Call for Paper - January 2023 Edition
IJCA solicits original research papers for the January 2023 Edition. Last date of manuscript submission is December 20, 2022. Read More

Exposing Digital Image Forgeries by Illumination Color Classification using Sift Algorithm

International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Year of Publication: 2017
Priyanka Manthale, Geeta Patil

Priyanka Manthale and Geeta Patil. Exposing Digital Image Forgeries by Illumination Color Classification using Sift Algorithm. International Journal of Computer Applications 177(1):9-13, November 2017. BibTeX

	author = {Priyanka Manthale and Geeta Patil},
	title = {Exposing Digital Image Forgeries by Illumination Color Classification using Sift Algorithm},
	journal = {International Journal of Computer Applications},
	issue_date = {November 2017},
	volume = {177},
	number = {1},
	month = {Nov},
	year = {2017},
	issn = {0975-8887},
	pages = {9-13},
	numpages = {5},
	url = {},
	doi = {10.5120/ijca2017915436},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}


A digital image is fundamentally composed of a series of pixels, a word derived from combining picture and element. Traditionally, a photograph implies the truth of what has happened. Our life is full of digital images and tampering these digital images can be done easily with the help of powerful image editing software’s mainly to cover up the truthfulness of the photographs which often serve as evidence in court, in forensic investigation, criminal investigation, surveillance systems, intelligence services, medical imaging, and journalism. It is very easily to change the information represented by an image without leaving any obvious traces of tampering by using photo editing software like photo shop, photo grids which are easily available in the internet. In this work we presents a method to detect image retouching, image splicing and copy move attacks. Image splicing means specifically copying and pasting a person or any things from an image to another. Our approach is machine-learning based and requires minimal user interaction. The technique is applicable to images containing two or more people and requires no expert interaction for the tampering decision. To achieve this, we incorporate information from ‘physics’ and ‘statistical-based’ illuminant estimators on image regions of similar material. For implementation of this both IE we make use scale invariant feature transform(SIFT)algorithm in Matlab programming language. The proposed method detects the illuminate colour mismatch among different persons in a composite image. The illuminate colour obtained is quantified using chromaticity coordinates. It is then matched against that of different persons in the composite image to detect the forgery. We use SVM classification technique in our proposed work, since the classification performance using an SVM meta-fusion classifier is quite promising. We expect much better detection rate than those obtained in with the state of art methods.


  1. M. Johnson and H. Farid, “Exposing digital forgeries in complex lighting environments,” IEEE Trans. Inf. Forensics Security, vol. 3, no. 2, pp. 450–461, Jun. 2007.
  2. S. Gholap and P. K. Bora, “Illuminant colour based image forensics,” in Proc. IEEE Region 10 Conf., 2008E.
  3. Kee and H.Farid, “Exposing digital forgeries from 3-D lighting environments,” in Proc. IEEE Int. Workshop on Inform. Forensics and Security (WIFS), Dec. 2010.
  4. P.Saboia,T.Carvalho,andA.Rocha,“Eye specular highlights telltales for digital forensics: A machine learning approach,”inProc. IEEEInt. Conf.Image Processing (ICIP), 2011, pp. 1937–1940.
  5. K. Barnard, L. Martin, A. Coath, and B. Funt, “A comparison of computational colorconstancy algorithms–PartII:Experiments With ImageData,”IEEETrans.ImageProcess.,vol.11,no.9,pp.985–996, Sep. 2002.
  6. Charmil Nitin Bharti and Purvi Tandel, “A Survey of Image Forgery Detection Techniques,” in Proc. IEEE WiSPNET 2016 conference.
  7. Mr.Arun Anoop M, “Image forgery and its detection:A survey”,in Prof. IEEE (ICIIECS)2015.


Digital image forgery, Color illuminant constancy, machine learning, SIFT algorithm, Matlab Programming language.