Super resolution combination methods for CCTV forensic interpretation

Nik Nur Aisyah Nik Ghazali, Nazri A. Zamani, Siti Norul Huda Sheikh Abdullah, Jinjuli Jameson

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

4 Citations (Scopus)

Abstract

Generating a quality high resolution image has become an essential for variety purposes especially in forensic field. Compressed and at low resolution video frames of common security surveillance videos are found to be very low in clarity and degraded with many noises, distortions, blurs, bad illumination and video compression artifact. This could interfere during image interpretation and analysis process. This paper proposed a combination of super resolution methods for image processing. Using super resolution methods, high resolution image is obtained from a set of low resolution images, after it had undergone two main processes; image registration process based on Keren algorithm and image reconstruction process based on Projection onto Convex Set (POCS) on frequency domain. The validation process of output is done by calculating the Peak Signal to Noise Ratio (PSNR) value to show the comparison of image quality. The experimental results have shown that our proposed combinatorial method based super resolution and nearest neighbor methods outperformed other state-of-the-art methods.

Original languageEnglish
Title of host publicationInternational Conference on Intelligent Systems Design and Applications, ISDA
Pages853-858
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

Closed circuit television systems
Image resolution
Image registration
Optical resolving power
Image compression
Image reconstruction
Image quality
Signal to noise ratio
Image processing
Lighting

Keywords

  • Peak Signal to Noise Ratio
  • Projection onto Convex Set
  • Super resolution
  • Video Forensics

ASJC Scopus subject areas

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

Cite this

Ghazali, N. N. A. N., Zamani, N. A., Sheikh Abdullah, S. N. H., & Jameson, J. (2012). Super resolution combination methods for CCTV forensic interpretation. In International Conference on Intelligent Systems Design and Applications, ISDA (pp. 853-858). [6416649] https://doi.org/10.1109/ISDA.2012.6416649

Super resolution combination methods for CCTV forensic interpretation. / Ghazali, Nik Nur Aisyah Nik; Zamani, Nazri A.; Sheikh Abdullah, Siti Norul Huda; Jameson, Jinjuli.

International Conference on Intelligent Systems Design and Applications, ISDA. 2012. p. 853-858 6416649.

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

Ghazali, NNAN, Zamani, NA, Sheikh Abdullah, SNH & Jameson, J 2012, Super resolution combination methods for CCTV forensic interpretation. in International Conference on Intelligent Systems Design and Applications, ISDA., 6416649, pp. 853-858, 2012 12th International Conference on Intelligent Systems Design and Applications, ISDA 2012, Kochi, 27/11/12. https://doi.org/10.1109/ISDA.2012.6416649
Ghazali NNAN, Zamani NA, Sheikh Abdullah SNH, Jameson J. Super resolution combination methods for CCTV forensic interpretation. In International Conference on Intelligent Systems Design and Applications, ISDA. 2012. p. 853-858. 6416649 https://doi.org/10.1109/ISDA.2012.6416649
Ghazali, Nik Nur Aisyah Nik ; Zamani, Nazri A. ; Sheikh Abdullah, Siti Norul Huda ; Jameson, Jinjuli. / Super resolution combination methods for CCTV forensic interpretation. International Conference on Intelligent Systems Design and Applications, ISDA. 2012. pp. 853-858
@inproceedings{70387e5dd88c4529809a78600dc9b00d,
title = "Super resolution combination methods for CCTV forensic interpretation",
abstract = "Generating a quality high resolution image has become an essential for variety purposes especially in forensic field. Compressed and at low resolution video frames of common security surveillance videos are found to be very low in clarity and degraded with many noises, distortions, blurs, bad illumination and video compression artifact. This could interfere during image interpretation and analysis process. This paper proposed a combination of super resolution methods for image processing. Using super resolution methods, high resolution image is obtained from a set of low resolution images, after it had undergone two main processes; image registration process based on Keren algorithm and image reconstruction process based on Projection onto Convex Set (POCS) on frequency domain. The validation process of output is done by calculating the Peak Signal to Noise Ratio (PSNR) value to show the comparison of image quality. The experimental results have shown that our proposed combinatorial method based super resolution and nearest neighbor methods outperformed other state-of-the-art methods.",
keywords = "Peak Signal to Noise Ratio, Projection onto Convex Set, Super resolution, Video Forensics",
author = "Ghazali, {Nik Nur Aisyah Nik} and Zamani, {Nazri A.} and {Sheikh Abdullah}, {Siti Norul Huda} and Jinjuli Jameson",
year = "2012",
doi = "10.1109/ISDA.2012.6416649",
language = "English",
isbn = "9781467351188",
pages = "853--858",
booktitle = "International Conference on Intelligent Systems Design and Applications, ISDA",

}

TY - GEN

T1 - Super resolution combination methods for CCTV forensic interpretation

AU - Ghazali, Nik Nur Aisyah Nik

AU - Zamani, Nazri A.

AU - Sheikh Abdullah, Siti Norul Huda

AU - Jameson, Jinjuli

PY - 2012

Y1 - 2012

N2 - Generating a quality high resolution image has become an essential for variety purposes especially in forensic field. Compressed and at low resolution video frames of common security surveillance videos are found to be very low in clarity and degraded with many noises, distortions, blurs, bad illumination and video compression artifact. This could interfere during image interpretation and analysis process. This paper proposed a combination of super resolution methods for image processing. Using super resolution methods, high resolution image is obtained from a set of low resolution images, after it had undergone two main processes; image registration process based on Keren algorithm and image reconstruction process based on Projection onto Convex Set (POCS) on frequency domain. The validation process of output is done by calculating the Peak Signal to Noise Ratio (PSNR) value to show the comparison of image quality. The experimental results have shown that our proposed combinatorial method based super resolution and nearest neighbor methods outperformed other state-of-the-art methods.

AB - Generating a quality high resolution image has become an essential for variety purposes especially in forensic field. Compressed and at low resolution video frames of common security surveillance videos are found to be very low in clarity and degraded with many noises, distortions, blurs, bad illumination and video compression artifact. This could interfere during image interpretation and analysis process. This paper proposed a combination of super resolution methods for image processing. Using super resolution methods, high resolution image is obtained from a set of low resolution images, after it had undergone two main processes; image registration process based on Keren algorithm and image reconstruction process based on Projection onto Convex Set (POCS) on frequency domain. The validation process of output is done by calculating the Peak Signal to Noise Ratio (PSNR) value to show the comparison of image quality. The experimental results have shown that our proposed combinatorial method based super resolution and nearest neighbor methods outperformed other state-of-the-art methods.

KW - Peak Signal to Noise Ratio

KW - Projection onto Convex Set

KW - Super resolution

KW - Video Forensics

UR - http://www.scopus.com/inward/record.url?scp=84874349781&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874349781&partnerID=8YFLogxK

U2 - 10.1109/ISDA.2012.6416649

DO - 10.1109/ISDA.2012.6416649

M3 - Conference contribution

AN - SCOPUS:84874349781

SN - 9781467351188

SP - 853

EP - 858

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

ER -