Skip to Main content Skip to Navigation
Conference papers

ICFHR 2020 Competition on Image Retrieval for Historical Handwritten Fragments

Abstract : This competition succeeds upon a line of compe-titions for writer and style analysis of historical documentimages. In particular, we investigate the performance of large-scale retrieval of historical document fragments in terms ofstyle and writer identification. The analysis of historic fragmentsis a difficult challenge commonly solved by trained humanists.In comparison to previous competitions, we make the resultsmore meaningful by addressing the issue of sample granularityand moving from writer to page fragment retrieval. The twoapproaches, style and author identification, provide informationon what kind of information each method makes better use of andindirectly contribute to the interpretability of the participatingmethod. Therefore, we created a large dataset consisting of morethan 120 000 fragments. Although the most teams submittedmethods based on convolutional neural networks, the winningentry achieves an mAP below 40 %.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02935079
Contributor : Dominique Stutzmann <>
Submitted on : Thursday, September 10, 2020 - 8:32:36 AM
Last modification on : Friday, September 11, 2020 - 7:44:24 AM

Identifiers

Collections

Citation

Mathias Seuret, Anguelos Nicolaou, Dominique Stutzmann, Andreas Maier, Vincent Christlein. ICFHR 2020 Competition on Image Retrieval for Historical Handwritten Fragments. 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), Sep 2020, Dortmund, Germany. pp.216-221, ⟨10.1109/ICFHR2020.2020.0004⟩. ⟨hal-02935079⟩

Share

Metrics

Record views

56