Image forgery detection review

Abstract

With the wide spread of digital document use in administrations, fabrication and use of forged documents have become a serious problem. This paper presents a study and classification of the most important works on image and document forgery detection. The classification is based on documents type, forgery type, detection method, validation dataset, evaluation metrics and obtained results. Most of existing forgery detection works are dealing with images and few of them analyze administrative documents and go deeper to analyze their contents.

A CNN based architecture for forgery detection in administrative documents

“…A stego picture is sent from a transmitter to a recipient. The secret message recovered from the stego picture can then be viewed by the receiver [4]. 2) Cellular automata: Cellular automata form a method for extracting statistical information from a digital image using the lower, upper and singular value decomposition.…”

“…The administrative document refers to a document and the information contained in a document created, received, or maintained by a court for recording administrative, fnancial, administrative, or managerial functions, policies, decisions, procedures, or the organization of operations or other court activities, subject to exceptions, and used to identify a person or his right or permission [4].…”

“…Verifying a digital images legitimacy is the aim of picture forgery detection. The two picture authentication methods are active and blind or passive [4].…”

“…1) Data collection: Benhamza et al [4] produced the dataset that we used in our study. It includes fles in pdf format.…”

A comparative study on image forgery-facial retouching

“…The detection of active forgery is quite simpler as one could have clue about the original image, such as watermarks or digital signatures [2]. On the contrary, a passive forgery detection is a techniques which requires no prior information of the image for verification; hence, it is very difficult to identify or authenticate the original image [3], [4]. Passive image forgery is further classified as copy move, rescaling, resizing and retouching.…”