Sparse representation super-resolution method for enhancement analysis in video forensics

Nazri A. Zamani, A. D M Zaharudin, Siti Norul Huda Sheikh Abdullah, Md. Jan Nordin

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

1 Citation (Scopus)

Abstract

The enhancement analysis in video forensics is used to enhance the clarity of video frames of a video exhibit. The enhanced version of these video frames is important as to assist law enforcement agency for investigation or to be tended as evidence in court. The most significant problem observed in the analysis is the enhancement of objects under probe in video. In many cases, the probes appeared to be in low-resolution and degraded with noise, lens blur and compression artifacts. The enhancement of these low quality probes via conventional method of denoising and resizing has proven to further degrade the quality of the prober The objective of this paper is to propose an enhancement analysis algorithm based on super-resolution. Hence, we present an solution which is a single-frame solution for super-resolution. For that purpose, our proposed method incorporates sparse coding with Non-Negative Matrix Factorization in order to improve hallucination of probes in video. Sparse coding is employed in learning a localized part-based subspace which synthesizes higher resolution with respect to overcomplete patch dictionaries. We test our proposed method and compare with state-of-the-art methods namely resampling and super-resolution method, by enhancing probes in exhibit videos. We measure the image quality using peak-signal-to-noise-ratio. The result shows that our proposed method outperforms state-of the-art methods after enhancing probes in exhibit videos.

Original languageEnglish
Title of host publicationInternational Conference on Intelligent Systems Design and Applications, ISDA
Pages921-926
Number of pages6
DOIs
Publication statusPublished - 2012
Event2012 12th International Conference on Intelligent Systems Design and Applications, ISDA 2012 - Kochi
Duration: 27 Nov 201229 Nov 2012

Other

Other2012 12th International Conference on Intelligent Systems Design and Applications, ISDA 2012
CityKochi
Period27/11/1229/11/12

Fingerprint

Law enforcement
Glossaries
Factorization
Image quality
Lenses
Signal to noise ratio

Keywords

  • Non-Negative Matrix Factorization
  • object hallucination
  • sparse coding
  • Super-resolution
  • video forensics

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Signal Processing
  • Control and Systems Engineering

Cite this

Zamani, N. A., Zaharudin, A. D. M., Sheikh Abdullah, S. N. H., & Nordin, M. J. (2012). Sparse representation super-resolution method for enhancement analysis in video forensics. In International Conference on Intelligent Systems Design and Applications, ISDA (pp. 921-926). [6416661] https://doi.org/10.1109/ISDA.2012.6416661

Sparse representation super-resolution method for enhancement analysis in video forensics. / Zamani, Nazri A.; Zaharudin, A. D M; Sheikh Abdullah, Siti Norul Huda; Nordin, Md. Jan.

International Conference on Intelligent Systems Design and Applications, ISDA. 2012. p. 921-926 6416661.

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

Zamani, NA, Zaharudin, ADM, Sheikh Abdullah, SNH & Nordin, MJ 2012, Sparse representation super-resolution method for enhancement analysis in video forensics. in International Conference on Intelligent Systems Design and Applications, ISDA., 6416661, pp. 921-926, 2012 12th International Conference on Intelligent Systems Design and Applications, ISDA 2012, Kochi, 27/11/12. https://doi.org/10.1109/ISDA.2012.6416661
Zamani NA, Zaharudin ADM, Sheikh Abdullah SNH, Nordin MJ. Sparse representation super-resolution method for enhancement analysis in video forensics. In International Conference on Intelligent Systems Design and Applications, ISDA. 2012. p. 921-926. 6416661 https://doi.org/10.1109/ISDA.2012.6416661
Zamani, Nazri A. ; Zaharudin, A. D M ; Sheikh Abdullah, Siti Norul Huda ; Nordin, Md. Jan. / Sparse representation super-resolution method for enhancement analysis in video forensics. International Conference on Intelligent Systems Design and Applications, ISDA. 2012. pp. 921-926
@inproceedings{49934105f0ff4913bf6811433ceb4d46,
title = "Sparse representation super-resolution method for enhancement analysis in video forensics",
abstract = "The enhancement analysis in video forensics is used to enhance the clarity of video frames of a video exhibit. The enhanced version of these video frames is important as to assist law enforcement agency for investigation or to be tended as evidence in court. The most significant problem observed in the analysis is the enhancement of objects under probe in video. In many cases, the probes appeared to be in low-resolution and degraded with noise, lens blur and compression artifacts. The enhancement of these low quality probes via conventional method of denoising and resizing has proven to further degrade the quality of the prober The objective of this paper is to propose an enhancement analysis algorithm based on super-resolution. Hence, we present an solution which is a single-frame solution for super-resolution. For that purpose, our proposed method incorporates sparse coding with Non-Negative Matrix Factorization in order to improve hallucination of probes in video. Sparse coding is employed in learning a localized part-based subspace which synthesizes higher resolution with respect to overcomplete patch dictionaries. We test our proposed method and compare with state-of-the-art methods namely resampling and super-resolution method, by enhancing probes in exhibit videos. We measure the image quality using peak-signal-to-noise-ratio. The result shows that our proposed method outperforms state-of the-art methods after enhancing probes in exhibit videos.",
keywords = "Non-Negative Matrix Factorization, object hallucination, sparse coding, Super-resolution, video forensics",
author = "Zamani, {Nazri A.} and Zaharudin, {A. D M} and {Sheikh Abdullah}, {Siti Norul Huda} and Nordin, {Md. Jan}",
year = "2012",
doi = "10.1109/ISDA.2012.6416661",
language = "English",
isbn = "9781467351188",
pages = "921--926",
booktitle = "International Conference on Intelligent Systems Design and Applications, ISDA",

}

TY - GEN

T1 - Sparse representation super-resolution method for enhancement analysis in video forensics

AU - Zamani, Nazri A.

AU - Zaharudin, A. D M

AU - Sheikh Abdullah, Siti Norul Huda

AU - Nordin, Md. Jan

PY - 2012

Y1 - 2012

N2 - The enhancement analysis in video forensics is used to enhance the clarity of video frames of a video exhibit. The enhanced version of these video frames is important as to assist law enforcement agency for investigation or to be tended as evidence in court. The most significant problem observed in the analysis is the enhancement of objects under probe in video. In many cases, the probes appeared to be in low-resolution and degraded with noise, lens blur and compression artifacts. The enhancement of these low quality probes via conventional method of denoising and resizing has proven to further degrade the quality of the prober The objective of this paper is to propose an enhancement analysis algorithm based on super-resolution. Hence, we present an solution which is a single-frame solution for super-resolution. For that purpose, our proposed method incorporates sparse coding with Non-Negative Matrix Factorization in order to improve hallucination of probes in video. Sparse coding is employed in learning a localized part-based subspace which synthesizes higher resolution with respect to overcomplete patch dictionaries. We test our proposed method and compare with state-of-the-art methods namely resampling and super-resolution method, by enhancing probes in exhibit videos. We measure the image quality using peak-signal-to-noise-ratio. The result shows that our proposed method outperforms state-of the-art methods after enhancing probes in exhibit videos.

AB - The enhancement analysis in video forensics is used to enhance the clarity of video frames of a video exhibit. The enhanced version of these video frames is important as to assist law enforcement agency for investigation or to be tended as evidence in court. The most significant problem observed in the analysis is the enhancement of objects under probe in video. In many cases, the probes appeared to be in low-resolution and degraded with noise, lens blur and compression artifacts. The enhancement of these low quality probes via conventional method of denoising and resizing has proven to further degrade the quality of the prober The objective of this paper is to propose an enhancement analysis algorithm based on super-resolution. Hence, we present an solution which is a single-frame solution for super-resolution. For that purpose, our proposed method incorporates sparse coding with Non-Negative Matrix Factorization in order to improve hallucination of probes in video. Sparse coding is employed in learning a localized part-based subspace which synthesizes higher resolution with respect to overcomplete patch dictionaries. We test our proposed method and compare with state-of-the-art methods namely resampling and super-resolution method, by enhancing probes in exhibit videos. We measure the image quality using peak-signal-to-noise-ratio. The result shows that our proposed method outperforms state-of the-art methods after enhancing probes in exhibit videos.

KW - Non-Negative Matrix Factorization

KW - object hallucination

KW - sparse coding

KW - Super-resolution

KW - video forensics

UR - http://www.scopus.com/inward/record.url?scp=84874396090&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874396090&partnerID=8YFLogxK

U2 - 10.1109/ISDA.2012.6416661

DO - 10.1109/ISDA.2012.6416661

M3 - Conference contribution

SN - 9781467351188

SP - 921

EP - 926

BT - International Conference on Intelligent Systems Design and Applications, ISDA

ER -