Go to page

Bibliographic Metadata

Learning Features for Writer Retrieval and Identification using Triplet CNNs
AuthorKeglevic, Manuel ; Fiel, Stefan ; Sablatnig, Robert
Published in
16th International Conference on Frontiers in Handwriting Recognition (ICFHR 2018), Niagara Falls, New York, USA, 2018, page 211-216
Document typeArticle in a collected edition
Keywords (EN)Writer Identification / Writer Retrieval / Document Analysis
Project-/ReportnumberEuropean Union's Horizon 2020: 674943
URNurn:nbn:at:at-ubtuw:3-3767 Persistent Identifier (URN)
 The work is publicly available
Learning Features for Writer Retrieval and Identification using Triplet CNNs [1.75 mb]
Abstract (English)

This paper presents a method for writer retrieval and identification using a feature descriptor learned by a Convolutional Neural Network. Instead of using a network for classification, we propose the use of a triplet network that learns a similarity measure for image patches. Patches of the handwriting are extracted and mapped into an embedding where this similarity measure is defined by the L2 distance. The triplet network is trained by maximizing the interclass distance, while minimizing the intraclass distance in this embedding. The image patches are encoded using the learned feature descriptor. By applying the Vector of Locally Aggregated Descriptors encoding to these features, we generate a feature vector for each document image. A detailed parameter evaluation is given which shows that this method achieves a mean average precision of 86.1% on the ICDAR 2013 writer identification dataset, but future work has to be done to improve the performance on historic datasets. In addition, the strategy for clustering the feature space is investigated.

The PDF-Document has been downloaded 13 times.