Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 22
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Capítulo o parte de un libro (BookPart)

ImageCLEF 2014: Overview and analysis of the results

  • Caputo, Barbara
  • Müller, Henning
  • Martinez-Gomez, Jesus
  • Villegas Santamaría, Mauricio
  • Acar, Burak
  • Patricia, Novi
  • Marvasti, Neda
  • Üsküdar, Suzan
  • Cazorla, Miguel
  • García Varea, Ismael
  • Morell, Vicente
  • Paredes Palacios, Roberto
This paper presents an overview of the ImageCLEF 2014 evaluation lab. Since its first edition in 2003, ImageCLEF has become one of the key initiatives promoting the benchmark evaluation of algorithms for the annotation and retrieval of images in various domains, such as public and personal images, to data acquired by mobile robot platforms and medical archives. Over the years, by providing new data collections and challenging tasks to the community of interest, the ImageCLEF lab has achieved an unique position in the image annotation and retrieval research landscape. The 2014 edition consists of four tasks: domain adaptation, scalable concept image annotation, liver CT image annotation and robot vision. This paper describes the tasks and the 2014 competition, giving a unifying perspective of the present activities of the lab while discussing future challenges and opportunities., This work has been partially supported by the tranScriptorium FP7 project under grant #600707 (M. V., R. P.).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Capítulo o parte de un libro (BookPart)

Multimodal output combination for transcribing historical handwritten documents

  • GRANELL, EMILIO|||0000-0001-5782-7568
  • Martínez-Hinarejos, Carlos-D.|||0000-0002-6139-2891
Transcription of digitalised historical documents is an interesting task in the document analysis area. This transcription can be achieved by using Handwritten Text Recognition (HTR) on digitalised pages or by using Automatic Speech Recognition (ASR) on the dictation of contents. Moreover, another option is using both systems in a multimodal combination to obtain a draft transcription, given that combining the outputs of different recognition systems will generally improve the recognition accuracy. In this work, we present a new combination method based on Confusion Network. We check its effectiveness for transcribing a Spanish historical book. Results on both unimodal combination with different optical (for HTR) and acoustic (for ASR) models, and multimodal combination, show a relative reduction of Word and Character Error Rate of 14.3% and 16.6%, respectively, over the HTR baseline., Work partially supported by European Union -7th FP, under grant 600707 (tranScriptorium), and by the Spanish MEC under projects STraDA (TIN2012-37475-C02-01), Active2Trans (TIN2012-31723), and SmartWays (RTC-2014-1466-4).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Capítulo o parte de un libro (BookPart)

Relevant clouds: leveraging relevance feedback to build tag clouds for image search

  • Leiva Torres, Luis Alberto
  • Villegas Santamaría, Mauricio
  • Paredes Palacios, Roberto
Previous work in the literature has been aimed at exploring tag clouds to improve image search and potentially increase retrieval performance. However, to date none has considered the idea of building tag clouds derived from relevance feedback. We propose a simple approach to such an idea, where the tag cloud gives more importance to the words from the relevant images than the non-relevant ones. A preliminary study with 164 queries inspected by 14 participants over a 30M dataset of automatically annotated images showed that 1) tag clouds derived this way are found to be informative: users considered roughly 20% of the presented tags to be relevant for any query at any time; and 2) the importance given to the tags correlates with user judgments: tags ranked in the first positions tended to be perceived more often as relevant to the topic that users had in mind., Work supported by EU FP7/2007-2013 under grant agreements 600707 (tranScriptorium) and 287576 (CasMaCat), and by the STraDA project (TIN2012-37475-C02-01).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Capítulo o parte de un libro (BookPart)

ImageCLEF 2013: The vision, the data and the open challenges

  • Caputo ., Barbara
  • Muller ., Henning
  • Thomee ., Bart
  • Villegas, Mauricio
  • Zellhofer ., David
  • Goeau ., Herve
  • Joly ., Alexis
  • Bonnet, Pierre
  • Martínez Gómez, Jesús
  • García Varea, Ismael
  • Cazorla ., Miguel
  • Paredes Palacios, Roberto
This paper presents an overview of the ImageCLEF 2013 lab. Since its first edition in 2003, ImageCLEF has become one of the key initiatives promoting the benchmark evaluation of algorithms for the cross-language annotation and retrieval of images in various domains, such as public and personal images, to data acquired by mobile robot platforms and botanic collections. Over the years, by providing new data collections and challenging tasks to the community of interest, the ImageCLEF lab has achieved an unique position in the multi lingual image annotation and retrieval research landscape. The 2013 edition consisted of three tasks: the photo annotation and retrieval task, the plant identification task and the robot vision task. Furthermore, the medical annotation task, that traditionally has been under the ImageCLEF umbrella and that this year celebrates its tenth anniversary, has been organized in conjunction with AMIA for the first time. The paper describes the tasks and the 2013 competition, giving an unifying perspective of the present activities of the lab while discussion the future challenges and opportunities., This work has been partially supported by the Halser Foundation (B. C.),by the LiMoSINe FP7 project under grant # 288024 (B. T.), by the Khresmoi (grant# 257528) and PROMISE ( grant # 258191) FP 7 projects (H.M.) and by the tranScriptorium FP7 project under grant # 600707 (M. V., R. P.)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Offline Features for Classifying Handwritten Math Symbols with Recurrent Neural Networks

  • Álvaro Muñoz, Francisco
  • Benedí Ruiz, José Miguel
  • Sánchez Peiró, Joan Andreu|||0000-0003-0423-2020
In mathematical expression recognition, symbol classification is a crucial step. Numerous approaches for recognizing handwritten math symbols have been published, but most of them are either an online approach or a hybrid approach. There is an absence of a study focused on offline features for handwritten math symbol recognition. Furthermore, many papers provide results difficult to compare. In this paper we assess the performance of several well-known offline features for this task. We also test a novel set of features based on polar histograms and the vertical repositioning method for feature extraction. Finally, we report and analyze the results of several experiments using recurrent neural networks on a large public database of online handwritten math expressions. The combination of online and offline features significantly improved the recognition rate., This work was partially supported by the Spanish MEC under the STraDA research project (TIN2012-37475-C02-01) and the FPU grant (AP2009-4363), by the Generalitat Valenciana under the grant Prometeo/2009/014, and through the EU 7th Framework Programme grant tranScriptorium (Ref: 600707).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Contex-aware gestures for mixed-initiative text editings UIs

  • Leiva, Luis A.
  • Alabau, Vicent
  • Romero Gómez, Verónica
  • Toselli, Alejandro Héctor|||0000-0001-6955-9249
  • Vidal, Enrique|||0000-0003-4579-5196
[EN] This work is focused on enhancing highly interactive text-editing applications with gestures. Concretely, we study Computer Assisted Transcription of Text Images (CATTI), a handwriting transcription system that follows a corrective feedback paradigm, where both the user and the system collaborate efficiently to produce a high-quality text transcription. CATTI-like applications demand fast and accurate gesture recognition, for which we observed that current gesture recognizers are not adequate enough. In response to this need we developed MinGestures, a parametric context-aware gesture recognizer. Our contributions include a number of stroke features for disambiguating copy-mark gestures from handwritten text, plus the integration of these gestures in a CATTI application. It becomes finally possible to create highly interactive stroke-based text-editing interfaces, without worrying to verify the user intent on-screen. We performed a formal evaluation with 22 e-pen users and 32 mouse users using a gesture vocabulary of 10 symbols. MinGestures achieved an outstanding accuracy (<1% error rate) with very high performance (<1 ms of recognition time). We then integrated MinGestures in a CATTI prototype and tested the performance of the interactive handwriting system when it is driven by gestures. Our results show that using gestures in interactive handwriting applications is both advantageous and convenient when gestures are simple but context-aware. Taken together, this work suggests that text-editing interfaces not only can be easily augmented with simple gestures, but also may substantially improve user productivity., This work has been supported by the European Commission through the 7th Framework Program (tranScriptorium: FP7- ICT-2011-9, project 600707 and CasMaCat: FP7-ICT-2011-7, project 287576). It has also been supported by the Spanish MINECO under grant TIN2012-37475-C02-01 (STraDa), and the Generalitat Valenciana under grant ISIC/2012/004 (AMIIS).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

tranScriptorium: a european project on handwritten text recognition

  • Sánchez Peiró, Joan Andreu|||0000-0003-0423-2020
  • Vidal, Enrique|||0000-0003-4579-5196
  • Mühlberger, Günter
  • Gatos, Basilis
  • Schofield, Philip
  • Depuydt, Katrien
  • Davis, Richard M.
  • De Does, Jesse
The tranScriptorium project aims to develop innovative, efficient and cost-effective solutions for annotating handwritten historical documents using modern, holistic Handwritten Text Recognition (HTR) technology. Three actions are planned in tranScriptorium: i) improve basic image preprocessing and holistic HTR techniques; ii) develop novel indexing and keyword searching approaches; and iii) capitalize on new, user-friendly interactive-predictive HTR approaches for computer-assisted operation., The research leading to these results has received funding from the European Union’s Seventh Framework Programme (FP7/2007-2013) under grant agreement no. 600707 - tranScriptorium.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Handwritten Text Recognition for Historical Documents in the tranScriptorium Project

  • Sánchez Peiró, Joan Andreu|||0000-0003-0423-2020
  • Bosch Campos, Vicente
  • Romero Gómez, Verónica
  • Depuydt, Katrien
  • De Does, Jesse
Transcription of historical handwritten documents is a crucial problem for making easier the access to these documents to the general public. Currently, huge amount of historical handwritten documents are being made available by on-line portals worldwide. It is not realistic to obtain the transcription of these documents manually, and therefore automatic techniques has to be used. tranScriptorium is a project that aims at researching on modern Handwritten Text Recognition (HTR) technology for transcribing historical handwritten documents. The HTR technology used in tranScriptorium is based on models that are learnt automatically from examples. This HTR technology has been used on a Dutch collection from 15th century selected for the tranScriptorium project. This paper provides preliminary HTR results on this Dutch collection that are very encouraging, taken into account that minimal resources have been deployed to develop the transcription system., The research leading to these results has received funding from the European Union’s Seventh Framework Programme (FP7/2007-2013) under grant agreement no. 600707 - tranScriptorium and the Spanish MEC under the STraDa (TIN2012-37475-C02-01) research project.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Capítulo o parte de un libro (BookPart)

Escritoire: A Multi-touch Desk with e-Pen Input for Capture, Management and Multimodal Interactive Transcription of Handwritten Documents

  • Martín-Albo Simón, Daniel
  • Romero Gómez, Verónica
  • Vidal, Enrique|||0000-0003-4579-5196
A large quantity of documents used every day are still handwritten. However, it is interesting to transform each of these documents into its digital version for managing, archiving and sharing. Here we present Escritoire, a multi-touch desk that allows the user to capture, transcribe and work with handwritten documents. The desktop is continuously monitored using two cameras. Whenever the user makes a specific hand gesture over a paper, Escritoire proceeds to take an image. Then, the capture is automatically preprocesses, obtaining as a result an improved representation. Finally, the text image is transcribed using automatic techniques and finally the transcription is displayed on Escritoire., This work was partially supported by the Spanish MEC under FPU scholarship (AP2010-0575), STraDA research project (TIN2012-37475-C02-01) and MITTRAL research project (TIN2009-14633-C03-01); the EU’s 7th Framework Programme under tranScriptorium grant agreement (FP7/2007-2013/600707).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

On improving robustness of LDA and SRDA by using tangent vectors

  • Villegas Santamaría, Mauricio
  • Paredes Palacios, Roberto
[EN] In the area of pattern recognition, it is common for few training samples to be available with respect to the dimensionality of the representation space; this is known as the curse of dimensionality. This problem can be alleviated by using a dimensionality reduction approach, which overcomes the curse relatively well. Moreover, supervised dimensionality reduction techniques generally provide better recognition performance; however, several of these tend to suffer from the curse when applied directly to high-dimensional spaces. We propose to overcome this problem by incorporating additional information to supervised subspace learning techniques using what is known as tangent vectors. This additional information accounts for the possible differences that the sample data can suffer. In fact, this can be seen as a way to model the unseen data and make better use of the scarce training samples. In this paper, methods for incorporating tangent vector information are described for one classical technique (LDA) and one state-of-the-art technique (SRDA). Experimental results confirm that this additional information improves performance and robustness to known transformations., Work partially supported through the EU 7th Framework Programme grant tranScriptorium (Ref: 600707), by the Spanish MEC under the STraDA research project (TIN2012-37475-C02-01) and by the Generalitat Valenciana under grant Prometeo/2009/014.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Capítulo o parte de un libro (BookPart)

Ground-Truth production in the tranScriptorium Project

  • Gatos, Basilis
  • Louloudis, Georgios
  • Caser, Tim
  • Grint, Kris
  • Romero Gómez, Verónica
  • Sánchez Peiró, Joan Andreu|||0000-0003-0423-2020
  • Toselli, Alejandro Héctor|||0000-0001-6955-9249
  • Vidal, Enrique|||0000-0003-4579-5196
Tran Scriptorium is a 3-years project that aims to develop innovative, cost-effective solutions for the indexing, search and full transcription of historical handwritten document images, using Handwritten Text Recognition (HTR) technology. The production of ground-truth (GT) of a dataset of handwritten document images is among the first tasks. We address novel approaches for the faster production of this GT based on crowd-sourcing and on prior-knowledge methods. We also address here a novel low-cost semi-supervised procedure for obtaining pairs of correct line-level aligned detected/extracted text line images and text line transcripts, specially suitable for training models of the HTR technology employed in Tran Scriptorium., Work supported by the European Union’s Seventh Framework Programme (FP7/2007-2013) under grant agreement No.600707 - tranScriptorium.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Overview of the ImageCLEF 2014 Scalable Concept Image Annotation Task

  • Villegas Santamaría, Mauricio
  • Paredes Palacios, Roberto
[EN] The ImageCLEF 2014 Scalable Concept Image Annotation task was the third edition of a challenge aimed at developing more scalable image annotation systems. Unlike traditional image annotation challenges, which rely on a set of manually annotated images as training data, the participants were only allowed to use data and/or resources that as new concepts to detect are introduced do not require significant human effort (such as hand labeling). The participants were provided with web data consisting of 500,000 images, which included textual features obtained from the web pages on which the images appeared, as well as various visual features extracted from the images themselves. To optimize their systems, the participants were provided with a development set of 1,940 samples and its corresponding hand labeled ground truth for 107 concepts. The performance of the submissions was measured using a test set of 7,291 samples which was hand labeled for 207 concepts among which 100 were new concepts unseen during development. In total 11 teams participated in the task submitting overall 58 system runs. Thanks to the larger amount of unseen concepts in the results the generalization of the systems has been more clearly observed and thus demonstrating the potential for scalability., The authors are very grateful with the CLEF initiative for supporting Image CLEF.The research leading to these results has received funding from the European Union’s Seventh Framework Programme (FP7/2007-2013) under the tranScriptorium project (#600707) and from the Spanish MEC under the STraDA project (TIN2012-37475-C02-01).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

On the Derivational Entropy of Left-to-Right Probabilistic Finite-State Automata and Hidden Markov Models

  • Sánchez Peiró, Joan Andreu|||0000-0003-0423-2020
  • Rocha, M. A.
  • Romero, Verónica
  • Villegas, Mauricio
[EN] Probabilistic finite-state automata are a formalism that is widely used in many problems of automatic speech recognition and natural language processing. Probabilistic finite-state automata are closely related to other finite-state models as weighted finite-state automata, word lattices, and hidden Markov models. Therefore, they share many similar properties and problems. Entropy measures of finite-state models have been investigated in the past in order to study the information capacity of these models. The derivational entropy quantifies the uncertainty that the model has about the probability distribution it represents. The derivational entropy in a finite-state automaton is computed from the probability that is accumulated in all of its individual state sequences. The computation of the entropy from a weighted finite-state automaton requires a normalized model. This article studies an efficient computation of the derivational entropy of left-to-right probabilistic finite-state automata, and it introduces an efficient algorithm for normalizing weighted finite-state automata. The efficient computation of the derivational entropy is also extended to continuous hidden Markov models., This work has been partially supported through the European Union's H2020 grant READ (Recognition and Enrichment of Archival Documents) (Ref: 674943) and the MINECO/FEDER-UE project TIN2015-70924-C2-1-R. The second author was supported by the "Division de Estudios de Posgrado e Investigacion" of Instituto Tecnologico de Leon.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Capítulo o parte de un libro (BookPart)

Page Segmentation of Structured Documents Using 2D Stochastic Context-Free Grammars

  • Álvaro Muñoz, Francisco
  • Cruz Fernández, Francisco
  • Ramos Terrades, Oriol
  • Benedí Ruiz, José Miguel
  • Sánchez Peiró, Joan Andreu|||0000-0003-0423-2020
n this paper we define a bidimensional extension of Stochastic Context-Free Grammars for page segmentation of structured documents. Two sets of text classification features are used to perform an initial classification of each zone of the page. Then, the page segmentation is obtained as the most likely hypothesis according to a grammar. This approach is compared to Conditional Random Fields and results show significant improvements in several cases. Furthermore, grammars provide a detailed segmentation that allowed a semantic evaluation which also validates this model., Work partially supported by the Spanish MEC under the STraDA research project (TIN2012-37475-C02-01), the MITTRAL (TIN2009- 14633-C03-01) project, the Spanish projects TIN2009-14633-C03-01/03 and 2010- CONES-00029, the FPU grant (AP2009-4363), by the Generalitat Valenciana under the grant Prometeo/2009/014, and through the EU 7th Framework Programme grant tranScriptorium (Ref: 600707)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Capítulo o parte de un libro (BookPart)

Word-Graph Based Applications for Handwriting Documents: Impact of Word-Graph Size on Their Performances

  • Toselli, Alejandro Héctor|||0000-0001-6955-9249
  • Vidal, Enrique|||0000-0003-4579-5196
  • Romero Gómez, Verónica
Computer Assisted Transcription of Text Images (CATTI) and Key-Word Spotting (KWS) applications aim at transcribing and indexing handwritten documents respectively. They both are approached by means of Word Graphs (WG) obtained using segmentation-free handwritten text recognition technology based on N-gram Language Models and Hidden Markov Models. A large WG contains most of the relevant information of the original text (line) image needed for CATTI and KWS but, if it is too large, the computational cost of generating and using it can become unaffordable. Conversely, if it is too small, relevant information may be lost, leading to a reduction of CATTI/KWS in performance accuracy. We study the trade-off between WG size and CATTI &KWS performance in terms of effectiveness and efficiency. Results show that small, computationally cheap WGs can be used without loosing the excellent CATTI/KWS performance achieved with huge WGs., Work partially supported by the Spanish MICINN projects STraDA (TIN2012-37475-C02-01) and by the EU 7th FP tranScriptorium project (Ref:600707).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Capítulo o parte de un libro (BookPart)

On the modification of binarization algorithms to retain grayscale information for handwritten text recognition

  • Villegas, Mauricio
  • Romero Gómez, Verónica
  • Sánchez Peiró, Joan Andreu|||0000-0003-0423-2020
[EN] The amount of digitized legacy documents has been rising over the last years due mainly to the increasing number of on-line digital libraries publishing this kind of documents. The vast majority of them remain waiting to be transcribed to provide historians and other researchers new ways of indexing, consulting and querying them. However, the performance accuracy of state-of-the-art Handwritten Text Recognition techniques decreases dramatically when they are applied to these historical documents. This is mainly due to the typical paper degradation problems. Therefore, robust pre-processing techniques is an important step for helping further recognition steps. This paper proposes to take existing binarization techniques, in order to retain their advantages, and modify them in such a way that some of the original grayscale information is preserved and be considered by the subsequent recognizer. Results are reported with the publicly available ESPOSALLES database., The research leading to these results has received funding from the European Union’s Seventh Framework Programme FP7/2007-2013) under grant agreement No. 600707 - tranScriptorium and the Spanish MEC under the STraDA project (TIN2012-37475-C02-01).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

The Impact of Visual Contextualization on UI Localization

  • Leiva, Luis A.
  • Alabau, Vicent
[EN] Translating the text in an interface is a challenging task. Besides the jargon and technical terms, many of the strings are often very short, such as those shown in buttons and pull-down menus. Then, as a result of the lack of visual context in the traditional localization process, an important ambiguity problem arises. We study three approaches to solve this problem: using plain gettext (baseline condition), using gettext plus being able to operate the UI, and translating the UI in-place. We found that translators are substantially faster with plain gettext but commit a significantly higher number of errors in comparison to the other approaches. Unexpectedly, the mixed condition was slower and more error-prone than in-place translation. The latter was found to be comparable to plain gettext in terms of time, although some strings passed unnoticed as the UI was operated. Based on our results, we arrive at a set of recommendations to augment localization tools to improve translator's productivity., This work is supported by the 7th Framework Program of the European Commision (FP7/2007-13) under grant agreements 287576 (CASMACAT) and 600707 (tranScriptorium)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Training of On-line Handwriting Text Recognizers with Synthetic Text Generated Using the Kinematic Theory of Rapid Human Movements

  • Martín-Albo Simón, Daniel
  • Plamondon, Réjean
  • Vidal, Enrique|||0000-0003-4579-5196
A method for automatic generation of synthetic handwritten words is presented which is based in the Kinematic Theory and its Sigma-lognormal model. To generate a new synthetic sample, first a real word is modelled using the Sigmalognormal model. Then the Sigma-lognormal parameters are randomly perturbed within a range, introducing human-like variations in the sample. Finally, the velocity function is recalculated taking into account the new parameters. The synthetic words are then used as training data for a Hidden Markov Model based on-line handwritten recognizer. The experimental results confirm the great potential of the Kinematic Theory of rapid human movements applied to writer adaptation., This work was partially supported by the Universitat Politècnica de València under the PMIA-2013 scholarship, the Spanish MEC under FPU scholarship AP2010-0575, the EU’s 7th Framework Programme (FP7/2007-2013) under grant agreement n. 600707 (tranScriptorium) and n. 287576 (CasMaCat) and the Natural Sciences and Engineering Research Council of Canada (NSERC) under grant RGPIN-915.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

ICFHR2014 Competition on Handwritten Text Recognition on tranScriptorium Datasets (HTRtS)

  • Sánchez Peiró, Joan Andreu|||0000-0003-0423-2020
  • Toselli, Alejandro Héctor|||0000-0001-6955-9249
  • Vidal, Enrique|||0000-0003-4579-5196
  • Romero Gómez, Verónica
A contest on Handwritten Text Recognition organised in the context of the ICFHR 2014 conference is described. Two tracks with increased freedom on the use of training data were proposed and three research groups participated in these two tracks. The handwritten images for this contest were drawn from an English data set which is currently being considered in the tranScriptorium project. The the goal of this project is to develop innovative, efficient and cost-effective solutions for the transcription of historical handwritten document images, focusing on four languages: English, Spanish, German and Dutch. For the English language, the so-called “Bentham collection” is being considered in tranScriptorium. It encompasses a large set of manuscripts written by the renowned English philosopher and reformer Jeremy Bentham (1748-1832). A small subset of this collection has been chosen for the present HTR competition. The selected subset has been written by several hands (Bentham himself and his secretaries) and entails significant varibilities and difficulties regarding the quality of text images and writting styles. Training and test data were provided in the form of carefully segmented line images, along with the corresponding transcripts. The three participants achieved very good results, with transcription word error rates ranging from 15.0% down to 8.6%., The research leading to these results has received funding from the European Union’s Seventh Framework Pro-gramme (FP7/2007-2013) under grant agreement no. 600707- tranScriptorium. The authors would like to thank all theTRANSCRIPTORIUMmembers for their collaboration and the entrants for their participation in this contest.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Capítulo o parte de un libro (BookPart)

An Image-Based Measure for Evaluation of Mathematical Expression Recognition

  • Álvaro Muñoz, Francisco
  • Benedí Ruiz, José Miguel
  • Sánchez Peiró, Joan Andreu|||0000-0003-0423-2020
Mathematical expression recognition is an active research field that is related to document image analysis and typesetting. In this study, we present a novel global performance evaluation measure for mathematical expression recognition based on image matching. Using an image representation for evaluation tries to overcome the representation ambiguity as human beings do. The results of a recent competition were used to perform several experiments in order to analyze the benefits and drawbacks of this measure., This work was partially supported by the Spanish MEC under the STraDA research project (TIN2012-37475-C02-01), the MITTRAL (TIN2009-14633-C03-01) project, the FPU grant (AP2009-4363), by the Generalitat Valenciana under the grant Prometeo/2009/014, and through the EU 7th Framework Programme grant tranScriptorium (Ref: 600707)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Structure detection and segmentation of documents using 2D stochastic context-free grammars

  • Álvaro Muñoz, Francisco
  • Cruz Fernández, Francisco
  • Ramos Terrades, Oriol
  • Benedí Ruiz, José Miguel
  • Sánchez Peiró, Joan Andreu|||0000-0003-0423-2020
[EN] In this paper we define a bidimensional extension of stochastic context-free grammars for structure detection and segmentation of images of documents. Two sets of text classification features are used to perform an initial classification of each zone of the page. Then, the document segmentation is obtained as the most likely hypothesis according to a stochastic grammar. We used a dataset of historical marriage license books to validate this approach. We also tested several inference algorithms for probabilistic graphical models and the results showed that the proposed grammatical model outperformed the other methods. Furthermore, grammars also provide the document structure along with its segmentation. & 2014 Elsevier B.V. All rights reserved., Work is partially supported by the Spanish MEC under the STraDA Research Project (TIN2012-37475-C02-01), the Spanish Project 2010-CONES-00029, the FPU Grant (AP2009-4363), and through the EU 7th Framework Programme Grant tranScriptorium (Ref: 600707).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Warped K-Means: An algorithm to cluster sequentially-distributed data

  • Leiva Torres, Luis Alberto
  • Vidal, Enrique|||0000-0003-4579-5196
[EN] Many devices generate large amounts of data that follow some sort of sequentiality, e.g., motion sensors, e-pens, eye trackers, etc. and often these data need to be compressed for classification, storage, and/or retrieval tasks. Traditional clustering algorithms can be used for this purpose, but unfortunately they do not cope with the sequential information implicitly embedded in such data. Thus, we revisit the well-known K-means algorithm and provide a general method to properly cluster sequentially-distributed data. We present Warped K-Means (WKM), a multi-purpose partitional clustering procedure that minimizes the sum of squared error criterion, while imposing a hard sequentiality constraint in the classification step. We illustrate the properties of WKM in three applications, one being the segmentation and classification of human activity. WKM outperformed five state-of- the-art clustering techniques to simplify data trajectories, achieving a recognition accuracy of near 97%, which is an improvement of around 66% over their peers. Moreover, such an improvement came with a reduction in the computational cost of more than one order of magnitude., This work has been partially supported by Casmacat (FP7-ICT-2011-7, Project 287576), tranScriptorium (FP7-ICT-2011-9, Project 600707), STraDA (MINECO, TIN2012-37475-0O2-01), and ALMPR (GVA, Prometeo/20091014) projects.