A keyword spotting approach using blurred shape model-based descriptors

Abstract

The automatic processing of handwritten historical documents is considered a hard problem in pattern recognition. In addition to the challenges given by modern handwritten data, a lack of training data as well as effects caused by the degradation of documents can be observed. In this scenario, keyword spotting arises to be a viable solution to make documents amenable for searching and browsing. For this task we propose the adaptation of shape descriptors used in symbol recognition. By treating each word image as a shape, it can be represented using the Blurred Shape Model and the Deformable Blurred Shape Model. Experiments on the George Washington database demonstrate that this approach is able to outperform the commonly used Dynamic Time Warping approach.

One Step Is Not Enough: A Multi-Step Procedure for Building the Training Set of a Query by String Keyword Spotting System to Assist the Transcription of Historical Document

“…KWS systems are usually grouped into two classes, depending on how the query is represented: query-by-example (QbE) and query-by-string (QbS) systems [ 1 ]. QbE systems require that users provide some examples of the word they want to search in the document collection [ 13 , 14 , 15 ], whereas QbS systems allow to provide a text string, named keyword , as query [ 16 , 17 , 18 , 19 ]. In the last few years, word spotting systems that can be used with both QbE and QbS search options have been proposed by exploiting, for example, an end-to-end deep neural network architecture [ 20 ] or pyramidal histogram of characters embeddings [ 21 , 22 ].…”

A Model for Evaluating the Performance of a Multiple Keywords Spotting System for the Transcription of Historical Handwritten Documents

“…Keyword spotting techniques can be grouped depending on whether the keyword is a string of characters ( Query-by-String ) [ 9 , 10 , 11 , 12 , 13 , 14 , 15 ] or a word image ( Query-by-Example ) [ 16 , 17 , 18 , 19 , 20 , 21 , 22 ] and whether the region of the document image to label is made by a preliminary segmentation step ( segmentation-based ) [ 23 , 24 , 25 , 26 ] or the whole page image ( segmentation-free ) [ 27 , 28 , 29 ]. For the purpose of historical document transcription, however, the most relevant discrimination is between lexicon-based and lexicon-free approaches.…”

Querying out-of-vocabulary words in lexicon-based keyword spotting

“…This work focuses on the case where queries are presented to the system as strings typed by the user (known as Query-by-String) [21,4,6,29,1,26,12,16,17,25], although an alternative formulation of KWS, where queries are presented as example images (known as Query-by-Example) is also very popular in the literature [10,19,11,7,22,5,3,27]. Query-by-Example approaches are typically training-free and are based on template (image) matching between the query (example image) and word-sized image regions of the documents.…”