuzzy logic. The information contained in a character, including shapes of individual strokes and their relative spatial relations, is examined by inference of fuzzy rule base, and the fuzzified representation is organized in a matrix structure. It is well known that Chinese characters are comprised of a set of basic units, representing fundamental meanings. Hence, a unit extraction module is designed to search the possible units within characters. The input character object is recognized by a combination of units with the largest fuzzy confidence degree. The training capability, which provides the unit model set, is performed using the qualitative fuzzy c-means clustering algorithm. An experimental system is implemented that achieves a real-time recognition rate of about 95% with a test set of 550 characters and two cases for each character written by six users. The experimental system has an average real-time recognition speed of 0.5 s/character. The presented approach shows the following two significant advantages over other methods: (1) less training time; and (2) less storage required to store character models. These are two crucial factors in designing PDA devices for mobile communication     

Efficient morphological shape representation

Mathematical morphology is well suited to capturing geometric information. Hence, morphology-based approaches have been popular for object shape representation. The two primary morphology-based approaches-the morphological skeleton and the morphological shape decomposition (MSD)-each represent an object as a collection of disjoint sets. A practical shape representation scheme, though, should give a representation that is computationally efficient to use. Unfortunately, little work has been done for the morphological skeleton and the MSD to address efficiency. We propose a flexible search-based shape representation scheme that typically gives more efficient representations than the morphological skeleton and MSD. Our method decomposes an object into a number of simple components based on homothetics of a set of structuring elements. To form the representation, the components are combined using set union and set difference operations. We use three constituent component types and a thorough cost-based search strategy to find efficient representations. We also consider allowing object representation error, which may yield even more efficient representations.