A novel image tamper detection approach by blending forensic tools and optimized CNN: Sealion customized firefly algorithm

Ahmad, Mohassin; Khursheed, Farida

doi:10.1007/s11042-021-11529-0

Cited by 9 publications

(8 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The traditional SURF method 50 is a robust as well as the fastest algorithm for representation of the local, similarity invariant. The box filter‐based operations are used in the SURF approach and thereby the computations seem to be faster.…”

Section: Feature Extraction Phase Frameworkmentioning

confidence: 99%

“…Since the scale values characterize the size of the involved box filters, a fixed radius

6\sigma

seems to be less accurate for low‐intensity images, as there is a huge chance of missing out on important information. Therefore, a Scale‐based Adaptive SURF 50 model is utilized for selecting the most relevant features. The flow diagram in Figure 2 manifests the process of the Scale‐based Adaptive SURF model.…”

Section: Feature Extraction Phase Frameworkmentioning

confidence: 99%

“…The HoG with Harmonic mean features on the basis of PCA is used for analyzing the noise inconsistency in digital images. The HOG (feature descriptor) identifies the homogeneous indistinguishable area in the image of input 50 . The input picture is partitioned into smaller connected sections for the HoG feature extraction method, which generates the “histogram of gradient directions or edge orientations” of each pixel in each cell.…”

Section: Feature Extraction Phase Frameworkmentioning

confidence: 99%

“…The SCFF model was developed with the conceptual amalgamation of the FF and SLnO model 50 . This technique was good in performing complex optimization problems with a higher convergence rate.…”

Section: Tampering Detection Via Optimized Cnn With Improved Scff Modelmentioning

confidence: 99%

“…Since the scale values characterize the size of the involved box filters, a fixed radius 6𝜎 seems to be less accurate for low-intensity images, as there is a huge chance of missing out on important information. Therefore, a Scale-based Adaptive SURF 50…”

Section: Scale-based Adaptive Surfmentioning

confidence: 99%

See 4 more Smart Citations

Detection and localization of image tampering in digital images with fused features

Ahmad

Khursheed

2022

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Summary In digital forensics, image tamper detection and localization have attracted increased attention in recent days, where the standard methods have limited description ability and high computational costs. As a result, this research introduces a novel picture tamper detection and localization model. Feature extraction, tamper detection, as well as tamper localization are the three major phases of the proposed model. From the input digital images, a group of features like “Scale‐based Adaptive Speeded Up Robust Features (SA‐SURF), Discrete Wavelet Transform (DWT) based Patched Local Vector Pattern (LVP) features, HoG feature with harmonic mean based PCA and MBFDF” are extracted. Then, with this extracted feature strain the “optimized Convolutional Neural Network (CNN)” will be trained in the tamper detection phase. Since it is the key decision‐maker about the presence/absence of tamper, its weighting parameters are fine‐tuned via a novel improved Sea‐lion Customized Firefly algorithm (ISCFF) model. This ensures the enhancement of detection accuracy. Once an image is recognized to have tampers, then it is essential to identify the tamper localization. In the tamper localization phase, the copy‐move tampers are localized using the SIFT features, splicing tampers are localized using the DBN and the noise inconsistency is localized with a newly introduced threshold‐based tamper localization technique. The simulation outcomes illustrate that the adopted model attains better tamper detection as well as localization performance over the existing methods.

show abstract

Section: Feature Extraction Phase Frameworkmentioning

confidence: 99%

“…Since the scale values characterize the size of the involved box filters, a fixed radius