Hand-drawn sketch recognition with a double-channel convolutional neural network

Abstract In hand-drawn sketch recognition, the traditional deep learning method has problems of insufficient feature extraction and low recognition rate. To solve this problem, a new algorithm based on dual-channel convolutional neural network is proposed. Firstly, preprocessed to get smooth sketch. The contour obtained by algorithm. Then, are used as input image CNN. Finally, fusion carried out in full connection layer, classification results using softmax classifier. Experimental show that can effectively improve rate