Sciweavers

61 search results - page 3 / 13
» Subset Selection for Active Object Recognition
Sort
View
ICPR
2002
IEEE
14 years 5 months ago
Feature Selection Using Multi-Objective Genetic Algorithms for Handwritten Digit Recognition
This paper discusses the use of genetic algorithm for feature selection for handwriting recognition. Its novelty lies in the use of a multi-objective genetic algorithms where sens...
Luiz E. Soares de Oliveira, Robert Sabourin, Fl&aa...
ICRA
2008
IEEE
204views Robotics» more  ICRA 2008»
13 years 11 months ago
Active exploration and keypoint clustering for object recognition
— Object recognition is a challenging problem for artificial systems. This is especially true for objects that are placed in cluttered and uncontrolled environments. To challenge...
Gert Kootstra, Jelmer Ypma, Bart de Boer
ICCV
2011
IEEE
12 years 4 months ago
Actively Selecting Annotations Among Objects and Attributes
We present an active learning approach to choose image annotation requests among both object category labels and the objects’ attribute labels. The goal is to solicit those labe...
Adriana Kovashka, Sudheendra Vijayanarasimhan, Kri...
ICPR
2004
IEEE
14 years 5 months ago
Selecting Canonical Views for View-Based 3-D Object Recognition
Given a collection of sets of 2-D views of 3-D objects and a similarity measure between them, we present a method for summarizing the sets using a small subset called a bounded ca...
Ali Shokoufandeh, Jeff Abrahamson, M. Fatih Demirc...
DAGM
2006
Springer
13 years 8 months ago
Handling Camera Movement Constraints in Reinforcement Learning Based Active Object Recognition
In real world scenes, objects to be classified are usually not visible from every direction, since they are almost always positioned on some kind of opaque plane. When moving a cam...
Christian Derichs, Heinrich Niemann