Image Forgery Detection: Survey and Future Directions
In this age of digitization, digital images are used as a prominent carrier of visual information. Images are becoming increasingly ubiquitous in everyday life. Unprecedented involvement of digital images can be seen in various paramount fields like medic
- PDF / 580,164 Bytes
- 32 Pages / 439.37 x 666.142 pts Page_size
- 70 Downloads / 326 Views
1 Introduction One famous proverb says “A picture is worth a thousand words”. Now everybody understands the essence of this idiom. But due to the availability of sophisticated tools for image manipulation, it is very easy to tamper the image by anyone with a modicum of computer skills. Hence, authenticity of image is challenged openly, therefore somewhere the above idiom loses its essence. According to Merriam-Webster dictionary, digital image forgery is defined as “falsely and fraudulently altering a digital image”. Image forgery is not a new concept; it started way back in 1840. French photographer Hippolyte Bayard created the first tampered image (Fig. 1) entitled with, “Self Portrait as a Drowned Man”, in which, Bayard has professed to commit suicide [1]. More than a century ago, during American Civil War, a photo of American commanding general, General Ulysses S. Grant came into existence, which claimed that General Grant was sitting on horseback in front of his troops, at City Point, Virginia [2]. Later on, it has been found that image was not authentic; rather it was a composite of three images formed using negatives of the photographs. Almost a decade ago, Iran has been accused of doctoring an image from its missile tests; the image [3] was released on the official website, Iran’s Revolutionary Guard, which claimed that four missiles were heading skyward simultaneously. Recently, in July 2017, a fake image of Russian president Vladimir Putin was circulated over the social media related to the meeting with American president Donald Trump during the G20 summit 2017. This faked image garnered several thousand likes and retweets [4].
K. B. Meena · V. Tyagi (B) Jaypee University of Engineering and Technology, Raghogarh, Guna, MP, India e-mail: [email protected] © Springer Nature Singapore Pte Ltd. 2019 R. K. Shukla et al. (eds.), Data, Engineering and Applications, https://doi.org/10.1007/978-981-13-6351-1_14
163
164
K. B. Meena and V. Tyagi
Fig. 1 First fake image [1]
Fig. 2 Number of publications in the field of image forensics over the last two decades
Number of Publications
Image has remarkable role in various areas such as forensic investigation, criminal investigation, surveillance systems, intelligence system, sports, legal services, medical imaging, insurance claim, and journalism. Substantial amount of research has been carried out in the last one decade in the field of forgery detection. Figure 2 shows the bar chart of a number of publications versus four types of image forgery detection techniques (copy-move, image splicing, resampling, retouching) for last two decades, over the years 1998–2017, collected from Google Scholar. Few observations from this bar chart are: startling growth has been seen in copy-move forgery detection in last one decade, and a significant focus is also given on image splicing detection in the last one decade over the first decade. However, less focus was given on retouching detection, one reason behind this may be that retouching is the least pernicious type
Data Loading...
