Feature Mixing for Writer Retrieval and Identification on Papyri Fragments

TL;DR

This paper introduces a novel deep learning architecture with feature mixing for improved writer retrieval and identification on papyri fragments, achieving state-of-the-art results on benchmark datasets.

Contribution

A new neural network architecture combining residual backbones and feature mixing for enhanced writer retrieval and identification on papyri fragments.

Findings

Achieved 26.6% and 24.9% mAP on PapyRow for writer and page retrieval.

Achieved 44.0% and 29.3% mAP on HisFragIR20, setting new state-of-the-art.

Binarization of fragments does not improve retrieval performance.

Abstract

This paper proposes a deep-learning-based approach to writer retrieval and identification for papyri, with a focus on identifying fragments associated with a specific writer and those corresponding to the same image. We present a novel neural network architecture that combines a residual backbone with a feature mixing stage to improve retrieval performance, and the final descriptor is derived from a projection layer. The methodology is evaluated on two benchmarks: PapyRow, where we achieve a mAP of 26.6 % and 24.9 % on writer and page retrieval, and HisFragIR20, showing state-of-the-art performance (44.0 % and 29.3 % mAP). Furthermore, our network has an accuracy of 28.7 % for writer identification. Additionally, we conduct experiments on the influence of two binarization techniques on fragments and show that binarizing does not enhance performance. Our code and models are available to the community.