toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
  Records Links
Author Mohammed Al Rawi; Ernest Valveny; Dimosthenis Karatzas edit   pdf
url  doi
openurl 
  Title Can One Deep Learning Model Learn Script-Independent Multilingual Word-Spotting? Type Conference Article
  Year (down) 2019 Publication 15th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume Issue Pages 260-267  
  Keywords  
  Abstract Word spotting has gained increased attention lately as it can be used to extract textual information from handwritten documents and scene-text images. Current word spotting approaches are designed to work on a single language and/or script. Building intelligent models that learn script-independent multilingual word-spotting is challenging due to the large variability of multilingual alphabets and symbols. We used ResNet-152 and the Pyramidal Histogram of Characters (PHOC) embedding to build a one-model script-independent multilingual word-spotting and we tested it on Latin, Arabic, and Bangla (Indian) languages. The one-model we propose performs on par with the multi-model language-specific word-spotting system, and thus, reduces the number of models needed for each script and/or language.  
  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 ICDAR  
  Notes DAG; 600.129; 600.121 Approved no  
  Call Number Admin @ si @ RVK2019 Serial 3337  
Permanent link to this record
 

 
Author Nibal Nayef; Yash Patel; Michal Busta; Pinaki Nath Chowdhury; Dimosthenis Karatzas; Wafa Khlif; Jiri Matas; Umapada Pal; Jean-Christophe Burie; Cheng-lin Liu; Jean-Marc Ogier edit   pdf
url  doi
openurl 
  Title ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition — RRC-MLT-2019 Type Conference Article
  Year (down) 2019 Publication 15th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume Issue Pages 1582-1587  
  Keywords  
  Abstract With the growing cosmopolitan culture of modern cities, the need of robust Multi-Lingual scene Text (MLT) detection and recognition systems has never been more immense. With the goal to systematically benchmark and push the state-of-the-art forward, the proposed competition builds on top of the RRC-MLT-2017 with an additional end-to-end task, an additional language in the real images dataset, a large scale multi-lingual synthetic dataset to assist the training, and a baseline End-to-End recognition method. The real dataset consists of 20,000 images containing text from 10 languages. The challenge has 4 tasks covering various aspects of multi-lingual scene text: (a) text detection, (b) cropped word script classification, (c) joint text detection and script classification and (d) end-to-end detection and recognition. In total, the competition received 60 submissions from the research and industrial communities. This paper presents the dataset, the tasks and the findings of the presented RRC-MLT-2019 challenge.  
  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 ICDAR  
  Notes DAG; 600.121; 600.129 Approved no  
  Call Number Admin @ si @ NPB2019 Serial 3341  
Permanent link to this record
 

 
Author Pau Riba; Anjan Dutta; Lutz Goldmann; Alicia Fornes; Oriol Ramos Terrades; Josep Llados edit   pdf
url  doi
openurl 
  Title Table Detection in Invoice Documents by Graph Neural Networks Type Conference Article
  Year (down) 2019 Publication 15th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume Issue Pages 122-127  
  Keywords  
  Abstract Tabular structures in documents offer a complementary dimension to the raw textual data, representing logical or quantitative relationships among pieces of information. In digital mail room applications, where a large amount of
administrative documents must be processed with reasonable accuracy, the detection and interpretation of tables is crucial. Table recognition has gained interest in document image analysis, in particular in unconstrained formats (absence of rule lines, unknown information of rows and columns). In this work, we propose a graph-based approach for detecting tables in document images. Instead of using the raw content (recognized text), we make use of the location, context and content type, thus it is purely a structure perception approach, not dependent on the language and the quality of the text
reading. Our framework makes use of Graph Neural Networks (GNNs) in order to describe the local repetitive structural information of tables in invoice documents. Our proposed model has been experimentally validated in two invoice datasets and achieved encouraging results. Additionally, due to the scarcity
of benchmark datasets for this task, we have contributed to the community a novel dataset derived from the RVL-CDIP invoice data. It will be publicly released to facilitate future research.
 
  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 ICDAR  
  Notes DAG; 600.140; 601.302; 602.167; 600.121; 600.141 Approved no  
  Call Number Admin @ si @ RDG2019 Serial 3355  
Permanent link to this record
 

 
Author Raul Gomez; Ali Furkan Biten; Lluis Gomez; Jaume Gibert; Marçal Rusiñol; Dimosthenis Karatzas edit   pdf
url  doi
openurl 
  Title Selective Style Transfer for Text Type Conference Article
  Year (down) 2019 Publication 15th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume Issue Pages 805-812  
  Keywords transfer; text style transfer; data augmentation; scene text detection  
  Abstract This paper explores the possibilities of image style transfer applied to text maintaining the original transcriptions. Results on different text domains (scene text, machine printed text and handwritten text) and cross-modal results demonstrate that this is feasible, and open different research lines. Furthermore, two architectures for selective style transfer, which means
transferring style to only desired image pixels, are proposed. Finally, scene text selective style transfer is evaluated as a data augmentation technique to expand scene text detection datasets, resulting in a boost of text detectors performance. Our implementation of the described models is publicly available.
 
  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 ICDAR  
  Notes DAG; 600.129; 600.135; 601.338; 601.310; 600.121 Approved no  
  Call Number GBG2019 Serial 3265  
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 (down) 2019 Publication Multi-Modal Scene Understanding Book Abbreviated Journal  
  Volume Issue Pages 279-306  
  Keywords 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
 

 
Author Rui Zhang; Yongsheng Zhou; Qianyi Jiang; Qi Song; Nan Li; Kai Zhou; Lei Wang; Dong Wang; Minghui Liao; Mingkun Yang; Xiang Bai; Baoguang Shi; Dimosthenis Karatzas; Shijian Lu; CV Jawahar edit   pdf
url  doi
openurl 
  Title ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard Type Conference Article
  Year (down) 2019 Publication 15th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume Issue Pages 1577-1581  
  Keywords  
  Abstract Chinese scene text reading is one of the most challenging problems in computer vision and has attracted great interest. Different from English text, Chinese has more than 6000 commonly used characters and Chinesecharacters can be arranged in various layouts with numerous fonts. The Chinese signboards in street view are a good choice for Chinese scene text images since they have different backgrounds, fonts and layouts. We organized a competition called ICDAR2019-ReCTS, which mainly focuses on reading Chinese text on signboard. This report presents the final results of the competition. A large-scale dataset of 25,000 annotated signboard images, in which all the text lines and characters are annotated with locations and transcriptions, were released. Four tasks, namely character recognition, text line recognition, text line detection and end-to-end recognition were set up. Besides, considering the Chinese text ambiguity issue, we proposed a multi ground truth (multi-GT) evaluation method to make evaluation fairer. The competition started on March 1, 2019 and ended on April 30, 2019. 262 submissions from 46 teams are received. Most of the participants come from universities, research institutes, and tech companies in China. There are also some participants from the United States, Australia, Singapore, and Korea. 21 teams submit results for Task 1, 23 teams submit results for Task 2, 24 teams submit results for Task 3, and 13 teams submit results for Task 4.  
  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 ICDAR  
  Notes DAG; 600.129; 600.121 Approved no  
  Call Number Admin @ si @ LZZ2019 Serial 3335  
Permanent link to this record
 

 
Author Sounak Dey; Anguelos Nicolaou; Josep Llados; Umapada Pal edit   pdf
url  openurl
  Title Evaluation of the Effect of Improper Segmentation on Word Spotting Type Journal Article
  Year (down) 2019 Publication International Journal on Document Analysis and Recognition Abbreviated Journal IJDAR  
  Volume 22 Issue Pages 361-374  
  Keywords  
  Abstract Word spotting is an important recognition task in large-scale retrieval of document collections. In most of the cases, methods are developed and evaluated assuming perfect word segmentation. In this paper, we propose an experimental framework to quantify the goodness that word segmentation has on the performance achieved by word spotting methods in identical unbiased conditions. The framework consists of generating systematic distortions on segmentation and retrieving the original queries from the distorted dataset. We have tested our framework on several established and state-of-the-art methods using George Washington and Barcelona Marriage Datasets. The experiments done allow for an estimate of the end-to-end performance of word spotting 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; 600.097; 600.084; 600.121; 600.140; 600.129 Approved no  
  Call Number Admin @ si @ DNL2019 Serial 3455  
Permanent link to this record
 

 
Author Sounak Dey; Pau Riba; Anjan Dutta; Josep Llados; Yi-Zhe Song edit   pdf
url  doi
openurl 
  Title Doodle to Search: Practical Zero-Shot Sketch-Based Image Retrieval Type Conference Article
  Year (down) 2019 Publication IEEE Conference on Computer Vision and Pattern Recognition Abbreviated Journal  
  Volume Issue Pages 2179-2188  
  Keywords  
  Abstract In this paper, we investigate the problem of zero-shot sketch-based image retrieval (ZS-SBIR), where human sketches are used as queries to conduct retrieval of photos from unseen categories. We importantly advance prior arts by proposing a novel ZS-SBIR scenario that represents a firm step forward in its practical application. The new setting uniquely recognizes two important yet often neglected challenges of practical ZS-SBIR, (i) the large domain gap between amateur sketch and photo, and (ii) the necessity for moving towards large-scale retrieval. We first contribute to the community a novel ZS-SBIR dataset, QuickDraw-Extended, that consists of 330,000 sketches and 204,000 photos spanning across 110 categories. Highly abstract amateur human sketches are purposefully sourced to maximize the domain gap, instead of ones included in existing datasets that can often be semi-photorealistic. We then formulate a ZS-SBIR framework to jointly model sketches and photos into a common embedding space. A novel strategy to mine the mutual information among domains is specifically engineered to alleviate the domain gap. External semantic knowledge is further embedded to aid semantic transfer. We show that, rather surprisingly, retrieval performance significantly outperforms that of state-of-the-art on existing datasets that can already be achieved using a reduced version of our model. We further demonstrate the superior performance of our full model by comparing with a number of alternatives on the newly proposed dataset. The new dataset, plus all training and testing code of our model, will be publicly released to facilitate future research.  
  Address Long beach; CA; USA; June 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 CVPR  
  Notes DAG; 600.140; 600.121; 600.097 Approved no  
  Call Number Admin @ si @ DRD2019 Serial 3462  
Permanent link to this record
 

 
Author Thanh Ha Do; Oriol Ramos Terrades; Salvatore Tabbone edit  url
openurl 
  Title DSD: document sparse-based denoising algorithm Type Journal Article
  Year (down) 2019 Publication Pattern Analysis and Applications Abbreviated Journal PAA  
  Volume 22 Issue 1 Pages 177–186  
  Keywords Document denoising; Sparse representations; Sparse dictionary learning; Document degradation models  
  Abstract In this paper, we present a sparse-based denoising algorithm for scanned documents. This method can be applied to any kind of scanned documents with satisfactory results. Unlike other approaches, the proposed approach encodes noise documents through sparse representation and visual dictionary learning techniques without any prior noise model. Moreover, we propose a precision parameter estimator. Experiments on several datasets demonstrate the robustness of the proposed approach compared to the state-of-the-art methods on document denoising.  
  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; 600.097; 600.140; 600.121 Approved no  
  Call Number Admin @ si @ DRT2019 Serial 3254  
Permanent link to this record
 

 
Author Veronica Romero; Emilio Granell; Alicia Fornes; Enrique Vidal; Joan Andreu Sanchez edit   pdf
url  openurl
  Title Information Extraction in Handwritten Marriage Licenses Books Type Conference Article
  Year (down) 2019 Publication 5th International Workshop on Historical Document Imaging and Processing Abbreviated Journal  
  Volume Issue Pages 66-71  
  Keywords  
  Abstract Handwritten marriage licenses books are characterized by a simple structure of the text in the records with an evolutionary vocabulary, mainly composed of proper names that change along the time. This distinct vocabulary makes automatic transcription and semantic information extraction difficult tasks. Previous works have shown that the use of category-based language models and a Grammatical Inference technique known as MGGI can improve the accuracy of these
tasks. However, the application of the MGGI algorithm requires an a priori knowledge to label the words of the training strings, that is not always easy to obtain. In this paper we study how to automatically obtain the information required by the MGGI algorithm using a technique based on Confusion Networks. Using the resulting language model, full handwritten text recognition and information extraction experiments have been carried out with results supporting the proposed approach.
 
  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 HIP  
  Notes DAG; 600.140; 600.121 Approved no  
  Call Number Admin @ si @ RGF2019 Serial 3352  
Permanent link to this record
Select All    Deselect All
 |   | 
Details

Save Citations:
Export Records: