• Laser & Optoelectronics Progress
  • Vol. 59, Issue 2, 0211001 (2022)
Yihang Peng, Wujian Ye*, and Yijun Liu
Author Affiliations
  • School of Information Engineering, Guangdong University of Technology, Guangzhou , Guangdong 510006, China
  • show less
    DOI: 10.3788/LOP202259.0211001 Cite this Article Set citation alerts
    Yihang Peng, Wujian Ye, Yijun Liu. Tampered Image Recognition Algorithm Based on Progressive Hybrid Feature[J]. Laser & Optoelectronics Progress, 2022, 59(2): 0211001 Copy Citation Text show less
    Flow chart of proposed algorithm
    Fig. 1. Flow chart of proposed algorithm
    Non-overlapping uniform segmentation
    Fig. 2. Non-overlapping uniform segmentation
    Similar sub-block extraction process of Soni algorithm
    Fig. 3. Similar sub-block extraction process of Soni algorithm
    Similar sub-block extraction process with non-threshold
    Fig. 4. Similar sub-block extraction process with non-threshold
    Adaptive sub-block combination. (a) Label for each sub-block; (b) sub-block on edge; (c) case of n=6; (d) case of n=8
    Fig. 5. Adaptive sub-block combination. (a) Label for each sub-block; (b) sub-block on edge; (c) case of n=6; (d) case of n=8
    Natural similar areas
    Fig. 6. Natural similar areas
    Progressive hybrid feature extraction
    Fig. 7. Progressive hybrid feature extraction
    Robust test in MICC-F220
    Fig. 8. Robust test in MICC-F220
    Robust test in MICC-F2000
    Fig. 9. Robust test in MICC-F2000
    Comparison of results on MICC-F220 dataset
    Fig. 10. Comparison of results on MICC-F220 dataset
    Comparison of results on MICC-F2000 dataset
    Fig. 11. Comparison of results on MICC-F2000 dataset
    ParameterG1G2G3G4G5G6G7G8G9G10
    θ /(°)0102030400001020
    Lx111111.21.31.41.21.4
    Ly111111.21,31.41.21.4
    Table 1. Type of geometric attack in MICC-F220 dataset
    ParameterG1G2G3G4G5G6G7G8G9G10G11G12G13G14
    θ /(°)0525709000000004030
    Lx111111.21.52.00.70.51.42.63.41.4
    Ly111111.21,52.00.70.51.71.31.20.7
    Table 2. Type of geometric attack in MICC-F2000 dataset
    Datasetabcd
    MICC-F220G1G2,G3,G4,G5G6,G7,G8G9,G10
    MICC-F2000G1G2,G3,G4,G5G6,G7,G8,G9,G10,G11,G12G13,G14
    Table 3. Attack type
    AlgorithmTPR /%FPR /%F1 /%
    Soni97.58.594.7
    Non-threshold method98.29.0994.6
    Non-threshold method+hybrid feature98.28.195.1
    Table 4. Experimental results of each stage
    AlgorithmTime /s
    Silva1739
    Pun19399
    Pun27123
    Ryu6565
    Soni2138
    Proposed algorithm47
    Table 5. Comparison of running time
    AlgorithmTPR /%FPR /%F1 /%
    CKN931187.2
    Proposed algorithm97.26.492.9
    Table 6. Performance comparison between proposed algorithm and CKN algorithm
    Yihang Peng, Wujian Ye, Yijun Liu. Tampered Image Recognition Algorithm Based on Progressive Hybrid Feature[J]. Laser & Optoelectronics Progress, 2022, 59(2): 0211001
    Download Citation