Proposing a fast circular HOG descriptor for detecting rotated objects

Junhyuk Hyun; Jeonghyun Baek; Jisu Kim; Peyman Hosseinzajeh Kassani; Euntai Kim

doi:10.1109/IJCNN.2015.7280501

Proposing a fast circular HOG descriptor for detecting rotated objects

Junhyuk Hyun, Jeonghyun Baek, Jisu Kim, Peyman Hosseinzajeh Kassani, Euntai Kim

Department of Electrical and Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

Object detection is one of the most interesting branches in computer vision. Accurate detection systems can be utilized to various areas. There are two steps in detection, feature extraction and classification. In this paper, new feature extraction method is proposed. Histogram Oriented Gradient (HOG) is famous, fast and accurate feature, but it is not rotation invariant. This paper proposes a new shape of HOG for fast detection of rotated objects. The proposed method is faster than conventional method in rotational object detection.

Original language	English
Title of host publication	2015 International Joint Conference on Neural Networks, IJCNN 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781479919604, 9781479919604, 9781479919604, 9781479919604
DOIs	https://doi.org/10.1109/IJCNN.2015.7280501
Publication status	Published - 2015 Sept 28
Event	International Joint Conference on Neural Networks, IJCNN 2015 - Killarney, Ireland Duration: 2015 Jul 12 → 2015 Jul 17

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	2015-September

Other

Other	International Joint Conference on Neural Networks, IJCNN 2015
Country/Territory	Ireland
City	Killarney
Period	15/7/12 → 15/7/17

Bibliographical note

Publisher Copyright:
© 2015 IEEE.

All Science Journal Classification (ASJC) codes

Software
Artificial Intelligence

Access to Document

10.1109/IJCNN.2015.7280501

Cite this

Hyun, J., Baek, J., Kim, J., Kassani, P. H., & Kim, E. (2015). Proposing a fast circular HOG descriptor for detecting rotated objects. In 2015 International Joint Conference on Neural Networks, IJCNN 2015 [7280501] (Proceedings of the International Joint Conference on Neural Networks; Vol. 2015-September). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2015.7280501

@inproceedings{84604a32a4bc42e9a65e60f4f4c4a36a,

title = "Proposing a fast circular HOG descriptor for detecting rotated objects",

abstract = "Object detection is one of the most interesting branches in computer vision. Accurate detection systems can be utilized to various areas. There are two steps in detection, feature extraction and classification. In this paper, new feature extraction method is proposed. Histogram Oriented Gradient (HOG) is famous, fast and accurate feature, but it is not rotation invariant. This paper proposes a new shape of HOG for fast detection of rotated objects. The proposed method is faster than conventional method in rotational object detection.",

author = "Junhyuk Hyun and Jeonghyun Baek and Jisu Kim and Kassani, {Peyman Hosseinzajeh} and Euntai Kim",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; International Joint Conference on Neural Networks, IJCNN 2015 ; Conference date: 12-07-2015 Through 17-07-2015",

year = "2015",

month = sep,

day = "28",

doi = "10.1109/IJCNN.2015.7280501",

language = "English",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2015 International Joint Conference on Neural Networks, IJCNN 2015",

address = "United States",

}

Hyun, J, Baek, J, Kim, J, Kassani, PH & Kim, E 2015, Proposing a fast circular HOG descriptor for detecting rotated objects. in 2015 International Joint Conference on Neural Networks, IJCNN 2015., 7280501, Proceedings of the International Joint Conference on Neural Networks, vol. 2015-September, Institute of Electrical and Electronics Engineers Inc., International Joint Conference on Neural Networks, IJCNN 2015, Killarney, Ireland, 15/7/12. https://doi.org/10.1109/IJCNN.2015.7280501

Proposing a fast circular HOG descriptor for detecting rotated objects. / Hyun, Junhyuk; Baek, Jeonghyun; Kim, Jisu et al.
2015 International Joint Conference on Neural Networks, IJCNN 2015. Institute of Electrical and Electronics Engineers Inc., 2015. 7280501 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2015-September).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Proposing a fast circular HOG descriptor for detecting rotated objects

AU - Hyun, Junhyuk

AU - Baek, Jeonghyun

AU - Kim, Jisu

AU - Kassani, Peyman Hosseinzajeh

AU - Kim, Euntai

PY - 2015/9/28

Y1 - 2015/9/28

N2 - Object detection is one of the most interesting branches in computer vision. Accurate detection systems can be utilized to various areas. There are two steps in detection, feature extraction and classification. In this paper, new feature extraction method is proposed. Histogram Oriented Gradient (HOG) is famous, fast and accurate feature, but it is not rotation invariant. This paper proposes a new shape of HOG for fast detection of rotated objects. The proposed method is faster than conventional method in rotational object detection.

AB - Object detection is one of the most interesting branches in computer vision. Accurate detection systems can be utilized to various areas. There are two steps in detection, feature extraction and classification. In this paper, new feature extraction method is proposed. Histogram Oriented Gradient (HOG) is famous, fast and accurate feature, but it is not rotation invariant. This paper proposes a new shape of HOG for fast detection of rotated objects. The proposed method is faster than conventional method in rotational object detection.

UR - http://www.scopus.com/inward/record.url?scp=84950975187&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84950975187&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2015.7280501

DO - 10.1109/IJCNN.2015.7280501

M3 - Conference contribution

AN - SCOPUS:84950975187

T3 - Proceedings of the International Joint Conference on Neural Networks

BT - 2015 International Joint Conference on Neural Networks, IJCNN 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - International Joint Conference on Neural Networks, IJCNN 2015

Y2 - 12 July 2015 through 17 July 2015

ER -

Proposing a fast circular HOG descriptor for detecting rotated objects

Abstract

Publication series

Other

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this