Retrieval Of Similar Shapes Research Articles

Automatic Parametric Modeling Technique for Structural Design Standardization

The challenge in designing new three-dimensional (3D) shapes is that considerable manual effort is required for repeated designing and verification to satisfy the required specifications. Extracting and standardizing parametric design rules from a designed 3D shape dataset will be useful for drastically reducing the design time. This paper describes a framework of automatically generating parametric models, design rules, in order to standardize designs for structural systems. In this framework, a design dataset whose dimensions and shapes have parametric relationships with a target shape is extracted using a new retrieval method. This method is an improvement of a conventional similar shape retrieval method. After the extraction of the design dataset, the corresponding parts between the collected shapes are automatically identified and parametric models are automatically generated. This new similar shape retrieval method has two improvements over the conventional method that uses images of 3D shapes captured from multiple directions. First, 3D shapes are converted to unit shapes by stretching or shrinking along each axis. Second, similar shapes are extracted using a special artificial intelligence (AI) model that learns parametric relationships. The effectiveness of the proposed framework is evaluated using the 3D shape data of various structural shapes. Although the accuracy rate of similar-shape retrieval based on parametric relationships was 62% in the conventional method, by using unit shapes and special AIs, it was improved to 99% in the new method. Moreover, the corresponding parts between similar shapes were automatically identified, and parametric models were automatically generated. The effectiveness of this framework has been demonstrated.

A Computer Vision Framework for Automated Shape Retrieval

With the increasing number of images generated every day, textual annotation of images for image mining becomes impractical and inefficient. Thus, computer vision based image retrieval has received considerable interest in recent years. One of the fundamental characteristics of any image representation of an object is its shape which plays a vital role to recognize the object at primitive level. Keeping this view as the primary motivational focus, we propose a shape descriptive frame work using a multilevel tree structured representation called Hierarchical Convex Polygonal Decomposition (HCPD). Such a frame work explores different degrees of convexity of an object’s contour-segments in the course of its construction. The convex and non-convex segments of an object’s contour are discovered at every level of the HCPD-tree generation by repetitive convex-polygonal approximation of contour segments. We have also presented a novel shape-string-encoding scheme for representing the HCPD-tree which allows us touse the popular concept of string-edit distance to compute shape similarity score between two objects. The proposed framework when deployed for similar shape retrieval task demonstrates reasonably good performance in comparison with other popular shape-retrieval algorithms.

Development of a methodology for retrieval of similarly shaped CAD models

The current interest amongst researchers in CAD field is the retrieval of components similar to a predefined geometry from a database of CAD models. The design efforts made earlier can be used to reduce the modelling time. After critically reviewing the available literature in this field, the authors propose a new approach to upload and retrieve information on CAD models that will result in reduced computational effort. To discriminate the shape information, principles of solid analytical geometry were used to incorporate sensitivity in differentiating concave and convex features. Shape descriptors are used for similar shape retrieval and benchmarking was done against various standard measures and these findings are reported in this paper.

WARP: accurate retrieval of shapes using phase of Fourier descriptors and time warping distance

Effective and efficient retrieval of similar shapes from large image databases is still a challenging problem in spite of the high relevance that shape information can have in describing image contents. In this paper, we propose a novel Fourier-based approach, called WARP, for matching and retrieving similar shapes. The unique characteristics of WARP are the exploitation of the phase of Fourier coefficients and the use of the Dynamic Time Warping (DTW) distance to compare shape descriptors. While phase information provides a more accurate description of object boundaries than using only the amplitude of Fourier coefficients, the DTW distance permits us to accurately match images even in the presence of (limited) phase shiftings. In terms of classical precision/recall measures, we experimentally demonstrate that WARP can gain, say, up to 35 percent in precision at a 20 percent recall level with respect to Fourier-based techniques that use neither phase nor DTW distance.

Robust normalization of silhouettes for recognition applications

In this work we introduce a new silhouette normalization method, which is robust with respect to deformations and enables the use of image domain based similarity measures for recognition applications. It is shown that a template matching operation can provide an accurate shortlist of candidates suitable for a more exact matching engine in spite of projective transformations and silhouette deformations. This retrieval of similar shapes has a low computational cost and has been tested with silhouettes of natural and man-made objects.

Retrieving Similar Shapes Effectively and Efficiently

In this paper, we address the following problem: given a large collection of shapes and a query shape, retrieve all shapes (from the shape database) that are similar to the query shape. A generalized centroid-radii model is used to model all forms of shapes — convex shapes, concave shapes and shapes with “holes”. Under the model, a shape is represented by a set of vectors, each obtained from the radii emanating from the centroid of a virtual concentric ring. The model can also facilitate multi-resolution and similarity retrievals. Furthermore, using the model, the shape of an object can be transformed into a point in a high dimensional data space. To speed up the retrieval of similar shapes, we also propose a multi-level R-tree index, called the Nested R-trees (NR-trees). Unlike traditional high-dimensional index structures that index a high-dimensional point as it is (with its full dimension), the NR-trees splits the dimensionality of the point into a set of lower dimensions that are indexed by levels of the NR-trees. We also proposed a quick filtering mechanism to further prune the search space. We implemented a shape retrieval system that employs the generalized centroid-radii model and the NR-trees with the filtering mechanism. Our experimental study shows the effectiveness of the proposed shape model, and the efficiency of the NR-trees. The results also show that the filtering mechanism can significantly reduce the retrieval time.

Efficient retrieval of similar shapes

We propose an indexing technique for the fast retrieval of objects in 2D images based on similarity between their boundary shapes. Our technique is robust in the presence of noise and supports several important notions of similarity including optimal matches irrespective of variations in orientation and/or position. Our method can also handle size-invariant matches using a normalization technique, although optimality is not guaranteed here. We implemented our method and performed experiments on real (hand-written digits) data. Our experimental results showed the superiority of our method compared to search based on sequential scanning, which is the only obvious competitor. The performance gain of our method increases with any increase in the number or the size of shapes.

Similar-shape retrieval in shape data management

Addresses the problem of similar-shape retrieval, where shapes or images in a shape database that satisfy specified shape-similarity constraints with respect to the query shape or image must be retrieved from the database. In its simplest form, the similar-shape retrieval problem can be stated as, "retrieve or select all shapes or images that are visually similar to the query shape or the query image's shape". We focus on databases of 2D shapes-or equivalently, databases of images of flat or almost flat objects. (We use the terms "object" and "shape" interchangeably). Two common types of 2D objects are rigid objects, which have a single rigid component called a link, and articulated objects, which have two or more rigid components joined by movable (rotating or sliding) joints. An ideal similar-shape retrieval technique must be general enough to handle images of articulated as well as rigid objects. It must be flexible enough to handle simple query images, which have isolated shapes, and complex query images, which have partially visible, overlapping or touching objects. We discuss the central issues in similar-shape retrieval and explain how these issues are resolved in a shape retrieval scheme called FIBSSR (Feature Index-Based Similar-Shape Retrieval). This new similar-shape retrieval system effectively models real-world applications.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>