Deformable kernels for early vision - Computer Vision and Pattern Recognition, 1991. Proceedings CVPR '91., IEEE Computer Society Confer

نویسنده

  • Pietro Perona
چکیده

Earl~ vision algorithms often have a first stage of linearfiltenng that 'extracts' from the image information at multiple scales of resolution and multiple orientations. A common difficulty in the design and implementation of such schemes is that one feels compelled to discretize coarsely the space of scales and orientations in order to reduce compu~tion ~d storage costs. This discretization produces an1~otrop1es due to a loss of traslation-, rotationscalinginvanance that makes early vision algorithms less precise and more difficult to design. This need not be so: one can compute and store efficiently the response of families of linear filters defined on a continuum of orientations and scales. A tech~iqu~ is presen~ that allows ( 1) to compute the best approximation of a g1ven family using linear combinations of a small number of 'basis' functions; (2) to describe all finitedimensional families, i.e. the families of filters for which a finite dimensional representation is possible with no error. The techniq~e is g~neral. and can be applied to generating filters m arb1trary dimens10ns. Experimental results are presented that demonstrate the applicabilityof the technique to generating multi-orientation multi-scale 20 edge-detection kernels. The implementation issues are also discussed.

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

Deformable models with parameter functions: application to heart-wall modeling

This paper develops a new class of physics-based deformable models which can deform both globally and locally. Their global parameters are functions allowing the definition of new parameterized primitives and parameterized global deformations. These new global parameter functions improve the accuracy of shape description through the use of a few intuitive parameters such as functional bending a...

متن کامل

Non-Rigid Matching Using Demons - Computer Vision and Pattern Recognition, 1996. Proceedings CVPR '96, 1996 IEEE Computer Society Co

W e present the concept of non-rigid matching based o n demons, by reference to Maxwell’s demons. W e contrast this concept with the more conventional viewpoint of attraction. W e show that demons and attractive points are clearly distinct f o r large deformations, but also that they become similar for small displacements, encompassing techniques close to optical flow. We describe a general ite...

متن کامل

Guest Editors' Introduction to the Special Section on Award Winning Papers from the IEEE CS Conference on Computer Vision and Pattern Recognition (CVPR)

WE are pleased to present this special section on the award-winning papers from the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) 2008, held in Anchorage, Alaska, 23-28 June 2008. CVPR has been a flagship conference representing the state of the art in the field of computer vision and pattern recognition for more than two decades. The CVPR 2008 conference re...

متن کامل

Convexity Analysis of Active Contour Problems - Computer Vision and Pattern Recognition, 1996. Proceedings CVPR '96, 1996 IEEE Computer Society Co

A general active contour formulation is considered and a convexity analysis of its energy function ispresented. Conditions under which this formulation has a unique solution are derived; these conditions involve both the active contour energy potential and the regularization parameters. This analysis is then applied to four particular active contour formulations, revealing important characteris...

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 1998