02065nam a22001577a 4500999001700000100005800017100001300075245008700088260003000175300000900205500151200214700004701726856003301773942001101806952009001817  c60375d60372  aMumtaz Alia13MCSE04aSupervisor - Dr. Umair Ali Khan  a13MCSE04  aPerformance Comparison of Feature Detectors in Image Forgery Detection (ME Thesis)  aNawabshah:bQUEST,c2016.  a56p.  aABSTRACT

The authenticity of digital images has remained questionable ever since the technology has progressed to the extent where a plethora of freely available software can drastically change the image contents with much less effort. This offers a dedicated challenge to ascertain the veracity of a digital image, especially when it is to be presented as legal evidence. A number of techniques have been proposed to detect image    forgery, albeit their respective efficacy depends on the type of forgery and image features. Moreover, their respective performance with respect to accuracy and execution time also varies.
This thesis focuses on the most frequently used image forgery referred to as. copy­ move forgery. The work carried out in this thesis is two-fold. First. n hybrid approach combining the existing block-based and non-block-based techniques of copy-move forgery has been proposed. second, the performance of the proposed techniques has been evaluated with different image feature, including	SIFT, SURF MSER,  MinEgen, FAST and Harris. The evaluation criteria comprising accuracy, Precision, recall and execution time help to	select a desired tradeoff between accuracy and execution time. The results proposed in the thesis show that the proposed image forgery detection technique can successfully detect copy-move forgery with remarkably high accuracy and reasonable execution time. Apart from this, the proposed technique also works fine with the smoothed and brightened images.


     aDepartment of Computer System Engineering   uhttps://tinyurl.com/v2ymcexv  cTHESIS  00104070aRESEARCHbRESEARCHd2018-10-03l0pMP/27-306r2018-10-03 00:00:00yTHESIS