Combining approaches to on-line handwriting information retrieval

Abstract

In this work, we propose to combine two quite different approaches for retrieving handwritten documents. Our hypothesis is that different retrieval algorithms should retrieve different sets of documents for the same query. Therefore, significant improvements in retrieval performances can be expected. The first approach is based on information retrieval techniques carried out on the noisy texts obtained through handwriting recognition, while the second approach is recognition-free using a word spotting algorithm. Results shows that for texts having a word error rate (WER) lower than 23%, the performances obtained with the combined system are close to the performances obtained on clean digital texts. In addition, for poorly recognized texts (WER > 52%), an improvement of nearly 17% can be observed with respect to the best available baseline method.

Ontology-Based Information Extraction from Handwritten Documents

“…Here the task is to find (retrieve) or classify a given set of documents [10]. Even if also some kind of information extraction is performed, this topic is only loosely related to the topic addressed in this paper, since we do not consider whole documents, but entities appearing in those documents.…”

From Handwriting Recognition to Ontologie-Based Information Extraction of Handwritten Notes

“…Document retrieval from handwritten documents became more and more popular in the last years. Here the task is to find (retrieve) or classify a given set of documents [9]. Even if also some kind of information extraction is performed, this topic is only loosely related to the topic addressed in this paper, since we do not consider whole documents, but entities appearing in those documents.…”