hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.17559/TV-20160804121351

Seam carving based image resizing detection using hybrid features

Zehra Karapinar Senturk ; Duzce University, Faculty of Engineering, Department of Computer Engineering, Konuralp Campus, 81620, Duzce, Turkey
Devrim Akgun   ORCID icon orcid.org/0000-0002-0770-599X ; Sakarya University, Faculty of Computer and Information Sciences, Computer Engineering Department, Esentepe Campus, 54187, Sakarya, Turkey

Puni tekst: engleski, pdf (1 MB) str. 1825-1832 preuzimanja: 246* citiraj
APA 6th Edition
Karapinar Senturk, Z. i Akgun, D. (2017). Seam carving based image resizing detection using hybrid features. Tehnički vjesnik, 24 (6), 1825-1832. https://doi.org/10.17559/TV-20160804121351
MLA 8th Edition
Karapinar Senturk, Zehra i Devrim Akgun. "Seam carving based image resizing detection using hybrid features." Tehnički vjesnik, vol. 24, br. 6, 2017, str. 1825-1832. https://doi.org/10.17559/TV-20160804121351. Citirano 25.08.2019.
Chicago 17th Edition
Karapinar Senturk, Zehra i Devrim Akgun. "Seam carving based image resizing detection using hybrid features." Tehnički vjesnik 24, br. 6 (2017): 1825-1832. https://doi.org/10.17559/TV-20160804121351
Harvard
Karapinar Senturk, Z., i Akgun, D. (2017). 'Seam carving based image resizing detection using hybrid features', Tehnički vjesnik, 24(6), str. 1825-1832. https://doi.org/10.17559/TV-20160804121351
Vancouver
Karapinar Senturk Z, Akgun D. Seam carving based image resizing detection using hybrid features. Tehnički vjesnik [Internet]. 2017 [pristupljeno 25.08.2019.];24(6):1825-1832. https://doi.org/10.17559/TV-20160804121351
IEEE
Z. Karapinar Senturk i D. Akgun, "Seam carving based image resizing detection using hybrid features", Tehnički vjesnik, vol.24, br. 6, str. 1825-1832, 2017. [Online]. https://doi.org/10.17559/TV-20160804121351
Puni tekst: hrvatski, pdf (1 MB) str. 1825-1832 preuzimanja: 87* citiraj
APA 6th Edition
Karapinar Senturk, Z. i Akgun, D. (2017). Otkrivanje promjene veličine slike temeljeno na tekućem skaliranju uporabom hibridnih značajki. Tehnički vjesnik, 24 (6), 1825-1832. https://doi.org/10.17559/TV-20160804121351
MLA 8th Edition
Karapinar Senturk, Zehra i Devrim Akgun. "Otkrivanje promjene veličine slike temeljeno na tekućem skaliranju uporabom hibridnih značajki." Tehnički vjesnik, vol. 24, br. 6, 2017, str. 1825-1832. https://doi.org/10.17559/TV-20160804121351. Citirano 25.08.2019.
Chicago 17th Edition
Karapinar Senturk, Zehra i Devrim Akgun. "Otkrivanje promjene veličine slike temeljeno na tekućem skaliranju uporabom hibridnih značajki." Tehnički vjesnik 24, br. 6 (2017): 1825-1832. https://doi.org/10.17559/TV-20160804121351
Harvard
Karapinar Senturk, Z., i Akgun, D. (2017). 'Otkrivanje promjene veličine slike temeljeno na tekućem skaliranju uporabom hibridnih značajki', Tehnički vjesnik, 24(6), str. 1825-1832. https://doi.org/10.17559/TV-20160804121351
Vancouver
Karapinar Senturk Z, Akgun D. Otkrivanje promjene veličine slike temeljeno na tekućem skaliranju uporabom hibridnih značajki. Tehnički vjesnik [Internet]. 2017 [pristupljeno 25.08.2019.];24(6):1825-1832. https://doi.org/10.17559/TV-20160804121351
IEEE
Z. Karapinar Senturk i D. Akgun, "Otkrivanje promjene veličine slike temeljeno na tekućem skaliranju uporabom hibridnih značajki", Tehnički vjesnik, vol.24, br. 6, str. 1825-1832, 2017. [Online]. https://doi.org/10.17559/TV-20160804121351

Sažetak
Detection of seam carving-based digital image resizing is a challenging task in image processing field since the method investigates the images on hand semantically. Resizing with seam carving is realized by inserting or removing relatively unimportant pixel paths to/from the images and so the changes in image content are mostly unnoticeable. Local Binary Patterns (LBP), a visual descriptor, unearths local changes in image texture. Therefore, using LBP transform of the images besides intensity values contributes to the detection ratio. In this paper, we proposed a hybrid detection mechanism for more accurate seam carving detection especially in low scaling ratios. We extracted LBP-based and non-LBP based features and trained a Support Vector Machine (SVM) with sixty features. We achieved approximately 9 % improvement in low detection ratios. The experimental results show that more satisfactory detection ratios can be obtained by the proposed hybrid approach.

Ključne riječi
forgery detection; Local Binary Patterns; seam carving; Support Vector Machines

Hrčak ID: 190180

URI
https://hrcak.srce.hr/190180

[hrvatski]

Posjeta: 473 *