DeepPainter: Painter Classification Using Deep Convolutional Autoencoders

TL;DR

This paper introduces DeepPainter, a deep convolutional autoencoder-based method for painter classification that outperforms previous techniques by significantly increasing accuracy without manual feature extraction.

Contribution

It presents a novel deep autoencoder approach for painter classification that eliminates manual feature extraction and achieves state-of-the-art accuracy.

Findings

Achieved 96.52% accuracy on 3-painter classification

Reduced error rate by 63% compared to previous methods

Operates directly on raw pixel data without preprocessing

Abstract

In this paper we describe the problem of painter classification, and propose a novel approach based on deep convolutional autoencoder neural networks. While previous approaches relied on image processing and manual feature extraction from paintings, our approach operates on the raw pixel level, without any preprocessing or manual feature extraction. We first train a deep convolutional autoencoder on a dataset of paintings, and subsequently use it to initialize a supervised convolutional neural network for the classification phase. The proposed approach substantially outperforms previous methods, improving the previous state-of-the-art for the 3-painter classification problem from 90.44% accuracy (previous state-of-the-art) to 96.52% accuracy, i.e., a 63% reduction in error rate.