toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
  Records Links
Author Anjan Dutta; Josep Llados; Umapada Pal edit   pdf
url  doi
openurl 
  Title A symbol spotting approach in graphical documents by hashing serialized graphs Type Journal Article
  Year 2013 Publication Pattern Recognition Abbreviated Journal PR  
  Volume 46 Issue 3 Pages 752-768  
  Keywords (down) Symbol spotting; Graphics recognition; Graph matching; Graph serialization; Graph factorization; Graph paths; Hashing  
  Abstract In this paper we propose a symbol spotting technique in graphical documents. Graphs are used to represent the documents and a (sub)graph matching technique is used to detect the symbols in them. We propose a graph serialization to reduce the usual computational complexity of graph matching. Serialization of graphs is performed by computing acyclic graph paths between each pair of connected nodes. Graph paths are one-dimensional structures of graphs which are less expensive in terms of computation. At the same time they enable robust localization even in the presence of noise and distortion. Indexing in large graph databases involves a computational burden as well. We propose a graph factorization approach to tackle this problem. Factorization is intended to create a unified indexed structure over the database of graphical documents. Once graph paths are extracted, the entire database of graphical documents is indexed in hash tables by locality sensitive hashing (LSH) of shape descriptors of the paths. The hashing data structure aims to execute an approximate k-NN search in a sub-linear time. We have performed detailed experiments with various datasets of line drawings and compared our method with the state-of-the-art works. The results demonstrate the effectiveness and efficiency of our technique.  
  Address  
  Corporate Author Thesis  
  Publisher Elsevier Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 0031-3203 ISBN Medium  
  Area Expedition Conference  
  Notes DAG; 600.042; 600.045; 605.203; 601.152 Approved no  
  Call Number Admin @ si @ DLP2012 Serial 2127  
Permanent link to this record
 

 
Author Thanh Ha Do; Salvatore Tabbone; Oriol Ramos Terrades edit   pdf
url  openurl
  Title Sparse representation over learned dictionary for symbol recognition Type Journal Article
  Year 2016 Publication Signal Processing Abbreviated Journal SP  
  Volume 125 Issue Pages 36-47  
  Keywords (down) Symbol Recognition; Sparse Representation; Learned Dictionary; Shape Context; Interest Points  
  Abstract In this paper we propose an original sparse vector model for symbol retrieval task. More speci cally, we apply the K-SVD algorithm for learning a visual dictionary based on symbol descriptors locally computed around interest points. Results on benchmark datasets show that the obtained sparse representation is competitive related to state-of-the-art methods. Moreover, our sparse representation is invariant to rotation and scale transforms and also robust to degraded images and distorted symbols. Thereby, the learned visual dictionary is able to represent instances of unseen classes of symbols.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes DAG; 600.061; 600.077 Approved no  
  Call Number Admin @ si @ DTR2016 Serial 2946  
Permanent link to this record
 

 
Author Partha Pratim Roy; Umapada Pal; Josep Llados edit  doi
isbn  openurl
  Title Touching Text Character Localization in Graphical Documents using SIFT Type Book Chapter
  Year 2010 Publication Graphics Recognition. Achievements, Challenges, and Evolution. 8th International Workshop, GREC 2009. Selected Papers Abbreviated Journal  
  Volume 6020 Issue Pages 199-211  
  Keywords (down) Support Vector Machine; Text Component; Graphical Line; Document Image; Scale Invariant Feature Transform  
  Abstract Interpretation of graphical document images is a challenging task as it requires proper understanding of text/graphics symbols present in such documents. Difficulties arise in graphical document recognition when text and symbol overlapped/touched. Intersection of text and symbols with graphical lines and curves occur frequently in graphical documents and hence separation of such symbols is very difficult.
Several pattern recognition and classification techniques exist to recognize isolated text/symbol. But, the touching/overlapping text and symbol recognition has not yet been dealt successfully. An interesting technique, Scale Invariant Feature Transform (SIFT), originally devised for object recognition can take care of overlapping problems. Even if SIFT features have emerged as a very powerful object descriptors, their employment in graphical documents context has not been investigated much. In this paper we present the adaptation of the SIFT approach in the context of text character localization (spotting) in graphical documents. We evaluate the applicability of this technique in such documents and discuss the scope of improvement by combining some state-of-the-art approaches.
 
  Address  
  Corporate Author Thesis  
  Publisher Springer Berlin Heidelberg Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN 0302-9743 ISBN 978-3-642-13727-3 Medium  
  Area Expedition Conference  
  Notes DAG Approved no  
  Call Number Admin @ si @ RPL2010c Serial 2408  
Permanent link to this record
 

 
Author Gemma Sanchez; Josep Llados; Enric Marti edit  url
openurl 
  Title Segmentation and analysis of linial texture in plans Type Conference Article
  Year 1997 Publication Intelligence Artificielle et Complexité. Abbreviated Journal  
  Volume Issue Pages  
  Keywords (down) Structural Texture, Voronoi, Hierarchical Clustering, String Matching.  
  Abstract The problem of texture segmentation and interpretation is one of the main concerns in the field of document analysis. Graphical documents often contain areas characterized by a structural texture whose recognition allows both the document understanding, and its storage in a more compact way. In this work, we focus on structural linial textures of regular repetition contained in plan documents. Starting from an atributed graph which represents the vectorized input image, we develop a method to segment textured areas and recognize their placement rules. We wish to emphasize that the searched textures do not follow a predefined pattern. Minimal closed loops of the input graph are computed, and then hierarchically clustered. In this hierarchical clustering, a distance function between two closed loops is defined in terms of their areas difference and boundary resemblance computed by a string matching procedure. Finally it is noted that, when the texture consists of isolated primitive elements, the same method can be used after computing a Voronoi Tesselation of the input graph.  
  Address Paris, France  
  Corporate Author Thesis  
  Publisher Place of Publication Paris Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference AERFAI  
  Notes DAG;IAM; Approved no  
  Call Number IAM @ iam @ SLM1997 Serial 1649  
Permanent link to this record
 

 
Author Jaume Gibert; Ernest Valveny; Horst Bunke edit   pdf
doi  openurl
  Title Feature Selection on Node Statistics Based Embedding of Graphs Type Journal Article
  Year 2012 Publication Pattern Recognition Letters Abbreviated Journal PRL  
  Volume 33 Issue 15 Pages 1980–1990  
  Keywords (down) Structural pattern recognition; Graph embedding; Feature ranking; PCA; Graph classification  
  Abstract Representing a graph with a feature vector is a common way of making statistical machine learning algorithms applicable to the domain of graphs. Such a transition from graphs to vectors is known as graphembedding. A key issue in graphembedding is to select a proper set of features in order to make the vectorial representation of graphs as strong and discriminative as possible. In this article, we propose features that are constructed out of frequencies of node label representatives. We first build a large set of features and then select the most discriminative ones according to different ranking criteria and feature transformation algorithms. On different classification tasks, we experimentally show that only a small significant subset of these features is needed to achieve the same classification rates as competing to state-of-the-art methods.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes DAG Approved no  
  Call Number Admin @ si @ GVB2012b Serial 1993  
Permanent link to this record
 

 
Author Jaume Gibert; Ernest Valveny; Horst Bunke edit   pdf
doi  openurl
  Title Graph Embedding in Vector Spaces by Node Attribute Statistics Type Journal Article
  Year 2012 Publication Pattern Recognition Abbreviated Journal PR  
  Volume 45 Issue 9 Pages 3072-3083  
  Keywords (down) Structural pattern recognition; Graph embedding; Data clustering; Graph classification  
  Abstract Graph-based representations are of broad use and applicability in pattern recognition. They exhibit, however, a major drawback with regards to the processing tools that are available in their domain. Graphembedding into vectorspaces is a growing field among the structural pattern recognition community which aims at providing a feature vector representation for every graph, and thus enables classical statistical learning machinery to be used on graph-based input patterns. In this work, we propose a novel embedding methodology for graphs with continuous nodeattributes and unattributed edges. The approach presented in this paper is based on statistics of the node labels and the edges between them, based on their similarity to a set of representatives. We specifically deal with an important issue of this methodology, namely, the selection of a suitable set of representatives. In an experimental evaluation, we empirically show the advantages of this novel approach in the context of different classification problems using several databases of graphs.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 0031-3203 ISBN Medium  
  Area Expedition Conference  
  Notes DAG Approved no  
  Call Number Admin @ si @ GVB2012a Serial 1992  
Permanent link to this record
 

 
Author Anjan Dutta; Hichem Sahbi edit   pdf
doi  openurl
  Title Stochastic Graphlet Embedding Type Journal Article
  Year 2018 Publication IEEE Transactions on Neural Networks and Learning Systems Abbreviated Journal TNNLS  
  Volume Issue Pages 1-14  
  Keywords (down) Stochastic graphlets; Graph embedding; Graph classification; Graph hashing; Betweenness centrality  
  Abstract Graph-based methods are known to be successful in many machine learning and pattern classification tasks. These methods consider semi-structured data as graphs where nodes correspond to primitives (parts, interest points, segments,
etc.) and edges characterize the relationships between these primitives. However, these non-vectorial graph data cannot be straightforwardly plugged into off-the-shelf machine learning algorithms without a preliminary step of – explicit/implicit –graph vectorization and embedding. This embedding process
should be resilient to intra-class graph variations while being highly discriminant. In this paper, we propose a novel high-order stochastic graphlet embedding (SGE) that maps graphs into vector spaces. Our main contribution includes a new stochastic search procedure that efficiently parses a given graph and extracts/samples unlimitedly high-order graphlets. We consider
these graphlets, with increasing orders, to model local primitives as well as their increasingly complex interactions. In order to build our graph representation, we measure the distribution of these graphlets into a given graph, using particular hash functions that efficiently assign sampled graphlets into isomorphic sets with a very low probability of collision. When
combined with maximum margin classifiers, these graphlet-based representations have positive impact on the performance of pattern comparison and recognition as corroborated through extensive experiments using standard benchmark databases.
 
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes DAG; 602.167; 602.168; 600.097; 600.121 Approved no  
  Call Number Admin @ si @ DuS2018 Serial 3225  
Permanent link to this record
 

 
Author Asma Bensalah; Pau Riba; Alicia Fornes; Josep Llados edit   pdf
openurl 
  Title Shoot less and Sketch more: An Efficient Sketch Classification via Joining Graph Neural Networks and Few-shot Learning Type Conference Article
  Year 2019 Publication 13th IAPR International Workshop on Graphics Recognition Abbreviated Journal  
  Volume Issue Pages 80-85  
  Keywords (down) Sketch classification; Convolutional Neural Network; Graph Neural Network; Few-shot learning  
  Abstract With the emergence of the touchpad devices and drawing tablets, a new era of sketching started afresh. However, the recognition of sketches is still a tough task due to the variability of the drawing styles. Moreover, in some application scenarios there is few labelled data available for training,
which imposes a limitation for deep learning architectures. In addition, in many cases there is a need to generate models able to adapt to new classes. In order to cope with these limitations, we propose a method based on few-shot learning and graph neural networks for classifying sketches aiming for an efficient neural model. We test our approach with several databases of
sketches, showing promising results.
 
  Address Sydney; Australia; September 2019  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference GREC  
  Notes DAG; 600.140; 601.302; 600.121 Approved no  
  Call Number Admin @ si @ BRF2019 Serial 3354  
Permanent link to this record
 

 
Author Jon Almazan; Alicia Fornes; Ernest Valveny edit   pdf
url  doi
openurl 
  Title A non-rigid appearance model for shape description and recognition Type Journal Article
  Year 2012 Publication Pattern Recognition Abbreviated Journal PR  
  Volume 45 Issue 9 Pages 3105--3113  
  Keywords (down) Shape recognition; Deformable models; Shape modeling; Hand-drawn recognition  
  Abstract In this paper we describe a framework to learn a model of shape variability in a set of patterns. The framework is based on the Active Appearance Model (AAM) and permits to combine shape deformations with appearance variability. We have used two modifications of the Blurred Shape Model (BSM) descriptor as basic shape and appearance features to learn the model. These modifications permit to overcome the rigidity of the original BSM, adapting it to the deformations of the shape to be represented. We have applied this framework to representation and classification of handwritten digits and symbols. We show that results of the proposed methodology outperform the original BSM approach.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 0031-3203 ISBN Medium  
  Area Expedition Conference  
  Notes DAG Approved no  
  Call Number DAG @ dag @ AFV2012 Serial 1982  
Permanent link to this record
 

 
Author Raul Gomez; Lluis Gomez; Jaume Gibert; Dimosthenis Karatzas edit   pdf
url  openurl
  Title Self-Supervised Learning from Web Data for Multimodal Retrieval Type Book Chapter
  Year 2019 Publication Multi-Modal Scene Understanding Book Abbreviated Journal  
  Volume Issue Pages 279-306  
  Keywords (down) self-supervised learning; webly supervised learning; text embeddings; multimodal retrieval; multimodal embedding  
  Abstract Self-Supervised learning from multimodal image and text data allows deep neural networks to learn powerful features with no need of human annotated data. Web and Social Media platforms provide a virtually unlimited amount of this multimodal data. In this work we propose to exploit this free available data to learn a multimodal image and text embedding, aiming to leverage the semantic knowledge learnt in the text domain and transfer it to a visual model for semantic image retrieval. We demonstrate that the proposed pipeline can learn from images with associated text without supervision and analyze the semantic structure of the learnt joint image and text embeddingspace. Weperformathoroughanalysisandperformancecomparisonoffivedifferentstateof the art text embeddings in three different benchmarks. We show that the embeddings learnt with Web and Social Media data have competitive performances over supervised methods in the text basedimageretrievaltask,andweclearlyoutperformstateoftheartintheMIRFlickrdatasetwhen training in the target data. Further, we demonstrate how semantic multimodal image retrieval can be performed using the learnt embeddings, going beyond classical instance-level retrieval problems. Finally, we present a new dataset, InstaCities1M, composed by Instagram images and their associated texts that can be used for fair comparison of image-text embeddings.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes DAG; 600.129; 601.338; 601.310 Approved no  
  Call Number Admin @ si @ GGG2019 Serial 3266  
Permanent link to this record
Select All    Deselect All
 |   | 
Details

Save Citations:
Export Records: