Boosted Landmarks of Contextual Descriptors and Forest-ECOC: A novel framework to detect and classify objects in cluttered scenes

Authors:
Sergio Escalera;Oriol Pujol;Petia Radeva
Affiliations:
Centre de Visió per Computador, Campus UAB, 08193 Bellaterra, Barcelona, Spain;Dept. Matemática Aplicada i Anílisi, UB, Gran Via 585, 08007 Barcelona, Spain;Centre de Visió per Computador, Campus UAB, 08193 Bellaterra, Barcelona, Spain
Venue:
Pattern Recognition Letters
Year:
2007

Citing 10
Cited 12

Text filtering by boosting naive Bayes classifiers

SIGIR '00 Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval
Shape Matching and Object Recognition Using Shape Contexts

IEEE Transactions on Pattern Analysis and Machine Intelligence
Error-Correcting Output Codes for Local Learners

ECML '98 Proceedings of the 10th European Conference on Machine Learning
Transformation Invariance in Pattern Recognition-Tangent Distance and Tangent Propagation

Neural Networks: Tricks of the Trade, this book is an outgrowth of a 1996 NIPS workshop
Reducing multiclass to binary: a unifying approach for margin classifiers

The Journal of Machine Learning Research
Learning to Detect Objects in Images via a Sparse, Part-Based Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Fast Spatial Pattern Discovery Integrating Boosting with Constellations of Contextual Descriptors

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Solving multiclass learning problems via error-correcting output codes

Journal of Artificial Intelligence Research
Learning a restricted Bayesian network for object detection

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Sharing features: efficient boosting procedures for multiclass object detection

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition

Separability of ternary codes for sparse designs of error-correcting output codes

Pattern Recognition Letters
Recoding Error-Correcting Output Codes

MCS '09 Proceedings of the 8th International Workshop on Multiple Classifier Systems
Blurred Shape Model for binary and grey-level symbol recognition

Pattern Recognition Letters
Forests of nested dichotomies

Pattern Recognition Letters
Error-Correcting Ouput Codes Library

The Journal of Machine Learning Research
Thinned-ECOC ensemble based on sequential code shrinking

Expert Systems with Applications: An International Journal
Decoding design based on posterior probabilities in Ternary Error-Correcting Output Codes

Pattern Recognition
Minimal design of error-correcting output codes

Pattern Recognition Letters
Object recognition using a bio-inspired neuron model with bottom-up and top-down pathways

Neurocomputing
A genetic inspired optimization for ECOC

SSPR'12/SPR'12 Proceedings of the 2012 Joint IAPR international conference on Structural, Syntactic, and Statistical Pattern Recognition
Solving multi-class problems by data-driven topology-preserving output codes

Neurocomputing
On the design of an ECOC-Compliant Genetic Algorithm

Pattern Recognition

Quantified Score

Hi-index	0.10

Visualization

Abstract

In this paper, we present a novel methodology to detect and recognize objects in cluttered scenes by proposing boosted contextual descriptors of landmarks in a framework of multi-class object recognition. To detect a sample of the object class, Boosted Landmarks identify landmark candidates in the image and define a constellation of contextual descriptors able to capture the spatial relationship among them. To classify the object, we consider the problem of multi-class classification with a battery of classifiers trained to share their knowledge among classes. For this purpose, we extend the Error Correcting Output Codes technique proposing a methodology based on embedding a forest of optimal tree structures. We validated our approach using public data-sets from the UCI and Caltech databases. Furthermore, we show results of the technique applied to a real computer vision problem: detection and categorization of traffic signs.