A modified convolutional neural network for face sketch synthesis

A novel deep learning method for face sketch synthesis is proposed in this work. It builds a lightweight neural network which contains two convolutional layers, a pooling layer and a multilayer perceptron convolutional layer to learn a mapping from face photos to sketches. Unlike conventional example-based methods which need to solve complex optimization problems, the proposed method only computes convolution and pooling operations, hence significantly improves the synthesis efficiency. Besides, due to the global feature extraction of the convolutional layer, it achieves more continuous and faithful facial contours. Experiments on three benchmark datasets demonstrate that compared with several state-of-the-arts, the proposed method achieves highly competitive numerical results and is more robust to illumination and expression variations.