Face Sketch Synthesis via Sparse Representation-Based Greedy Search

• Published in: IEEE transactions on image processing Vol. 24; no. 8; pp. 2466 - 2477
• Main Authors: Zhang, Shengchuan, Gao, Xinbo, Wang, Nannan, Li, Jie, Zhang, Mingjin
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.08.2015
• Subjects: Algorithms; Bayes methods; Biometric Identification - methods; Dictionaries; dictionary learning; Face; Face - anatomy & histology; Face sketch synthesis; fast index; Glass; greedy search; Hidden Markov models; Humans; Image coding; Image Processing, Computer-Assisted - methods; Machine Learning; Training; greedy search; dictionary learning; Face sketch synthesis; fast index
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2015.2422578

Face sketch synthesis has wide applications in digital entertainment and law enforcement. Although there is much research on face sketch synthesis, most existing algorithms cannot handle some nonfacial factors, such as hair style, hairpins, and glasses if these factors are excluded in the training set. In addition, previous methods only work on well controlled conditions and fail on images with different backgrounds and sizes as the training set. To this end, this paper presents a novel method that combines both the similarity between different image patches and prior knowledge to synthesize face sketches. Given training photo-sketch pairs, the proposed method learns a photo patch feature dictionary from the training photo patches and replaces the photo patches with their sparse coefficients during the searching process. For a test photo patch, we first obtain its sparse coefficient via the learnt dictionary and then search its nearest neighbors (candidate patches) in the whole training photo patches with sparse coefficients. After purifying the nearest neighbors with prior knowledge, the final sketch corresponding to the test photo can be obtained by Bayesian inference. The contributions of this paper are as follows: 1) we relax the nearest neighbor search area from local region to the whole image without too much time consuming and 2) our method can produce nonfacial factors that are not contained in the training set and is robust against image backgrounds and can even ignore the alignment and image size aspects of test photos. Our experimental results show that the proposed method outperforms several state-of-the-arts in terms of perceptual and objective metrics.