Improved object recognition with decision trees using subspace clustering

Billy Peralta, Luis Alberto Caro

Resultado de la investigación: Article

2 Citas (Scopus)

Resumen

Generic object recognition algorithms usually require complex classificationmodels because of intrinsic difficulties arising from problems such as changes in pose, lighting conditions, or partial occlusions. Decision trees present an inexpensive alternative for classification tasks and offer the advantage of being simple to understand. On the other hand, a common scheme for object recognition is given by the appearances of visual words, also known as the bag-of-words method. Although multiple co-occurrences of visual words are more informative regarding visual classes, a comprehensive evaluation of such combinations is unfeasible because it would result in a combinatorial explosion. In this paper, we propose to obtain the multiple co-occurrences of visual words using a variant of the CLIQUE subspace-clustering algorithm for improving the object recognition performance of simple decision trees. Experiments on standard object datasets show that our method improves the accuracy of the classification of generic objects in comparison to traditional decision tree techniques that are similar, in terms of accuracy, to ensemble techniques. In future we plan to evaluate other variants of decision trees, and apply other subspace-clustering algorithms.

Idioma originalEnglish
Páginas (desde-hasta)41-48
Número de páginas8
PublicaciónJournal of Advanced Computational Intelligence and Intelligent Informatics
Volumen20
N.º1
EstadoPublished - 1 ene 2016

Huella dactilar

Object recognition
Decision trees
Clustering algorithms
Explosions
Lighting
Experiments

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Citar esto

@article{720e3de8baa4491d91a9feb1bce354b6,
title = "Improved object recognition with decision trees using subspace clustering",
abstract = "Generic object recognition algorithms usually require complex classificationmodels because of intrinsic difficulties arising from problems such as changes in pose, lighting conditions, or partial occlusions. Decision trees present an inexpensive alternative for classification tasks and offer the advantage of being simple to understand. On the other hand, a common scheme for object recognition is given by the appearances of visual words, also known as the bag-of-words method. Although multiple co-occurrences of visual words are more informative regarding visual classes, a comprehensive evaluation of such combinations is unfeasible because it would result in a combinatorial explosion. In this paper, we propose to obtain the multiple co-occurrences of visual words using a variant of the CLIQUE subspace-clustering algorithm for improving the object recognition performance of simple decision trees. Experiments on standard object datasets show that our method improves the accuracy of the classification of generic objects in comparison to traditional decision tree techniques that are similar, in terms of accuracy, to ensemble techniques. In future we plan to evaluate other variants of decision trees, and apply other subspace-clustering algorithms.",
keywords = "Decision trees, Object recognition, Random forest, Subspace clustering",
author = "Billy Peralta and Caro, {Luis Alberto}",
year = "2016",
month = "1",
day = "1",
language = "English",
volume = "20",
pages = "41--48",
journal = "Journal of Advanced Computational Intelligence and Intelligent Informatics",
issn = "1343-0130",
publisher = "Fuji Technology Press",
number = "1",

}

Improved object recognition with decision trees using subspace clustering. / Peralta, Billy; Caro, Luis Alberto.

En: Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol. 20, N.º 1, 01.01.2016, p. 41-48.

Resultado de la investigación: Article

TY - JOUR

T1 - Improved object recognition with decision trees using subspace clustering

AU - Peralta, Billy

AU - Caro, Luis Alberto

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Generic object recognition algorithms usually require complex classificationmodels because of intrinsic difficulties arising from problems such as changes in pose, lighting conditions, or partial occlusions. Decision trees present an inexpensive alternative for classification tasks and offer the advantage of being simple to understand. On the other hand, a common scheme for object recognition is given by the appearances of visual words, also known as the bag-of-words method. Although multiple co-occurrences of visual words are more informative regarding visual classes, a comprehensive evaluation of such combinations is unfeasible because it would result in a combinatorial explosion. In this paper, we propose to obtain the multiple co-occurrences of visual words using a variant of the CLIQUE subspace-clustering algorithm for improving the object recognition performance of simple decision trees. Experiments on standard object datasets show that our method improves the accuracy of the classification of generic objects in comparison to traditional decision tree techniques that are similar, in terms of accuracy, to ensemble techniques. In future we plan to evaluate other variants of decision trees, and apply other subspace-clustering algorithms.

AB - Generic object recognition algorithms usually require complex classificationmodels because of intrinsic difficulties arising from problems such as changes in pose, lighting conditions, or partial occlusions. Decision trees present an inexpensive alternative for classification tasks and offer the advantage of being simple to understand. On the other hand, a common scheme for object recognition is given by the appearances of visual words, also known as the bag-of-words method. Although multiple co-occurrences of visual words are more informative regarding visual classes, a comprehensive evaluation of such combinations is unfeasible because it would result in a combinatorial explosion. In this paper, we propose to obtain the multiple co-occurrences of visual words using a variant of the CLIQUE subspace-clustering algorithm for improving the object recognition performance of simple decision trees. Experiments on standard object datasets show that our method improves the accuracy of the classification of generic objects in comparison to traditional decision tree techniques that are similar, in terms of accuracy, to ensemble techniques. In future we plan to evaluate other variants of decision trees, and apply other subspace-clustering algorithms.

KW - Decision trees

KW - Object recognition

KW - Random forest

KW - Subspace clustering

UR - http://www.scopus.com/inward/record.url?scp=84958245823&partnerID=8YFLogxK

M3 - Article

VL - 20

SP - 41

EP - 48

JO - Journal of Advanced Computational Intelligence and Intelligent Informatics

JF - Journal of Advanced Computational Intelligence and Intelligent Informatics

SN - 1343-0130

IS - 1

ER -