Copy-paste forgery detection using deep learning with error level analysis

K, N V S K Vijayalakshmi; Sasikala, J.; Shanmuganathan, C.

doi:10.1007/s11042-023-15594-5

Cited by 3 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Building on prior research, we adopt ELA image processing [7]. This approach has exhibited a high accuracy score, prompting our interest in evaluating its performance on a model that we have developed.…”

Section: Methodsmentioning

confidence: 99%

“…Numerous studies have been conducted on image forgery detection, as referenced in [7][8] [9]. The existing research indicates that the outcomes in detecting image splicing forgery remain suboptimal.…”

Section: Issn 2085-4579mentioning

confidence: 99%

“…When an image is initially saved as a JPEG, compression takes place, facilitated by various editing software tools such as Adobe Lightroom, GIMP, and Adobe Photoshop. ELA serves as a technique to emphasize differences between authentic and manipulated images by analyzing the error levels introduced during compression [7]. ELA is a forensic method involving the recompression of an image with a predetermined error rate after the initial compression using lossy techniques.…”

Section: Error Level Analysis (Ela)mentioning

confidence: 99%

“…In the following research conducted by Vijayalakshmi K et al [7], ELA is employed to detect copy-paste images. The method was tested using the MICCF200 dataset.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Image Splicing Forgery Detection using Error Level Analysis and CNN

Irmawati

2023

ULTIMA InfoSys

View full text Add to dashboard Cite

The issue of image forgery through splicing has become increasingly relevant in the current digital era. Splicing involves the manipulation of images by combining parts of two or more different images to create a deceptive composite image. This technique can be employed for various purposes, including the dissemination of false information, damaging someone's reputation, or even creating confusion in specific contexts. Several techniques used to detect splicing involve statistical analysis, color analysis, and texture analysis. Additionally, artificial intelligence developments, such as deep learning, have been applied to enhance detection capabilities. In this study, we employed a Convolutional Neural Network (CNN) model to identify image deviations caused by splicing. Optimization was performed on the convolutional layers of the model to improve CNN performance. The integration of Error Level Analysis (ELA) was also implemented to aid in identifying splicing forgeries, where portions of one image are combined with parts of another. Areas that have undergone splicing may exhibit noticeable differences in error levels. The dataset utilized for this research was sourced from DVMM and CUISDE. The validation accuracy results for our CNN model before incorporating ELA were 61% for DVMM and 74% for CUISDE. After adding ELA, the CNN model demonstrated improved detection accuracy, achieving validation rates of 72% for DVMM and 71% for CUISDE.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Issn 2085-4579mentioning

confidence: 99%

Section: Error Level Analysis (Ela)mentioning

confidence: 99%

“…In the following research conducted by Vijayalakshmi K et al [7], ELA is employed to detect copy-paste images. The method was tested using the MICCF200 dataset.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations