Showing papers on "Scale-invariant feature transform published in 2003"

Shape recognition with edge-based features

Abstract: In this paper we describe an approach to recognizing poorly textured objects, that may contain holes and tubular parts, in cluttered scenes under arbitrary viewing conditions. To this end we develop a number of novel components. First, we introduce a new edge-based local feature detector that is invariant to similarity transformations. The features are localized on edges and a neighbourhood is estimated in a scale invariant manner. Second, the neighbourhood descriptor computed for foreground features is not affected by background clutter, even if the feature is on an object boundary. Third, the descriptor generalizes Lowe's SIFT method to edges. An object model is learnt from a single training image. The object is then recognized in new images in a series of steps which apply progressively tighter geometric restrictions. A final contribution of this work is to allow sufficient flexibility in the geometric representation that objects in the same visual class can be recognized. Results are demonstrated for various object classes including bikes and rackets.

Multi-scale phase-based local features

Abstract: Local feature methods suitable for image feature based object recognition and for the estimation of motion and structure are composed of two steps, namely the 'where' and 'what' steps. The 'where' step (e.g., interest point detector) must select image points that are robustly localizable under common image deformations and whose neighborhoods are relatively informative. The 'what' step (e.g., local feature extractor) then provides a representation of the image neighborhood that is semi-invariant to image deformations, but distinctive enough to provide model identification. We present a quantitative evaluation of both the 'where' and the 'what' steps for three recent local feature methods: a) phase-based local features (Carneiro and Jepson, 2002), b) differential invariants (Schmid and Mohr, 1997), and c) the scale invariant feature transform (SIFT) (Lowe, 1999). Moreover, in order to make the phase-based approach more comparable to the other two approaches, we also introduce a new form of multi-scale interest point detector to be used for its 'where' step. The results show that the phase-based local features lead to better performance than the other two approaches when dealing with common illumination changes, 2D rotation, and sub-pixel translation. On the other hand, the phase-based local features are somewhat more sensitive to scale and large shear changes than the other two methods. Finally, we demonstrate the viability of the phase-based local feature in a simple object recognition system.

Cloth Motion Capture

Abstract: Recent years have seen an increased interest in motion capture systems. Current systems, however, are limitedto only a few degrees of freedom, so that effectively only the motion of linked rigid bodies can be acquired. Wepresent a system for the capture of deformable surfaces, most notably moving cloth, including both geometry andparameterisation. We recover geometry using stereo correspondence, and use the Scale Invariant Feature Transform(SIFT) to identify an arbitrary pattern printed on the cloth, even in the presence of fast motion. We describea novel seed-and-grow approach to adapt the SIFT algorithm to deformable geometry. Finally, we interpolatefeature points to parameterise the complete geometry. Categories and Subject Descriptors (according to ACM CCS): I.3.5 [Computer Graphics]: Physically based modelingI.4.8 [Image Processing and Computer Vision]: Scene analysis

A graphics hardware implementation of the generalized Hough transform for fast object recognition, scale, and 3D pose detection

Abstract: The generalized Hough transform constitutes a wellknown approach to object recognition and pose detection. To attain reliable detection results, however, a very large number of candidate object poses and scale factors need to be considered. We employ an inexpensive, consumer-market graphics-card as the "poor man's" parallel processing system. We describe the implementation of a fast and enhanced version of the generalized Hough transform on graphics hardware. Thanks to the high bandwidth of on-board texture memory, a single pose can be evaluated in less than 3 ms, independent of the number of edge pixels in the image. From known object geometry, our hardware-accelerated generalized Hough transform algorithm is capable of detecting an object's 3D pose, scale, and position in the image within less than one minute. A good pose estimation is even delivered in less than 10 seconds.

Parameter estimation based on Hough transform

Abstract: Although the Hough transform is mainly used in image processing for its robustness to impulsive noise, it can be applied to nonimage data. This technique with the new modification of Hough transform - continuous Kernel Hough transform - has been applied to parameter estimation for linear models. The experimental results confirm the efficiency of the proposed estimation algorithm also its comparison with the known technique of estimation - the least square method.

Edge orientation-based fuzzy Hough transform (EOFHT).

Abstract: The Hough Transform [6] -HTis a standard tool in image analysis that allows recognizing global patterns in an image space. To detect shapes in noisy data, preserving the idea of the conventional HT, but allowing detection of approximate shapes, the Fuzzy Hough Transform -FHTwas introduced [8]. Based on the FHT way of work, we propose an Edge Orientation-based Fuzzy Hough Transform -EOFHTwherein the information provided by the gradient vector is considered. The use of gradient vector's stability properties allows considering only some relevant orientations, so reducing the computational waste of time.

2 D Object Recognition Using the Hough Transform

Abstract: The objective of this paper is to identify 2D object features in object recognition in order to ensure quality assurance. In this paper we use Hough transform technique to identify the shape of the object by mapping the edge points of the image and also to identify the existing straight lines in the image. The Edge Detection Algorithm is applied to detect the edge points by the sharp or sudden change in intensity. Object recognition is usually performed using the property of shape as a discriminator. The shape of the edges, their size, orientation, and location can be extracted from the objects, which is used for object recognition.

Extended Hough methodology for 3D feature detection

Abstract: In an effort to make automatically detect image features for pattern recognition, we described a 3-dimesional (3-D) Hough transform. We describe two interlocking theoretical extensions to greatly enhance the Hough transform's ability to handle finite lineal features and allow directed search for various features while balancing memory and computational complexity. We computed the 2-D Hough transform of 1-D slices of an image which results in a 2-D to 3-D transform. Features such as line segments will cluster in a particular location so that both line orientation and spatial extent can be determined. This approach allows the Hough transform to be more widely applied in pattern recognition including 3-D features.

The hough transform as a tool for image analysis

Abstract: The Hough transform is a widespread technique in image analysis. Its main idea is to transform the image to a parameter space where clusters or particular configurations identify instances of a shape under detection. In this chapter we overview some meaningful Hough-based techniques for shape detection, either parametrized or generalized shapes. We also analyze some approaches based on the straight line Hough transform able to detect particular structural properties in images. Some of the ideas of these approaches will be used in the following chapter to solve one of the goals of the present work.