Study of Image Splicing Detection

Zhang, Zhen; Zhou, Ying; Kang, Jian; Ren, Yuan

doi:10.1007/978-3-540-87442-3_136

Cited by 17 publications

(11 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 3 shows the ROC curves plotted between detection accuracy and false positive ratio for all the features. The area under the ROC curve can be find out using mathematical formula given in (5). In case of SURF, as the threshold value increases the curve also increases and last value denotes the point where curve becomes stable.…”

Section: Experimental Outcomesmentioning

confidence: 99%

See 1 more Smart Citation

Calibrating Thresholds Based on Trade-Offs Between Detection Accuracy and FPR for Copy Move Forgery Detection

Walia¹,

Kumar²

2019

IJRTE

View full text Add to dashboard Cite

In this paper, prominent keypoint based features are compared in order to analyze their reliability and efficiency against forgery detection. Four features specifically SURF, KAZE, Harris corner points and BRISK features are used individually on a set of images. The method includes four phases: Image pre-processing, keypoint detection, feature vector description and feature vector matching. In feature matching, MaxRatio has been chosen as a varying parameter for calculating values of false positives and false negatives for each feature. MaxRatio defines the ratio for rejecting ambiguous matches of feature descriptors in the images. The optimal threshold value for MaxRatio is calibrated with the help of trade-off between detection accuracy and false positive ratio. The changes in false negative ratio and false positive ratio are picturized in order to find out optimal threshold for detection accuracy. ROC curves are also plotted for each feature at different values of MaxRatio and area under the ROC curves are calculated. The experiments are performed on two benchmark datasets, namely CASIA version 2.0 and MICC-F600. It has been perceived from experimental outcomes that KAZE features gave best values for all the performance metrics namely accuracy, precision, area under the ROC curve and F1-score with little compromise in time complexity, whereas Harris corner points gave the worst results as compared to rest of the features. Further, in order to improve the execution time, the computation of non-linear scale space process in KAZE can be simplified and GPU programming for real-time performance may also be used.

show abstract

Section: Experimental Outcomesmentioning

confidence: 99%

“…Image retouching is most commonly used in fashion photography and in magazines to make photographs more attractive. Splicing is a method in which the images are consolidated to make an altered image [5]. A piece of one image is taken and fixed into another image.…”

Section: Introductionmentioning

confidence: 99%

Calibrating Thresholds Based on Trade-Offs Between Detection Accuracy and FPR for Copy Move Forgery Detection

Walia¹,

Kumar²

2019

IJRTE

View full text Add to dashboard Cite

show abstract

“…The basic definition of image splicing is a process that crops and paste regions from same or separate sources. The following figure (4) shows one of the example form of image splicing process and its steps [4].…”

Section: Image Splicingmentioning

confidence: 99%

Analysis of Digital Image Splicing Detection

Burvin¹,

Esther²

2014

IOSRJCE

View full text Add to dashboard Cite

The availability of photo manipulation software has made it unprecedentedly easy to manipulate images for malicious purposes. One of the most common forms of digital image or photographic manipulation operation is known as image splicing or image composition. It is a process that's crops and paste regions from same or separate sources. In this paper, we analyze various automatic image forensic techniques for detecting digital image splicing.

show abstract

“…Image splicing [4] means combining two or more parts of different images and creating a new one without performing any post-processing, is one of the most prevalent operations to make digital image forgeries. In fact, image splicing deceives the Human Visual System (HVS) to achieve its malicious purposes.…”

Section: Introductionmentioning

confidence: 99%

SVD-based image splicing detection

Moghaddasi

Jalab

Noor

2014

Proceedings of the 6th International Conference on Information Technology and Multimedia

View full text Add to dashboard Cite

Digital image forgery is becoming easier to perform because of the rapid development of various manipulation tools. Image splicing is one of the most common image forgery techniques. To detect the spliced images several methods proposed utilizing the statistical features of the digital images. In this paper, a new image splicing detection approach proposed based on singular value decomposition (SVD) feature extraction method applied in steganalysis. SVD-based features are merged with discrete cosine transform (DCT) for image splicing detection. Support vector machine is used to distinguish between authentic and spliced images. The results show a detection accuracy of 78.82% is achieved for the proposed method with only 50 dimensional feature vector. Furthermore the performance of SVD-based features needs more improvement in image splicing detection area of work.

show abstract

Study of Image Splicing Detection

Cited by 17 publications

References 8 publications

Calibrating Thresholds Based on Trade-Offs Between Detection Accuracy and FPR for Copy Move Forgery Detection

Calibrating Thresholds Based on Trade-Offs Between Detection Accuracy and FPR for Copy Move Forgery Detection

Analysis of Digital Image Splicing Detection

SVD-based image splicing detection

Contact Info

Product

Resources

About