2018 24th International Conference on Pattern Recognition (ICPR) 2018
DOI: 10.1109/icpr.2018.8545647
|View full text |Cite
|
Sign up to set email alerts
|

Global Contrast Enhancement Detection via Deep Multi-Path Network

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
9
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
4
2

Relationship

0
6

Authors

Journals

citations
Cited by 7 publications
(9 citation statements)
references
References 9 publications
0
9
0
Order By: Relevance
“…So, to limit the scope, in the following analysis we take a historical perspective, but focus especially on recent CNN-based methods. Moreover, we neglect global manipulations, such as histogram equalization or gamma correction [3], [4], which are not necessarily related to a malicious forgeries, as well as methods devoted only to copy-move forgery detection [5], [6], [7], [8].…”
Section: Related Workmentioning
confidence: 99%
See 2 more Smart Citations
“…So, to limit the scope, in the following analysis we take a historical perspective, but focus especially on recent CNN-based methods. Moreover, we neglect global manipulations, such as histogram equalization or gamma correction [3], [4], which are not necessarily related to a malicious forgeries, as well as methods devoted only to copy-move forgery detection [5], [6], [7], [8].…”
Section: Related Workmentioning
confidence: 99%
“…Several papers, to begin with [24], followed more recently by [31] and [4], train explicitly the net to distinguish between homogeneous and heterogeneous patches, the latter characterized by the presence of both pristine and forged areas. The rationale is to catch the patterns that characterize transitions regions, anomalous with respect to the background, so as to localize possible forgeries.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…These algorithms described are based on handcrafted, low-level features, which are not easy to deal with the above problems simultaneously. With the development of data-driven techniques, some researchers have started to study the deep feature representations for CE forensics via data-driven approach using recent and existing methods [24][25][26][27] focused on exploring in single domain. Barni et al [24] presented a CNN containing a total of nine convolutional layers in the pixel domain, which is similar to the typical CNNs used in the field of computer vision.…”
Section: Related Workmentioning
confidence: 99%
“…With the rapid development of deep-learning techniques, and especially convolutional neural networks (CNNs), some researchers have recently attempted to use them for digital image forensics. A number of preliminary works exploring CNNs in a single domain (such as the pixel domain [24], the histogram domain [25], and the gray-level co-occurrence matrix (GLCM) [26,27]) have been proposed for CE forensics. According to the report [26], deep-learning-based CE forensic schemes achieved better performance than traditional ones.…”
Section: Introductionmentioning
confidence: 99%