A Novel Graph Database for Handwritten Word Images

Stauffer, Michael; Fischer, Andreas; Riesen, Kaspar

doi:10.1007/978-3-319-49055-7_49

Cited by 24 publications

(23 citation statements)

References 20 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second strategy only considers the two most promising individual graph extraction methods as proposed in [49], viz. Keypoint and Projection.…”

Section: Ensemble Methods For Graphsmentioning

confidence: 99%

“…The present article combines several lines of research and substantially extends three preliminary conference papers [49][50][51]. Moreover, in the empirical evaluation we use two additional datasets of a very recent KWS benchmark [52] and thoroughly present and discuss the evaluation of all parameters.…”

Section: Contributionmentioning

confidence: 99%

“…In the following paragraphs four graph representation formalisms (so-called graph extraction algorithms) as well as their corresponding parameters (see Table 1) are introduced. For further details and a more thorough introduction we refer to [49].…”

Section: Graph Representationmentioning

confidence: 99%

See 2 more Smart Citations

Keyword spotting in historical handwritten documents based on graph matching

Stauffer

Fischer

Riesen

2018

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

In the last decades historical handwritten documents have become increasingly available in digital form. Yet, the accessibility to these documents with respect to browsing and searching remained limited as full automatic transcription is often not possible or not sufficiently accurate. This paper proposes a novel reliable approach for template-based keyword spotting in historical handwritten documents. In particular, our framework makes use of different graph representations for segmented word images and a sophisticated matching procedure. Moreover, we extend our method to a spotting ensemble. In an exhaustive experimental evaluation on four widely used benchmark datasets we show that the proposed approach is able to keep up or even outperform several state-of-the-art methods for template-and learning-based keyword spotting.

show abstract

“…The second strategy only considers the two most promising individual graph extraction methods as proposed in [49], viz. Keypoint and Projection.…”

Section: Ensemble Methods For Graphsmentioning

confidence: 99%

Section: Contributionmentioning

confidence: 99%

See 1 more Smart Citation

Keyword spotting in historical handwritten documents based on graph matching

Stauffer

Fischer

Riesen

2018

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

show abstract

“…One task researchers have focused on is the following: Given a database G that contains labeled graphs, find all graphs G ∈ G that are sufficiently similar to a query graph H or find the k graphs from G that are most similar to H [23, 29,66]. Being able to quickly answer graph similarity queries of this kind is crucial for the development of performant pattern recognition techniques in various application domains [62], such as keyword spotting in handwritten documents [61] and cancer detection [48].…”

Section: Introductionmentioning

confidence: 99%

Comparing heuristics for graph edit distance computation

Blumenthal¹,

Boria²,

Gamper³

et al. 2019

The VLDB Journal

View full text Add to dashboard Cite

Because of its flexibility, intuitiveness, and expressivity, the graph edit distance (GED) is one of the most widely used distance measures for labeled graphs. Since exactly computing GED is NP-hard, over the past years, various heuristics have been proposed. They use techniques such as transformations to the linear sum assignment problem with error-correction, local search, and linear programming to approximate GED via upper or lower bounds. In this paper, we provide a systematic overview of the most important heuristics. Moreover, we empirically evaluate all compared heuristics within an integrated implementation.

show abstract

“…The COIL-DEL database includes 3900 graphs belonging to 100 different classes with 39 instances per class; each instance has a different rotation angle. The HistoGraph dataset 4[68] consists of graphs representing words from the communicating letters written by the first US president, George Washington. It consists of 293 graphs generated from 30 distinct words.…”

mentioning

confidence: 99%

Hierarchical stochastic graphlet embedding for graph-based pattern recognition

Dutta

Riba

Lladós

et al. 2019

Neural Comput & Applic

View full text Add to dashboard Cite

Despite being very successful within the pattern recognition and machine learning community, graph-based methods are often unusable with many machine learning tools. This is because of the incompatibility of most of the mathematical operations in graph domain. Graph embedding has been proposed as a way to tackle these difficulties, which maps graphs to a vector space and makes the standard machine learning techniques applicable for them. However, it is well known that graph embedding techniques usually suffer from the loss of structural information. In this paper, given a graph, we consider its hierarchical structure for mapping it into a vector space. The hierarchical structure is constructed by topologically clustering the graph nodes, and considering each cluster as a node in the upper hierarchical level. Once this hierarchical structure of graph is constructed, we consider its various configurations of its parts, and use stochastic graphlet embedding (SGE) for mapping them into vector space. Broadly speaking, SGE produces a distribution of uniformly sampled low to high order graphlets as a way to embed graphs into the vector space.In what follows, the coarse-to-fine structure of a graph hierarchy and the statistics fetched through the distribution of low to high order stochastic graphlets complements each other and include important structural information with varied contexts. Altogether, these two techniques substantially cope with the usual information loss involved in graph embedding techniques, and it is not a surprise that we obtain more robust vector space embedding of graphs. This fact has been corroborated through a detailed experimental evaluation on various benchmark graph datasets, where we outperform the state-of-the-art methods.

show abstract

A Novel Graph Database for Handwritten Word Images

Cited by 24 publications

References 20 publications

Keyword spotting in historical handwritten documents based on graph matching

Keyword spotting in historical handwritten documents based on graph matching

Comparing heuristics for graph edit distance computation

Hierarchical stochastic graphlet embedding for graph-based pattern recognition

Contact Info

Product

Resources

About