Journal article Open Access

Content-aware Detection of JPEG Grid Inconsistencies for Intuitive Image Forensics

Iakovidou, Chryssanthi; Zampoglou, Markos; Papadopoulos, Symeon; Kompatsiaris, Yannis


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/e431a517-f488-4de7-b0dd-feabefcedeb0/CAGI.pdf"
      }, 
      "checksum": "md5:5c51526c7f4f0b1c260fd167d88a7e36", 
      "bucket": "e431a517-f488-4de7-b0dd-feabefcedeb0", 
      "key": "CAGI.pdf", 
      "type": "pdf", 
      "size": 5109916
    }
  ], 
  "owners": [
    27159
  ], 
  "doi": "10.5281/zenodo.1246437", 
  "stats": {
    "version_unique_downloads": 132.0, 
    "unique_views": 113.0, 
    "views": 115.0, 
    "downloads": 135.0, 
    "unique_downloads": 125.0, 
    "version_unique_views": 122.0, 
    "volume": 689838660.0, 
    "version_downloads": 147.0, 
    "version_views": 128.0, 
    "version_volume": 742213620.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.1246437", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.1246419", 
    "bucket": "https://zenodo.org/api/files/e431a517-f488-4de7-b0dd-feabefcedeb0", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.1246419.svg", 
    "html": "https://zenodo.org/record/1246437", 
    "latest_html": "https://zenodo.org/record/1246437", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.1246437.svg", 
    "latest": "https://zenodo.org/api/records/1246437"
  }, 
  "conceptdoi": "10.5281/zenodo.1246419", 
  "created": "2018-05-14T10:09:47.326437+00:00", 
  "updated": "2019-04-09T13:45:19.630312+00:00", 
  "conceptrecid": "1246419", 
  "revision": 7, 
  "id": 1246437, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.1246437", 
    "description": "<p>The paper proposes a novel method for detecting indicators of image forgery by locating grid alignment abnormalities in JPEG compressed image bitmaps. The method evaluates multiple grid positions with respect to a fitting function, and areas of lower contribution are identified as grid discontinuities and possibly tampered areas. An image segmentation step is introduced to dif-ferentiate between discontinuities produced by tampering and those that are attributed to image content, making the output maps easier to interpret by suppressing non-relevant activations. Our evaluations, on both synthetically produced datasets and real world tampering cases against seven methods from the literature, highlight the effectiveness of the proposed method in its ability to produce output maps that are clear and readable, and which can achieve successful detections on cases where other algorithms fail.</p>", 
    "language": "eng", 
    "title": "Content-aware Detection of JPEG Grid Inconsistencies for Intuitive Image Forensics", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "journal": {
      "title": "Journal of Visual Communication and Image Representation"
    }, 
    "relations": {
      "version": [
        {
          "count": 2, 
          "index": 1, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "1246419"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "1246437"
          }
        }
      ]
    }, 
    "grants": [
      {
        "code": "700024", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::700024"
        }, 
        "title": "Retrieval and Analysis of Heterogeneous Online Content for Terrorist Activity Recognition", 
        "acronym": "TENSOR", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [
            "EC"
          ], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }, 
      {
        "code": "687786", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::687786"
        }, 
        "title": "In Video Veritas \u2013 Verification of Social Media Video Content for the News Industry", 
        "acronym": "InVID", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [
            "EC"
          ], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }, 
      {
        "code": "610928", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::610928"
        }, 
        "title": "REVEALing hidden concepts in Social Media", 
        "acronym": "REVEAL", 
        "program": "FP7", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [
            "EC"
          ], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }
    ], 
    "keywords": [
      "image forensics", 
      "JPEG artifacts", 
      "forgery localization", 
      "image splicing"
    ], 
    "publication_date": "2018-05-14", 
    "creators": [
      {
        "orcid": "0000-0002-2382-4817", 
        "affiliation": "CERTH-ITI", 
        "name": "Iakovidou, Chryssanthi"
      }, 
      {
        "orcid": "0000-0001-7296-5942", 
        "affiliation": "CERTH-ITI", 
        "name": "Zampoglou, Markos"
      }, 
      {
        "orcid": "0000-0002-0708-7431", 
        "affiliation": "CERTH-ITI", 
        "name": "Papadopoulos, Symeon"
      }, 
      {
        "orcid": "0000-0001-6447-9020", 
        "affiliation": "CERTH-ITI", 
        "name": "Kompatsiaris, Yannis"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "subtype": "article", 
      "type": "publication", 
      "title": "Journal article"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.1246419", 
        "relation": "isVersionOf"
      }
    ]
  }
}
128
147
views
downloads
All versions This version
Views 128115
Downloads 147135
Data volume 742.2 MB689.8 MB
Unique views 122113
Unique downloads 132125

Share

Cite as