Synthesis of workspaces of planar manipulators with arbitrary topology using shape representation and simulated annealing

This paper presents a general methodology for the synthesis of the external boundary of the workspaces of a planar manipulator with arbitrary topology. Both the desired workspace and the manipulator workspaces are identified by their boundaries and are treated as simple closed polygons. The paper introduces the concept of best match configuration and shows that the corresponding transformation can be obtained by using the concept of shape normalization available in image processing literature. Introduction of the concept of shape in workspace synthesis allows highly accurate synthesis with fewer numbers of design variables. This paper uses a new global property based vector representation for the shape of the workspaces which is computationally efficient because six out of the seven elements of this vector are obtained as a by-product of the shape normalization procedure. The synthesis of workspaces is formulated as an optimization problem where the distance between the shape vector of the desired workspace and that of the workspace of the manipulator at hand are minimized by changing the dimensional parameters of the manipulator. In view of the irregular nature of the error manifold, the statistical optimization procedure of simulated annealing has been used. A number of worked-out examples illustrate the generality and efficiency of the present method. (C) 1998 Elsevier Science Ltd. All rights reserved.

The Role of Knowledge in Visual Shape Representation

This report shows how knowledge about the visual world can be built into a shape representation in the form of a descriptive vocabulary making explicit the important geometrical relationships comprising objects' shapes. Two computational tools are offered: (1) Shapestokens are placed on a Scale-Space Blackboard, (2) Dimensionality-reduction captures deformation classes in configurations of tokens. Knowledge lies in the token types and deformation classes tailored to the constraints and regularities ofparticular shape worlds. A hierarchical shape vocabulary has been implemented supporting several later visual tasks in the two-dimensional shape domain of the dorsal fins of fishes.

Investigating shape representation in area V4 with HMAX: Orientation and Grating selectivities

The question of how shape is represented is of central interest to understanding visual processing in cortex. While tuning properties of the cells in early part of the ventral visual stream, thought to be responsible for object recognition in the primate, are comparatively well understood, several different theories have been proposed regarding tuning in higher visual areas, such as V4. We used the model of object recognition in cortex presented by Riesenhuber and Poggio (1999), where more complex shape tuning in higher layers is the result of combining afferent inputs tuned to simpler features, and compared the tuning properties of model units in intermediate layers to those of V4 neurons from the literature. In particular, we investigated the issue of shape representation in visual area V1 and V4 using oriented bars and various types of gratings (polar, hyperbolic, and Cartesian), as used in several physiology experiments. Our computational model was able to reproduce several physiological findings, such as the broadening distribution of the orientation bandwidths and the emergence of a bias toward non-Cartesian stimuli. Interestingly, the simulation results suggest that some V4 neurons receive input from afferents with spatially separated receptive fields, leading to experimentally testable predictions. However, the simulations also show that the stimulus set of Cartesian and non-Cartesian gratings is not sufficiently complex to probe shape tuning in higher areas, necessitating the use of more complex stimulus sets.

Sparse shape representation using the Laplace-Beltrami eigenfunctions and its application to modeling subcortical structures

We present a new sparse shape modeling framework on the Laplace-Beltrami (LB) eigenfunctions. Traditionally, the LB-eigenfunctions are used as a basis for intrinsically representing surface shapes by forming a Fourier series expansion. To reduce high frequency noise, only the first few terms are used in the expansion and higher frequency terms are simply thrown away. However, some lower frequency terms may not necessarily contribute significantly in reconstructing the surfaces. Motivated by this idea, we propose to filter out only the significant eigenfunctions by imposing l1-penalty. The new sparse framework can further avoid additional surface-based smoothing often used in the field. The proposed approach is applied in investigating the influence of age (38-79 years) and gender on amygdala and hippocampus shapes in the normal population. In addition, we show how the emotional response is related to the anatomy of the subcortical structures.

Spatial information in histograms for shape representation

Histograms have been used for Shape Representation and Retrieval. In this paper, the traditional technique has been modified to capture additional information. We compare the performance of the proposed method with the traditional method by performing experiments on a database of shapes. The results show that the proposed enhancement to the histogram based method improves the effectiveness significantly.

3D die shape optimisation for net-shape forging of aerofoil blades

This paper reports on work in developing a finite element (FE) based die shape optimisation for net-shape forging of 3D aerofoil blades for aeroengine applications. Quantitative representations of aerofoil forging tolerances were established to provide a correlation between conventional dimensional and shape specifications in forging production and those quantified in FE simulation. A new direct compensation method was proposed, employing variable weighting factors to minimise the total forging tolerances in forging optimisation computations. A surface approximation using a B-spline surface was also developed to ensure improved die surface quality for die shape representation and design. For a Ni-alloy blade test case, substantial reduction in dimensional and shape tolerances was achieved using the developed die shape optimisation system.

Representation and Detection of Shapes in Images

We present a set of techniques that can be used to represent and detect shapes in images. Our methods revolve around a particular shape representation based on the description of objects using triangulated polygons. This representation is similar to the medial axis transform and has important properties from a computational perspective. The first problem we consider is the detection of non-rigid objects in images using deformable models. We present an efficient algorithm to solve this problem in a wide range of situations, and show examples in both natural and medical images. We also consider the problem of learning an accurate non-rigid shape model for a class of objects from examples. We show how to learn good models while constraining them to the form required by the detection algorithm. Finally, we consider the problem of low-level image segmentation and grouping. We describe a stochastic grammar that generates arbitrary triangulated polygons while capturing Gestalt principles of shape regularity. This grammar is used as a prior model over random shapes in a low level algorithm that detects objects in images.

Coherence based histograms for shape retrieval

Histograms have been used for Shape Representation and Retrieval. The drawback of the histograms method is that histograms can be same for dissimilar shapes, which renders the method less effective for retrieval of shapes. In this paper, we describe the concept of coherence. We show how coherence can be used with distance and angular histograms. We perform experiments to test the effectiveness of the proposed method. It is found that coherence improves accuracy of retrieval significantly.

Angular histograms for shape retrieval

Distance histograms have been used for Shape Representation and Retrieval [1][2]. In this paper, we have proposed the use of angular histograms for shape representation. We have implemented a system for conducting experiments and evaluating the effectiveness of the proposed method. The proposed method is compared with the distance histograms method. It is found that the
proposed method is effective.

Connectivity-based shape descriptors

In this paper, we propose a method for indexing and retrieval of images based on shapes of objects. The concept of connectivity is introduced. 3D models are used to represent 2D images. 2D images are decomposed a priori using connectivity which is followed by 3D model construction. 3D model descriptors are obtained for 3D models and used to represent the underlying 2D shapes. We have used spherical harmonics descriptors as the 3D model descriptors. Difference between two images is computed as the Euclidean distance between their descriptors. Experiments are performed to test the effectiveness of spherical harmonics for retrieval of 2D images. The proposed method is compared with methods based on principal components analysis (PCA) and generic Fourier descriptors (GFD). It is found that the proposed method is effective. Item S8 within the MPEG-7 still images content set is used for performing experiments.

Spectral shape descriptor using spherical harmonics

In this paper, we propose a spectral descriptor for shapes of objects. The method relies on transforming the 2D objects into 3D space; distance transform and scale space theory is used to transform objects into 3D space. Spherical harmonics of the voxel grid are used to obtain shape descriptors. The proposed methods are compared against two existing methods which use spherical harmonics for shape based retrieval of images. Comparison is done based on ranking of images which is articulated in recall-precision curves. MPEG-7 Still Images Content Set is used for performing experiments. Experimental results show that the performance of the proposed descriptor is significantly better than other methods in the same category.

The silent witness: art as a mode of representation of voices and visions of how,as a woman, I build borders and bridges in enacting my identit(ies)

Feminist theorists unveil how women negotiate their identities within complex entanglements of social constructs such as race, ethnicity, religious belief and practices, cultural tradition, and values. Feminist artists use subjective experiences that shape representation and performativity in empowering women to have a ‘voice’. In this paper, I focus on ‘breaking silences’ through series of my artworks (as part of my PhD research) that represent self-narratives as subjectivities of life experiences, contingencies, and cultural shifts through migration transitions as new ways of figuration and reflection on such issues. I look through discourses of gender differences, nomadic subjectivity, and new ways of figurations (Braidotti 2011, 10) and the affect theory (Gregg and Seigworth 2010), and the concept of giving ‘voice’ (Berlant 2011). Such discourses frame how I interrogate and represent my gendered identities.

Automatic object segmentation from calibrated images

This paper addresses the problem of automatically obtaining the object/background segmentation of a rigid 3D object observed in a set of images that have been calibrated for camera pose and intrinsics. Such segmentations can be used to obtain a shape representation of a potentially texture-less object by computing a visual hull. We propose an automatic approach where the object to be segmented is identified by the pose of the cameras instead of user input such as 2D bounding rectangles or brush-strokes. The key behind our method is a pairwise MRF framework that combines (a) foreground/background appearance models, (b) epipolar constraints and (c) weak stereo correspondence into a single segmentation cost function that can be efficiently solved by Graph-cuts. The segmentation thus obtained is further improved using silhouette coherency and then used to update the foreground/background appearance models which are fed into the next Graph-cut computation. These two steps are iterated until segmentation convergences. Our method can automatically provide a 3D surface representation even in texture-less scenes where MVS methods might fail. Furthermore, it confers improved performance in images where the object is not readily separable from the background in colour space, an area that previous segmentation approaches have found challenging. © 2011 IEEE.