Fast color-based object recognition independent of position and orientation

Authors:
Martijn van de Giessen;Jürgen Schmidhuber
Affiliations:
IDSIA, Manno, Lugano, Switzerland;TU Munich, Garching, München, Germany
Venue:
ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
Year:
2005

Citing 6
Cited 0

Gradient-based learning algorithms for recurrent networks and their computational complexity

Backpropagation
VisualSEEk: a fully automated content-based image query system

MULTIMEDIA '96 Proceedings of the fourth ACM international conference on Multimedia
Long short-term memory

Neural Computation
A Simple Algorithm for Nearest Neighbor Search in High Dimensions

IEEE Transactions on Pattern Analysis and Machine Intelligence
HPAT indexing for fast object/scene recognition based on local appearance

CIVR'03 Proceedings of the 2nd international conference on Image and video retrieval
Gradient calculations for dynamic recurrent neural networks: a survey

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Small mobile robots typically have little on-board processing power for time-consuming vision algorithms. Here we show how they can quickly extract very dense yet highly useful information from color images. A single pass through all pixels of an image serves to segment it into color-dependent regions and to compactly represent it by a short list of the average hues, saturations and color intensities of its regions; all other information is discarded. Experiments with two image databases show that in 90 % of all cases the remaining information is sufficient for a simple weighted voting algorithm to recognize objects shown in query images, independently of position and orientation and partial occlusions.