Image aesthetic evaluation using paralleled deep convolution neural network
This addresses the problem of automating aesthetic feature extraction for image evaluation, but it is incremental as it builds on existing deep learning approaches.
The paper tackled image aesthetic evaluation by proposing a paralleled deep convolutional neural network (PDCNN) to automatically learn aesthetic features, achieving better performance than traditional methods.
Image aesthetic evaluation has attracted much attention in recent years. Image aesthetic evaluation methods heavily depend on the effective aesthetic feature. Traditional meth-ods always extract hand-crafted features. However, these hand-crafted features are always designed to adapt particu-lar datasets, and extraction of them needs special design. Rather than extracting hand-crafted features, an automati-cally learn of aesthetic features based on deep convolutional neural network (DCNN) is first adopt in this paper. As we all know, when the training dataset is given, the DCNN architecture with high complexity may meet the over-fitting problem. On the other side, the DCNN architecture with low complexity would not efficiently extract effective features. For these reasons, we further propose a paralleled convolutional neural network (PDCNN) with multi-level structures to automatically adapt to the training dataset. Experimental results show that our proposed PDCNN architecture achieves better performance than other traditional methods.