Sciweavers

566 search results - page 18 / 114
» OCR with No Shape Training
Sort
View
ICDAR
2007
IEEE
14 years 1 months ago
Exploiting Fisher Kernels in Decoding Severely Noisy Document Images
Decoding noisy document images is commonly needed in applications such as enterprise content management. Available OCR solutions are still not satisfactory especially on noisy ima...
J. Chen, Y. Wang
CVPR
2009
IEEE
15 years 2 months ago
Learning Shape Prior Models for Object Matching
The aim of this work is to learn a shape prior model for an object class and to improve shape matching with the learned shape prior. Given images of example instances, we can le...
Cordelia Schmid, Frédéric Jurie, Tin...
ECCV
2008
Springer
14 years 9 months ago
Cat Head Detection - How to Effectively Exploit Shape and Texture Features
In this paper, we focus on the problem of detecting the head of cat-like animals, adopting cat as a test case. We show that the performance depends crucially on how to effectively ...
Weiwei Zhang, Jian Sun, Xiaoou Tang
ISBI
2008
IEEE
14 years 8 months ago
Landmark selection for shape model construction via equalization of variance
Model-based segmentation approaches, such as those employing Active Shape Models (ASMs), have proved to be useful for medical image segmentation and understanding. To build the mo...
Sylvia Rueda, Jayaram K. Udupa, Li Bai
IPMI
2005
Springer
14 years 8 months ago
Multi-figure Anatomical Objects for Shape Statistics
Abstract. Multi-figure m-reps allow us to represent and analyze a complex anatomical object by its parts, by relations among its parts, and by the object itself as a whole entity. ...
Qiong Han, Stephen M. Pizer, Derek Merck, Sarang C...