Seamless image stitching using structure deformation with HoG matching

Seohyung Lee; Youngtae Park; Daeho Lee

doi:10.1109/ICTC.2015.7354704

Seamless image stitching using structure deformation with HoG matching

Seohyung Lee, Youngtae Park, Daeho Lee

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

5 Citations (Scopus)

Abstract

In this paper, we propose an efficient image stitching using structure deformation. We use image stitching based on common stitching algorithms such as speeded up robust features (SURF) feature detection, approximated nearest neighbor (ANN) matching and random sample consensus (RANSAC) parameter estimation. And we use homography similarity to identify if input images have enough correlation. To reduce structure misalignment, we use double-seam selection. Through local maximum in gradient domain, we find 1-D feature points along with each seam. To find matching points, we used histogram of oriented gradients (HoG) which find matching points robustly. In addition, we use multi-band blending algorithm to remove intensity difference efficiently. In the experimental results, we compare with common stitching algorithms and existing structure deformation algorithms.

Original language	English
Title of host publication	International Conference on ICT Convergence 2015
Subtitle of host publication	Innovations Toward the IoT, 5G, and Smart Media Era, ICTC 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	933-935
Number of pages	3
ISBN (Electronic)	9781467371155
DOIs	https://doi.org/10.1109/ICTC.2015.7354704
Publication status	Published - 11 Dec 2015
Event	6th International Conference on Information and Communication Technology Convergence, ICTC 2015 - Jeju Island, Korea, Republic of Duration: 28 Oct 2015 → 30 Oct 2015

Publication series

Name	International Conference on ICT Convergence 2015: Innovations Toward the IoT, 5G, and Smart Media Era, ICTC 2015

Conference

Conference	6th International Conference on Information and Communication Technology Convergence, ICTC 2015
Country/Territory	Korea, Republic of
City	Jeju Island
Period	28/10/15 → 30/10/15

Bibliographical note

Publisher Copyright:
© 2015 IEEE.

Keywords

HoG
Image stitching
Structure deformation

Access to Document

10.1109/ICTC.2015.7354704

Cite this

Lee, S., Park, Y., & Lee, D. (2015). Seamless image stitching using structure deformation with HoG matching. In International Conference on ICT Convergence 2015: Innovations Toward the IoT, 5G, and Smart Media Era, ICTC 2015 (pp. 933-935). Article 7354704 (International Conference on ICT Convergence 2015: Innovations Toward the IoT, 5G, and Smart Media Era, ICTC 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICTC.2015.7354704

Lee, Seohyung ; Park, Youngtae ; Lee, Daeho. / Seamless image stitching using structure deformation with HoG matching. International Conference on ICT Convergence 2015: Innovations Toward the IoT, 5G, and Smart Media Era, ICTC 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 933-935 (International Conference on ICT Convergence 2015: Innovations Toward the IoT, 5G, and Smart Media Era, ICTC 2015).

@inproceedings{49475963ba01483aa69cde0536850d93,

title = "Seamless image stitching using structure deformation with HoG matching",

abstract = "In this paper, we propose an efficient image stitching using structure deformation. We use image stitching based on common stitching algorithms such as speeded up robust features (SURF) feature detection, approximated nearest neighbor (ANN) matching and random sample consensus (RANSAC) parameter estimation. And we use homography similarity to identify if input images have enough correlation. To reduce structure misalignment, we use double-seam selection. Through local maximum in gradient domain, we find 1-D feature points along with each seam. To find matching points, we used histogram of oriented gradients (HoG) which find matching points robustly. In addition, we use multi-band blending algorithm to remove intensity difference efficiently. In the experimental results, we compare with common stitching algorithms and existing structure deformation algorithms.",

keywords = "HoG, Image stitching, Structure deformation",

author = "Seohyung Lee and Youngtae Park and Daeho Lee",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 6th International Conference on Information and Communication Technology Convergence, ICTC 2015 ; Conference date: 28-10-2015 Through 30-10-2015",

year = "2015",

month = dec,

day = "11",

doi = "10.1109/ICTC.2015.7354704",

language = "English",

series = "International Conference on ICT Convergence 2015: Innovations Toward the IoT, 5G, and Smart Media Era, ICTC 2015",

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

pages = "933--935",

booktitle = "International Conference on ICT Convergence 2015",

address = "United States",

}

Lee, S, Park, Y & Lee, D 2015, Seamless image stitching using structure deformation with HoG matching. in International Conference on ICT Convergence 2015: Innovations Toward the IoT, 5G, and Smart Media Era, ICTC 2015., 7354704, International Conference on ICT Convergence 2015: Innovations Toward the IoT, 5G, and Smart Media Era, ICTC 2015, Institute of Electrical and Electronics Engineers Inc., pp. 933-935, 6th International Conference on Information and Communication Technology Convergence, ICTC 2015, Jeju Island, Korea, Republic of, 28/10/15. https://doi.org/10.1109/ICTC.2015.7354704

Seamless image stitching using structure deformation with HoG matching. / Lee, Seohyung; Park, Youngtae; Lee, Daeho.
International Conference on ICT Convergence 2015: Innovations Toward the IoT, 5G, and Smart Media Era, ICTC 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 933-935 7354704 (International Conference on ICT Convergence 2015: Innovations Toward the IoT, 5G, and Smart Media Era, ICTC 2015).

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

TY - GEN

T1 - Seamless image stitching using structure deformation with HoG matching

AU - Lee, Seohyung

AU - Park, Youngtae

AU - Lee, Daeho

PY - 2015/12/11

Y1 - 2015/12/11

N2 - In this paper, we propose an efficient image stitching using structure deformation. We use image stitching based on common stitching algorithms such as speeded up robust features (SURF) feature detection, approximated nearest neighbor (ANN) matching and random sample consensus (RANSAC) parameter estimation. And we use homography similarity to identify if input images have enough correlation. To reduce structure misalignment, we use double-seam selection. Through local maximum in gradient domain, we find 1-D feature points along with each seam. To find matching points, we used histogram of oriented gradients (HoG) which find matching points robustly. In addition, we use multi-band blending algorithm to remove intensity difference efficiently. In the experimental results, we compare with common stitching algorithms and existing structure deformation algorithms.

AB - In this paper, we propose an efficient image stitching using structure deformation. We use image stitching based on common stitching algorithms such as speeded up robust features (SURF) feature detection, approximated nearest neighbor (ANN) matching and random sample consensus (RANSAC) parameter estimation. And we use homography similarity to identify if input images have enough correlation. To reduce structure misalignment, we use double-seam selection. Through local maximum in gradient domain, we find 1-D feature points along with each seam. To find matching points, we used histogram of oriented gradients (HoG) which find matching points robustly. In addition, we use multi-band blending algorithm to remove intensity difference efficiently. In the experimental results, we compare with common stitching algorithms and existing structure deformation algorithms.

KW - HoG

KW - Image stitching

KW - Structure deformation

UR - http://www.scopus.com/inward/record.url?scp=84964839802&partnerID=8YFLogxK

U2 - 10.1109/ICTC.2015.7354704

DO - 10.1109/ICTC.2015.7354704

M3 - Conference contribution

AN - SCOPUS:84964839802

T3 - International Conference on ICT Convergence 2015: Innovations Toward the IoT, 5G, and Smart Media Era, ICTC 2015

SP - 933

EP - 935

BT - International Conference on ICT Convergence 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 6th International Conference on Information and Communication Technology Convergence, ICTC 2015

Y2 - 28 October 2015 through 30 October 2015

ER -

Lee S, Park Y, Lee D. Seamless image stitching using structure deformation with HoG matching. In International Conference on ICT Convergence 2015: Innovations Toward the IoT, 5G, and Smart Media Era, ICTC 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 933-935. 7354704. (International Conference on ICT Convergence 2015: Innovations Toward the IoT, 5G, and Smart Media Era, ICTC 2015). doi: 10.1109/ICTC.2015.7354704

Seamless image stitching using structure deformation with HoG matching

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this