Using multimodal bio-metric features surgically altered face images recognition

Face recognition is an active area of research since 1980s. The increasing acceptability of the face as a biometric for recognition is due to the fact that it is non-intrusive. This makes it more suited to application areas of surveillance, border control and authentication. The task of successfully matching face images obtained before and after plastic surgery is a challenging problem. The challenge that plastic surgery imposes on the recognition system is enormous, considering the fact that the images are geometrically and structurally degraded by surgery amidst other degrading factors such as illumination, pose and expression. The degree to which a face is altered depends on the type and number of plastic surgeries performed, and it is difficult to model such variations. Existing approaches use learning based methods that are either computationally expensive or rely on a set of training images. Altering facial appearance using surgical procedures has raised a challenge for face recognition algorithms. Facial plastic surgery can also be misused by individuals who are trying to conceal their identity with the intent to commit fraud or evade law enforcement. These procedures amend the facial features and skin texture thereby providing a makeover in the appearance of face.

Basically, plastic surgery procedure introduces skin texture variations between images of the same person (intra-face) thereby making recognition more difficult than in normal scenario. Since the shape of significant face features such as eyes, nose, eyebrow and mouth remains unchanged even after plastic surgery, making use of these parameters face recognition algorithm can be designed. This paper focuses on analyzing the effect of plastic surgery in face recognition algorithms and a multimodal bio-metric feature extractor algorithm is proposed therefore to match face images before and after plastic surgery.