Fisher Kernels for Handwritten Word-spotting

Perronnin, Florent; Rodríguez-Serrano, José A.

doi:10.1109/icdar.2009.16

Cited by 34 publications

(25 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We observe how the FV baseline is already able to outperform some popular methods on both datasets. This is in line with the findings of [20], where the FV of a HMM outperforms the standard HMM on keyword classification tasks. The exemplar SVM has a limited influence.…”

Section: Methodssupporting

confidence: 80%

See 1 more Smart Citation

Handwritten Word Spotting with Corrected Attributes

Almazán

Gordo

Fornés

et al. 2013

2013 IEEE International Conference on Computer Vision

View full text Add to dashboard Cite

We propose an approach to multi-writer word spotting, where the goal is to find a query word in a dataset comprised of document images. We propose an attributes-based approach that leads to a low-dimensional, fixed-length representation of the word images that is fast to compute and, especially, fast to compare. This approach naturally leads to an unified representation of word images and strings, which seamlessly allows one to indistinctly perform queryby-example, where the query is an image, and query-bystring, where the query is a string. We also propose a calibration scheme to correct the attributes scores based on Canonical Correlation Analysis that greatly improves the results on a challenging dataset. We test our approach on two public datasets showing state-of-the-art results.

show abstract

Section: Methodssupporting

confidence: 80%

“…In both cases, the methods are limited to tiny datasets. A more recent work [20] exploits the Fisher kernel framework [13] to construct the Fisher vector of a HMM. This representation has a fixed length and can be used for efficient spotting tasks, although the paper focuses on only 10 different keywords.…”

Section: Word Representationmentioning

confidence: 99%

Handwritten Word Spotting with Corrected Attributes

Almazán

Gordo

Fornés

et al. 2013

2013 IEEE International Conference on Computer Vision

View full text Add to dashboard Cite

show abstract

“…In [8] pseudo-2D HMMs have been investigated and [31] proposes generalized HMMs where more than one emission in each hidden state is allowed. Unsupervised adaptation of whole word HMMs to a specific writer is proposed in [32] and [33] discusses the usage of the Fisher Kernel of the HMM to estimate a good confidence measure.…”

Section: A Related Work 1) Word Based Abstractpottingmentioning

confidence: 99%

“…It is based on Hidden Markov Models (HMMs). HMMs are state-of-the-art for modeling handwritten text [51] and have been widely used for keyword spotting [3], [28], [31], [33], [47], [52], [53]. In [30], trained character models are used to spot arbitrary keywords in complete text line images using an efficient lexicon-free approach.…”

Section: B Hmm Reference Systemmentioning

confidence: 99%

A Novel Word Spotting Method Based on Recurrent Neural Networks

Frinken

Fischer

Manmatha

et al. 2012

IEEE Trans. Pattern Anal. Mach. Intell.

243

191

View full text Add to dashboard Cite

Abstract-Keyword spotting refers to the process of retrieving all instances of a given keyword from a document. In the present paper, a novel keyword spotting method for handwritten documents is described. It is derived from a neural network based system for unconstrained handwriting recognition. As such it performs template-free spotting, i.e. it is not necessary for a keyword to appear in the training set. The keyword spotting is done using a modification of the CTC Token Passing algorithm in conjunction with a recurrent neural network. We demonstrate that the proposed systems outperforms not only a classical dynamic time warping based approach but also a modern keyword spotting system, based on hidden Markov models. Furthermore, we analyze the performance of the underlying neural networks when using them in a recognition task followed by keyword spotting on the produced transcription. We point out the advantages of keyword spotting when compared to classic text line recognition.

show abstract

“…Recently, keyword spotting systems that are modified versions of handwriting recognition systems have received increasing attention. In [10], [11], [12], hidden Markov models are used to find the words to be searched. In [13], a novel approach using bidirectional long short-term (BLSTM) neural networks is proposed.…”

Section: Introductionmentioning

confidence: 99%

Adapting BLSTM Neural Network Based Keyword Spotting Trained on Modern Data to Historical Documents

Frinken

Fischer

Bunke

et al. 2010

2010 12th International Conference on Frontiers in Handwriting Recognition

View full text Add to dashboard Cite

Abstract-Being able to search for words or phrases in historic handwritten documents is of paramount importance when preserving cultural heritage. Storing scanned pages of written text can save the information from degradation, but it does not make the textual information readily available. Automatic keyword spotting systems for handwritten historic documents can fill this gap. However, most such systems have trouble with the great variety of writing styles. It is not uncommon for handwriting processing systems to be built for just a single book. In this paper we show that neural network based keyword spotting systems are flexible enough to be used successfully on historic data, even when they are trained on a modern handwriting database. We demonstrate that with little transcribed historic text, added to the training set, the performance can further be enhanced.

show abstract

Fisher Kernels for Handwritten Word-spotting

Abstract: The

Cited by 34 publications

References 10 publications

Handwritten Word Spotting with Corrected Attributes

Handwritten Word Spotting with Corrected Attributes

A Novel Word Spotting Method Based on Recurrent Neural Networks

Adapting BLSTM Neural Network Based Keyword Spotting Trained on Modern Data to Historical Documents

Contact Info

Product

Resources

About