Word and Symbol Spotting Using Spatial Organization of Local Descriptors

Rusiñol, Marçal; Lladós, Josep

doi:10.1109/das.2008.24

Cited by 19 publications

(6 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many authors from the document analysis field, understanding keyword spotting as being a particular case of the object recognition task, started to apply such keypoint matching techniques to the problem of keyword spotting [23,48,56,58]. Such matching techniques have been either used to directly estimate similarities between word images, or by searching the query model image within full pages in segmentation-free scenarios.…”

Section: Abstractpotting As An Object Recognition Taskmentioning

confidence: 98%

A study of Bag-of-Visual-Words representations for handwritten keyword spotting

Aldavert

Rusiñol

Toledo

et al. 2015

IJDAR

Self Cite

View full text Add to dashboard Cite

The Bag-of-Visual-Words (BoVW) framework has gained popularity among the document image analysis community, specifically as a representation of handwritten words for recognition or spotting purposes. Although in the computer vision field the BoVW method has been greatly improved, most of the approaches in the document image analysis domain still rely on the basic implementation of the BoVW method disregarding such latest refinements. In this paper, we present a review of those improvements and its application to the keyword spotting task. We thoroughly evaluate their impact against a baseline system in the well-known George Washington dataset and compare the obtained results against nine state-of-the-art keyword spotting methods. In addition, we also compare both the baseline and improved systems with the methods presented at the Handwritten Keyword Spotting Competition 2014.

show abstract

Section: Abstractpotting As An Object Recognition Taskmentioning

confidence: 98%

A study of Bag-of-Visual-Words representations for handwritten keyword spotting

Aldavert

Rusiñol

Toledo

et al. 2015

IJDAR

Self Cite

View full text Add to dashboard Cite

show abstract

“…Later, it has been represented by using local descriptors such as SIFT features (222). In (223), for example, local descriptor (Harris-Laplace detector (224)) is used to build a proximity graph for any studied symbol. Fig.…”

Section: Structural Approachesmentioning

confidence: 99%

Graphical Symbol Recognition

Santosh

Wendling

2015

Wiley Encyclopedia of Electrical and Electronics Engineering

View full text Add to dashboard Cite

The chapter focuses on one of the key issues in document image processing i.e., graphical symbol recognition. Graphical symbol recognition is a sub-field of a larger research domain: pattern recognition. The chapter covers several approaches (i.e., statistical, structural and syntactic) and specially designed symbol recognition techniques inspired by real-world industrial problems. It, in general, contains research problems, state-of-the-art methods that convey basic steps as well as prominent concepts or techniques and research standpoints/directions that are associated with graphical symbol recognition. Keywords. Graphics processing • graphical symbol • recognition, retrieval and spotting • statistical approaches • structural and syntactic approaches • real-world problems. '... the recurring wish for methods capable of efficiently combining structural and statistical methods' and 'the very structural and spatial nature of the information we work with makes structural methods quite natural in the community.' The problem can further be extended to symbol spotting, but one can view this as a kind of retrieval (29-33), which is guided by user queries. Additionally, the recognition/retrieval process can be made with the help of local descriptors like scale invariant feature transform (SIFT) and with the use of techniques like bag-of-features so that either primitive or region extraction (segmentation) can be avoided. The question always remains the same, 'what approach does what (i.e., performance) in which context?'. As mentioned earlier, graphics recognition has an extremely rich state-of-the-art literature in symbol recognition and localization (6; 9; 34; 35). But the major state-of-the-art methods for symbol recognition,

show abstract

“…These component pairs are selected based on their proximity [7]. Each component is associated to its n-nearest components from its boundary.…”

Section: Spatial Information Encodingmentioning

confidence: 99%

“…Text information matching [4,5] has also been exploited to recognize textual objects. Document objects (symbol, seal, logos) are synthetic entities consisting of uniform regions which are highly structured [7,8]. These facts make geometric relationships between primitives a discriminative cue to spot symbols.…”

Section: Introductionmentioning

confidence: 99%

Seal object detection in document images using GHT of local component shapes

Roy¹,

Pal²,

Lladós³

2010

Proceedings of the 2010 ACM Symposium on Applied Computing

Self Cite

View full text Add to dashboard Cite

Due to noise, overlapped text/signature and multi-oriented nature, seal (stamp) object detection involves a difficult challenge. This paper deals with automatic detection of seal from documents with cluttered background. Here, a seal object is characterized by scale and rotation invariant spatial feature descriptors (distance and angular position) computed from recognition result of individual connected components (characters). Recognition of multi-scale and multioriented component is done using Support Vector Machine classifier. Generalized Hough Transform (GHT) is used to detect the seal and a voting is casted for finding possible location of the seal object in a document based on these spatial feature descriptor of components pairs. The peak of votes in GHT accumulator validates the hypothesis to locate the seal object in a document. Experimental results show that, the method is efficient to locate seal instance of arbitrary shape and orientation in documents.

show abstract

Word and Symbol Spotting Using Spatial Organization of Local Descriptors

Abstract: In this paper we present a method to spot

Cited by 19 publications

References 26 publications

A study of Bag-of-Visual-Words representations for handwritten keyword spotting

A study of Bag-of-Visual-Words representations for handwritten keyword spotting

Graphical Symbol Recognition

Seal object detection in document images using GHT of local component shapes

Contact Info

Product

Resources

About