Applying support vector regression to predict structure in image completion

Tzung Shiuan Lai, Cho Wei Shin, Hui Chuan Chu, Yuh-Min Chen, Chin Bin Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Image completion is a technique widely used that automatically removes objects or repairs damaged portions of image. However, information regarding the original image is often lacking in structure reconstruction, and as a result, images with complex structures are difficult to restore. This study proposed a support vector regression-oriented image completion (SVR-IC) method, the goal of which is to predict the original structure of unknown areas and then repair or make appropriate adjustments to the structure and texture of the damaged area. From the experimental results, SVR-IC produced images of good quality that were superior to those of other methods. The results show that integrated structure prediction to image completion can effectively enhance the quality of the restored image.

Original languageEnglish
Title of host publicationProceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011
Pages659-665
Number of pages7
Publication statusPublished - 2011 Dec 1
Event2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011 - Las Vegas, NV, United States
Duration: 2011 Jul 182011 Jul 21

Publication series

NameProceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011
Volume2

Other

Other2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011
CountryUnited States
CityLas Vegas, NV
Period11-07-1811-07-21

Fingerprint

Repair
Textures

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Cite this

Lai, T. S., Shin, C. W., Chu, H. C., Chen, Y-M., & Wang, C. B. (2011). Applying support vector regression to predict structure in image completion. In Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011 (pp. 659-665). (Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011; Vol. 2).
Lai, Tzung Shiuan ; Shin, Cho Wei ; Chu, Hui Chuan ; Chen, Yuh-Min ; Wang, Chin Bin. / Applying support vector regression to predict structure in image completion. Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011. 2011. pp. 659-665 (Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011).
@inproceedings{cc77a55277a54dcb81ac1de79f48eae5,
title = "Applying support vector regression to predict structure in image completion",
abstract = "Image completion is a technique widely used that automatically removes objects or repairs damaged portions of image. However, information regarding the original image is often lacking in structure reconstruction, and as a result, images with complex structures are difficult to restore. This study proposed a support vector regression-oriented image completion (SVR-IC) method, the goal of which is to predict the original structure of unknown areas and then repair or make appropriate adjustments to the structure and texture of the damaged area. From the experimental results, SVR-IC produced images of good quality that were superior to those of other methods. The results show that integrated structure prediction to image completion can effectively enhance the quality of the restored image.",
author = "Lai, {Tzung Shiuan} and Shin, {Cho Wei} and Chu, {Hui Chuan} and Yuh-Min Chen and Wang, {Chin Bin}",
year = "2011",
month = "12",
day = "1",
language = "English",
isbn = "9781601321916",
series = "Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011",
pages = "659--665",
booktitle = "Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011",

}

Lai, TS, Shin, CW, Chu, HC, Chen, Y-M & Wang, CB 2011, Applying support vector regression to predict structure in image completion. in Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011. Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011, vol. 2, pp. 659-665, 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011, Las Vegas, NV, United States, 11-07-18.

Applying support vector regression to predict structure in image completion. / Lai, Tzung Shiuan; Shin, Cho Wei; Chu, Hui Chuan; Chen, Yuh-Min; Wang, Chin Bin.

Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011. 2011. p. 659-665 (Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011; Vol. 2).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Applying support vector regression to predict structure in image completion

AU - Lai, Tzung Shiuan

AU - Shin, Cho Wei

AU - Chu, Hui Chuan

AU - Chen, Yuh-Min

AU - Wang, Chin Bin

PY - 2011/12/1

Y1 - 2011/12/1

N2 - Image completion is a technique widely used that automatically removes objects or repairs damaged portions of image. However, information regarding the original image is often lacking in structure reconstruction, and as a result, images with complex structures are difficult to restore. This study proposed a support vector regression-oriented image completion (SVR-IC) method, the goal of which is to predict the original structure of unknown areas and then repair or make appropriate adjustments to the structure and texture of the damaged area. From the experimental results, SVR-IC produced images of good quality that were superior to those of other methods. The results show that integrated structure prediction to image completion can effectively enhance the quality of the restored image.

AB - Image completion is a technique widely used that automatically removes objects or repairs damaged portions of image. However, information regarding the original image is often lacking in structure reconstruction, and as a result, images with complex structures are difficult to restore. This study proposed a support vector regression-oriented image completion (SVR-IC) method, the goal of which is to predict the original structure of unknown areas and then repair or make appropriate adjustments to the structure and texture of the damaged area. From the experimental results, SVR-IC produced images of good quality that were superior to those of other methods. The results show that integrated structure prediction to image completion can effectively enhance the quality of the restored image.

UR - http://www.scopus.com/inward/record.url?scp=84864915868&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864915868&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781601321916

T3 - Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011

SP - 659

EP - 665

BT - Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011

ER -

Lai TS, Shin CW, Chu HC, Chen Y-M, Wang CB. Applying support vector regression to predict structure in image completion. In Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011. 2011. p. 659-665. (Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011).