# DeepPainter: Painter Classification Using Deep Convolutional Autoencoders

arXiv: https://arxiv.org/abs/1711.08763 · HTML: https://mlsanity.com/paper/1711.08763/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2017.

## Built on by (most cited first, 5 of 5)

- [Understanding and Creating Art with AI: Review and Outlook](https://mlsanity.com/paper/2102.09109/) (2021)
- [Towards Artistic Image Aesthetics Assessment: a Large-scale Dataset and a New Method](https://mlsanity.com/paper/2303.15166/) (2023)
- [A Convolutional Architecture for 3D Model Embedding](https://mlsanity.com/paper/2103.03764/) (2021)
- [Synergy of Machine and Deep Learning Models for Multi-Painter Recognition](https://mlsanity.com/paper/2304.14773/) (2023)
- [Large-image Object Detection for Fine-grained Recognition of Punches Patterns in Medieval Panel Painting](https://mlsanity.com/paper/2501.12489/) (2025)

## Abstract (arXiv)

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.