Pattern spotting in historical documents using convolutional models

Ignacio Ubeda , José M. Saavedra , Stéphane Nicolas (1) , Caroline Petitjean (1) , Laurent Heutte (1)

1 DocApp - LITIS - Equipe Apprentissage

Pattern spotting consists of searching in a collection of historical document images for occurrences of a graphical object using an image query. Contrary to object detection, no prior information nor predefined class is given about the query so training a model of the object is not feasible. In this paper, a convolutional neural network approach is proposed to tackle this problem. We use RetinaNet as a feature extractor to obtain multiscale embeddings of the regions of the documents and also for the queries. Experiments conducted on the DocExplore dataset show that our proposal is better at locating patterns and requires less storage for indexing images than the state-of-the-art system, but fails at retrieving some pages containing multiple instances of the query.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Ignacio Ubeda, José M. Saavedra, Stéphane Nicolas, Caroline Petitjean, Laurent Heutte. Pattern spotting in historical documents using convolutional models. 5th International Workshop on Historical Document Imaging and Processing, HIP 2019, Sydney, Australia, Sept 2019, ICDAR2019, Sep 2019, Sydney, Australia. pp.60-65, ⟨10.1145/3352631⟩. ⟨hal-02335779⟩