Example-Based Facial Sketch Hallucination

In this paper, we propose an example-based facial sketch hallucination approach. Given a face image, its sketch image will be automatically hallucinated by learning from a training set, which includes a lot of face images and their corresponding sketch images. Our algorithm involves three stages. In the first stage which is called ¿feature extracting¿, we create the feature pyramid for each face image. And then, we find the closest matching pixel from the training face images for each pixel in the input image basing on the features defined in the extracting stage. The third is optimization stage in which we synthesize the ¿initial sketch¿ and optimize it to generate the finally hallucinated sketch. Experimental results demonstrate the efficacy of our algorithm.