The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
The present paper details a novel methodology called Meta-Process Model that is able to generate new data-based models for manufacturing processes when no experimental data is available. For that purpose, the concept of Hyper-Models was used to create a higher level of abstraction of these manufacturing processes, along with a Statistical Shape Model (SSM) that is able to capture the modes of shape...
The present work proposes a review and comparison of different Nonlocal Means (NLM) methods in the task of digital image filtering. Some different alternatives to change the classical exponential kernel function used in NLM methods are explored. Moreover, some approaches that change the geometry of the neighborhood and use dimensionality reduction of the neighborhood or patches onto principal component...
What are the attributes and features of faces that allow humans or machines to make most reliable inferences from visible to occluded regions of the face, or from shape to texture and vice versa? While both the Human Visual System and many example-based algorithms rely on correlations, these are implicit and difficult to visualize. This paper identifies and visualizes the most reliable correlations...
In this paper, we describe the use of concepts from the areas of structural and statistical pattern recognition for the purposes of recovering a mapping which can be viewed as an operator on the graph attribute-set. This mapping can be used to embed graphs into spaces where tasks such as classification and retrieval can be effected. To do this, we depart from concepts in graph theory so as to introduce...
Conditional Random Fields (CRFs) can be used as a discriminative approach for simultaneous sequence segmentation and frame labeling. Latent-Dynamic Conditional Random Fields (LDCRFs) incorporates hidden state variables within CRFs which model sub-structure motion patterns and dynamics between labels. Motivated by the success of LDCRFs in gesture recognition, we propose a framework for automatic facial...
In Kansei Engineering, sample shapes have been treated as categorical variables in nominal scale. In this paper, we describe the method for focusing on product shapes concerning customers' Kansei, to avoid confusing effects on Kansei caused by other properties such as sizes, orientations, colors, textures, and so on. We standardized the shapes of sample products and made them into statistical values...
We propose a shape model fitting algorithm that uses linear programming optimization. Most shape model fitting approaches (such as ASM, AAM) are based on gradient-descent-like local search optimization and usually suffer from local minima. In contrast, linear programming (LP) techniques achieve globally optimal solution for linear problems. In [1], a linear programming scheme based on successive convexification...
Image-based morphometry of cells, tissues, and organs is an important topic in biomedical image analysis. We propose a novel method to characterize the morphological information that discriminates between two populations of morphological exemplars (cells, organs). We first demonstrate that the application of standard techniques such as Fisher linear discriminant analysis (FDA) can lead to undesirable...
This paper presents a unified framework for human action classification and localization in video using structured learning of local space-time features. Each human action class is represented by a set of its own compact set of local patches. In our approach, we first use a discriminative hierarchical Bayesian classifier to select those space-time interest points that are constructive for each particular...
The paper presents an extension of active appearance models (AAMs) that is better capable of dealing with the large variation in face appearance that is encountered in large multi-person face data sets. Instead of the traditional PCA-based texture model, our extended AAM employs a mixture of probabilistic PCA to describe texture variation, leading to a richer model. The resulting extended AAM can...
This paper presents an algorithm for object localization and segmentation. The algorithm uses machine learning, and statistical and combinatorial optimization tools to build a tracker that is robust to noise and occlusions. The method is based on a novel energy formulation and its dual use for object localization and segmentation. The energy uses kernel principal component analysis to incorporate...
We propose an algorithm for non-rigidly registering a 3D template mesh with a dense point cloud, using a morphable shape model to control the deformation of the template mesh. A cost function involving nonrigid shape as well as rigid pose is proposed. Registration is performed by minimizing a first-order approximation of the cost function in the Iterative Closest Points framework. We show how a complex...
This paper propose a new shape descriptor for 3D model retrieval. The shape descriptor is using a histogram of 2D images sliced along the x-, y-, and z-coordinates for measuring the similarity in 3D models. We demonstrate the proposed 3D retrieval system with an intermediate example at each step. Experimental results show that the proposed approach outperforms the previous approaches.
3-dimensional (3D) model retrieval is one of an important research fields to retrieve a query for models with matching shape from the database. This paper proposes a new shape descriptor using histograms of 2D slice images to cut in the x-, y-, and z-coordinates, respectively for solving the similarity measure from 3D models. Our approach is to compute the slices of 3D model for the x-, y-, and z-coordinates,...
Active shape model (ASM) has been widely accepted as one of the best methods for image understanding. In this paper, we propose to improve ASM by introducing Procrustes analysis technique in the matching of feature landmark points of a set of training images and strengthening the edge in searching face profile. Firstly, each landmark point labeled manually is matched by its local profile in its current...
This paper presents a computer vision based virtual learning environment for teaching communicative hand gestures used in Sign Language. A virtual learning environment was developed to demonstrate signs to the user. The system then gives real time feedback to the user on their performance of the demonstrated sign. Gesture features are extracted from a standard web-cam video stream and shape and trajectory...
We have investigated a technique for recognising faces invariant of facial expressions. We apply multi-linear tensor algebra, which subsumes linear algebra, to analyse and recognise 3D face surfaces. This potent framework possesses a remarkable ability to deal with the shortcomings of principle component analysis in less constrained situations. A set of vector spaces can be used to represent the variation...
In this paper, we propose a tensor-based active appearance model (AAM) which improves the fitting performance of conventional AAM. Tensor-based AAM generates the specific AAM basis vectors by indexing the model tensor in terms of the estimated input image variations. Experimental results show that the proposed tensor-based AAM reduces the average fitting error than the conventional AAM significantly.
Statistical shape modelling is a technique whereby the variation of shape across the population is modelled by principal component analysis (PCA) on a set of sample shape vectors. The number of principal modes retained in the model (PCA dimension) is often determined by simple rules, for example choosing those cover a percentage of total variance. We show that this rule is highly dependent on sample...
Linear and multi-linear models of object shape/appearance (PCA, 3 DMM, AAM/ASM, multilinear tensors) have been very popular in computer vision. In this paper, we analyze the validity of these models from the fundamental physical laws of object motion and image formation. We rigorously prove that the image appearance space can be closely approximated to be locally multilinear, with the illumination...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.