Unsupervised machine learning algorithm for face morphing

Face morphing is the process of morphing or merging the face of the subject image with the face of another test image. Techniques of face morphing have been utilized in quite diverse fields, mostly in the entertainment industry to replace the face of an actor with a resembling actor to complete movies in absence of the actor. Typical face morphing implemented in commercial cinemas are a result of image morphing that is implemented on still images. Face morphing is a complex procedure that encompasses extracting the face marking, followed by the formation of a mesh of triangles that would be further used for morphing the face of a test image to the subject Image. Though there are many different programs with the ability to morph faces the proceeds to select a suitable candidate still largely is done via manual procedures or even if automated, the process is rarely integrated with the face morphing program. For the morphing results to be seamless it should be ensured that there is very less difference between the original image and the morphed image that is, the resemblance between the two images should be very high, therefore there is a brief description in the report about “what is the process of implementing morphing and how such resemblance will be achieved. Our research work aims to design and implement a similar face morphing program that has a model integrated into it for selecting the best suitable candidate for face morphing. Using python programming and concepts of unsupervised learning we aim to create will have the ability to calculate the resemblance between the faces of the subject and various candidates and decide for itself which among different candidates is best suitable for face morphing. Since it finds the most resembling candidate for face morphing, hence the name Doppelgänger.