Shape Matching and Object Recognition

نویسندگان

  • David A. Forsyth
  • Peter J. Bickel
چکیده

Shape Matching and Object Recognition by Alexander Christiansen Berg Doctor of Philosophy in Computer Science University of California, Berkeley Professor Jitendra Malik, Chair We address comparing related, but not identical shapes in images following a deformable template strategy. At the heart of this is the notion of an alignment between the shapes to be matched. The transformation necessary for alignment and the remaining differences after alignment are then used to make a comparison. A model determines what kind of deformations or alignments are acceptable, and what variation in appearance should remain after alignment. This ties strongly with the idea that the difference in shape is the residual difference, after some family of transformations has been applied for alignment. Finding an alignment of a model to a novel object involves search through the space of possible alignments. In many settings this search is quite difficult. This work shows that the search can be approximated by an easier discrete matching problem between key points on a model and a novel object. This is a departure from traditional approaches to deformable template matching that concentrate on analyzing differential models. This thesis presents theories and experiments on searching for, identifying, and using alignments found via discrete matchings. In particular we present a mathematical and ecological motivation for a medium scale descriptor of shape, geometric blur. Geometric blur is an average over transfor-

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Holistic Shape-Based Object Recognition Using Bottom-Up Image Structures

HOLISTIC SHAPE-BASED OBJECT RECOGNITION USING BOTTOM-UP IMAGE STRUCTURES Praveen Srinivasan Jianbo Shi, Associate Professor of Computer and Information Science Object recognition performance that rivals human ability is one of the primary goals of computer vision research. While recognition may take many forms, key tasks include detection, estimating object pose, and segmenting the object from ...

متن کامل

Shape recognition using fuzzy string-matching technique

Object recognition is a very important task in industrial applications. Attributed string matching is a well-known technique for pattern matching. The present paper proposes a fuzzy string-matching approach for two-dimensional object recognition. The fuzzy numbers are used to represent the edit costs. Therefore, the edit distances are also presented as fuzzy numbers. The attributed string-match...

متن کامل

Object Recognition Using Shape-from-Shading

ÐThis paper investigates whether surface topography information extracted from intensity images using a recently reported shape-from-shading (SFS) algorithm can be used for the purposes of 3D object recognition. We consider how curvature and shape-index information delivered by this algorithm can be used to recognize objects based on their surface topography. We explore two contrasting object r...

متن کامل

Perceptually motivated shape context which uses shape interiors

In this paper, we identify some of the limitations of current-day shape matching techniques. We provide examples of how contour-based shape matching techniques cannot provide a good match for certain visually similar shapes. To overcome this limitation, we propose a perceptually motivated variant of the well-known shape context descriptor. We identify that the interior properties of the shape p...

متن کامل

Eigen-css Shape Matching and Recognizing Fish in Underwater Video

This thesis presents work on shape matching and object recognition. First, we describe Eigen-CSS, a faster and more accurate approach to representing and matching the curvature scale space (CSS) features of shape silhouette contours. Phase-correlated marginal-sum features and PCA eigenspace decomposition via SVD differentiate our technique from earlier work. Next, we describe a deformable templ...

متن کامل

Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes

We present a 3D shape-based object recognition system for simultaneous recognition of multiple objects in scenes containing clutter and occlusion. Recognition is based on matching surfaces by matching points using the spin image representation. The spin image is a data level shape descriptor that is used to match surfaces represented as surface meshes. We present a compression scheme for spin i...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2005