New Dimensional Approach towards Fraps-Face Recognition after Plastic Surgery
Increasing popularity of plastic surgery and its effect on automatic face recognition has attracted attention from the research community and many studies were begun towards this area. The nonlinear variations introduced by plastic surgery remain difficult to be modelled by face recognition systems. The variations caused by plastic surgery are long lasting and irreversible. This paper focused on accurately recognizing face images before and after plastic surgery. A face granulation approach is used here. Non-disjoint granules of face images are generated. The face granulation scheme helps in analyzing multiple features simultaneously. Moreover the granulation approach helps to gain significant insights about the effect of plastic surgery procedures on different facial features and in the neighboring regions. In this approach face granules are generated pertaining to three levels of granularity. Two popular feature extractors namely Extended Uniform Circular Local Binary pattern (EUCLBP) and Scale Invariant Feature Transform (SIFT) are used for extracting discriminating information from face granules. BAT algorithm is used to match face images before and after plastic surgery. This approach provides the advantage of choosing better performing feature extractor for each face granule. This algorithm helps in discarding redundant and non discriminating face granules and achieving high identification accuracy.
Beema K.K, S. Shobana, M.E.
To read the full article Download Full Article