Sciweavers

9 search results - page 1 / 2
» A Trainable Low-level Feature Detector
Sort
View
ICDM
2003
IEEE
178views Data Mining» more  ICDM 2003»
13 years 10 months ago
Spatial Interest Pixels (SIPs): Useful Low-Level Features of Visual Media Data
Visual media data such as an image is the raw data representation for many important applications. Reducing the dimensionality of raw visual media data is desirable since high dime...
Qi Li, Jieping Ye, Chandra Kambhamettu
ICPR
2004
IEEE
14 years 6 months ago
A Trainable Low-level Feature Detector
We introduce a trainable system that simultaneously filters and classifies low-level features into types specified by the user. The system operates over full colour images, and ou...
John P. Collomosse, Martin Owen, Peter M. Hall
ICPR
2006
IEEE
14 years 6 months ago
A Trainable Similarity Measure for Image Classification
In object recognition problems a two-stage system is usually adopted composed of a fast and simple detector and a more complex classifier. This paper studies a design of the secon...
Jana Novovicová, Pavel Paclík, Rober...
ICDAR
2007
IEEE
13 years 11 months ago
A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images
We describe an unsupervised learning algorithm for extracting sparse and locally shift-invariant features. We also devise a principled procedure for learning hierarchies of invari...
Marc'Aurelio Ranzato, Yann LeCun
CVPR
1998
IEEE
14 years 6 months ago
Action Recognition Using Probabilistic Parsing
A new approach to the recognition of temporal behaviors and activities is presented. The fundamental idea, inspired by work in speech recognition, is to divide the inference probl...
Aaron F. Bobick, Yuri A. Ivanov