Ontological random forests for image classification

Ning Xu, Jiangping Wang, Guojun Qi, Thomas S Huang, Weiyao Lin

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Previous image classification approaches mostly neglect semantics, which has two major limitations. First, categories are simply treated independently while in fact they have semantic overlaps. For example, “sedan” is a specific kind of “car”. Therefore, it’s unreasonable to train a classifier to distinguish between “sedan” and “car”. Second, image feature representations used for classifying different categories are the same. However, the human perception system is believed to use different features for different objects. In this paper, we leverage semantic ontologies to solve the aforementioned problems. The authors propose an ontological random forest algorithm where the splitting of decision trees are determined by semantic relations among categories. Then hierarchical features are automatically learned by multiple-instance learning to capture visual dissimilarities at different concept levels. Their approach is tested on two image classification datasets. Experimental results demonstrate that their approach not only outperforms state-of-the-art results but also identifies semantic visual features.

Original languageEnglish (US)
Title of host publicationComputer Vision
Subtitle of host publicationConcepts, Methodologies, Tools, and Applications
PublisherIGI Global
Pages784-799
Number of pages16
ISBN (Electronic)9781522552055
ISBN (Print)9781522552048
DOIs
StatePublished - Jan 1 2018

Fingerprint

Image classification
Semantics
Railroad cars
Decision trees
Ontology
Classifiers

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Xu, N., Wang, J., Qi, G., Huang, T. S., & Lin, W. (2018). Ontological random forests for image classification. In Computer Vision: Concepts, Methodologies, Tools, and Applications (pp. 784-799). IGI Global. https://doi.org/10.4018/978-1-5225-5204-8.ch031

Ontological random forests for image classification. / Xu, Ning; Wang, Jiangping; Qi, Guojun; Huang, Thomas S; Lin, Weiyao.

Computer Vision: Concepts, Methodologies, Tools, and Applications. IGI Global, 2018. p. 784-799.

Research output: Chapter in Book/Report/Conference proceedingChapter

Xu, N, Wang, J, Qi, G, Huang, TS & Lin, W 2018, Ontological random forests for image classification. in Computer Vision: Concepts, Methodologies, Tools, and Applications. IGI Global, pp. 784-799. https://doi.org/10.4018/978-1-5225-5204-8.ch031
Xu N, Wang J, Qi G, Huang TS, Lin W. Ontological random forests for image classification. In Computer Vision: Concepts, Methodologies, Tools, and Applications. IGI Global. 2018. p. 784-799 https://doi.org/10.4018/978-1-5225-5204-8.ch031
Xu, Ning ; Wang, Jiangping ; Qi, Guojun ; Huang, Thomas S ; Lin, Weiyao. / Ontological random forests for image classification. Computer Vision: Concepts, Methodologies, Tools, and Applications. IGI Global, 2018. pp. 784-799
@inbook{03c59234aad74d7ebfb3043f73417d09,
title = "Ontological random forests for image classification",
abstract = "Previous image classification approaches mostly neglect semantics, which has two major limitations. First, categories are simply treated independently while in fact they have semantic overlaps. For example, “sedan” is a specific kind of “car”. Therefore, it’s unreasonable to train a classifier to distinguish between “sedan” and “car”. Second, image feature representations used for classifying different categories are the same. However, the human perception system is believed to use different features for different objects. In this paper, we leverage semantic ontologies to solve the aforementioned problems. The authors propose an ontological random forest algorithm where the splitting of decision trees are determined by semantic relations among categories. Then hierarchical features are automatically learned by multiple-instance learning to capture visual dissimilarities at different concept levels. Their approach is tested on two image classification datasets. Experimental results demonstrate that their approach not only outperforms state-of-the-art results but also identifies semantic visual features.",
author = "Ning Xu and Jiangping Wang and Guojun Qi and Huang, {Thomas S} and Weiyao Lin",
year = "2018",
month = "1",
day = "1",
doi = "10.4018/978-1-5225-5204-8.ch031",
language = "English (US)",
isbn = "9781522552048",
pages = "784--799",
booktitle = "Computer Vision",
publisher = "IGI Global",

}

TY - CHAP

T1 - Ontological random forests for image classification

AU - Xu, Ning

AU - Wang, Jiangping

AU - Qi, Guojun

AU - Huang, Thomas S

AU - Lin, Weiyao

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Previous image classification approaches mostly neglect semantics, which has two major limitations. First, categories are simply treated independently while in fact they have semantic overlaps. For example, “sedan” is a specific kind of “car”. Therefore, it’s unreasonable to train a classifier to distinguish between “sedan” and “car”. Second, image feature representations used for classifying different categories are the same. However, the human perception system is believed to use different features for different objects. In this paper, we leverage semantic ontologies to solve the aforementioned problems. The authors propose an ontological random forest algorithm where the splitting of decision trees are determined by semantic relations among categories. Then hierarchical features are automatically learned by multiple-instance learning to capture visual dissimilarities at different concept levels. Their approach is tested on two image classification datasets. Experimental results demonstrate that their approach not only outperforms state-of-the-art results but also identifies semantic visual features.

AB - Previous image classification approaches mostly neglect semantics, which has two major limitations. First, categories are simply treated independently while in fact they have semantic overlaps. For example, “sedan” is a specific kind of “car”. Therefore, it’s unreasonable to train a classifier to distinguish between “sedan” and “car”. Second, image feature representations used for classifying different categories are the same. However, the human perception system is believed to use different features for different objects. In this paper, we leverage semantic ontologies to solve the aforementioned problems. The authors propose an ontological random forest algorithm where the splitting of decision trees are determined by semantic relations among categories. Then hierarchical features are automatically learned by multiple-instance learning to capture visual dissimilarities at different concept levels. Their approach is tested on two image classification datasets. Experimental results demonstrate that their approach not only outperforms state-of-the-art results but also identifies semantic visual features.

UR - http://www.scopus.com/inward/record.url?scp=85045026777&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045026777&partnerID=8YFLogxK

U2 - 10.4018/978-1-5225-5204-8.ch031

DO - 10.4018/978-1-5225-5204-8.ch031

M3 - Chapter

AN - SCOPUS:85045026777

SN - 9781522552048

SP - 784

EP - 799

BT - Computer Vision

PB - IGI Global

ER -