============================================================================ IAPR TC-11 Newsletter February 2015 http://www.iapr-tc11.org ========== Contents ======================================================== * Message from the Editor * Dates 'n' Deadlines - BTAS 2015, Arlington, Virginia , USA April 1 (http://www.btas2015.org/) * New and Recently Published Datasets * Call for Papers - Special Issue on Pattern Recognition at IEEE Intelligent Systems - 6th Int. Workshop on Camera Based Document Analysis and Recognition (CBDAR 2015), in conjunction with ICDAR 2015, August 22 (repost) * Announcement - DAS 2016, Santorini, Greece, April 11-14, 2016 - ICDAR 2015 Competitions: Overview * Call for Participation - ICDAR 2015 Competition HTRtS: Handwritten Text Recognition on the tranScriptorium Dataset - ICDAR'15 Smartphone Document Capture and OCR Competition (SmartDoc) - ICDAR 2015 Robust Reading Competition (repost) * Call for Dataset Submissions * Call for Contributions ============================================================================ ========== Message from the Editor ========================================= Welcome to the February of our newsletter. This edition brings to you a Call for Papers for a Special Issue on Pattern Recognition of IEEE Intelligent Systems. Furthermore, you will find below the first announcement of DAS 2016, which will be organized by Apostolos Antonacopoulos and Basilis Gatos on the beautiful island of Santorini, Greece in April 2016. This newsleter also includes an overview of the impressive number of competitions (18 competitions in 5 categories) that will be organized in conjunction with this year's ICDAR including detailed Calls for Participation for the HTRtS and SmartDoc competitions. Gernot A. Fink, IAPR TC-11 Newsletter Editor Gernot.Fink@udo.edu ============================================================================ ========== Dates 'n' Deadlines ============================================= Event/Location/Web: Event Date: Deadline (paper submission): ---------------------------------------------------------------------------- * BTAS 2015, Arlington, Virginia , USA September 8 - 11 April 1 (http://www.btas2015.org/) * ICCV 2015, Santiago, Chile December 13-16, 2015 April 30 (http://pamitc.org/iccv15/) * ICDAR 2015, Gammarath, Tunisia August 23-26, 2015 - passed - (http://2015.icdar.org/) - Doctoral Consortium: August 23 May 15 * CBDAR 2015 in conjunction with ICDAR August 22 May 15 (http://www.cvc.uab.es/CBDAR2015) * ACPR 2015, Kuala Lumpur, Malaysia November 3-6, 2015 June 1 (http://acpr2015.org/) * DAS 2015, Santorini, Greece April 11-14, 20016 TBA (http://www.primaresearch.org/das2016) * CVPR 2015, Boston, United States June 8-10, 2015 - passed - (http://www.pamitc.org/cvpr15/) ============================================================================ ========== New and Recently Published: TC-11 Datasets ====================== For a list of all datasets available visit: http://www.iapr-tc11.org/mediawiki/index.php/Datasets_List ============================================================================ ========== Call for Parpers: Special Issue on Pattern Recognition ========== Special Issue on Pattern Recognition at IEEE Intelligent Systems ---------------------------------------------------------------- Submission Deadline: 25 May 2015 Publication: November/December 2015 Pattern Recognition (PR) is one of the key abilities in human and machine intelligence, and an important branch of the more broad area of Artificial Intelligence (AI). Pattern recognition endows machines the ability of environmental perception, while cognition (including reasoning, knowledge engineering, and language understanding), is addressed by other branches of AI. PR and AI are often interwoven in intelligent systems (for example, the perceptron process exploits knowledge to solve ambiguities in recognition). The scope of Pattern Recognition includes pattern classification (statistical and structural PR, neural networks, kernel methods, ensemble methods, etc.), clustering, feature extraction and selection, data pre-processing (such as image processing and segmentation), visual object recognition, video analysis, applications in document analysis, biometrics, medical imaging, remote sensing image analysis, multimedia, video surveillance, intelligent transportation, and so on. Methods and applications have both seen tremendous advances in recent years. For example, deep learning methods have boosted performance in many fields such as handwriting recognition, facial recognition, speech recognition, traffic sign recognition, and so on. This special issue aims to report on and discuss the state of the art in pattern recognition theory and applications - particularly, new ideas, methods, and innovative applications. The topics of interest include, but are not limited to: . Cognitive mechanism and mathematical foundation of PR . Pattern classification . Feature extraction and selection . Machine learning for pattern recognition . Object detection and recognition . Image and Video analysis . Applications in document analysis, biometrics, data mining, intelligent transportation, etc. Guest Editors . Cheng-Lin Liu, Institute of Automation of Chinese Academy of Sciences, China . Brian Lovell, University of Queensland, Australia . Dacheng Tao, University of Technology Sydney, Australia . Massimo Tistarelli, University of Sassari, Italy Submission Guidelines Submissions should be 3,000 to 5,400 words (counting a standard figure or table as 200 words) and should follow IEEE Intelligent Systems style and presentation guidelines ( www.computer.org/intelligent/author). The manuscripts cannot have been published or be currently submitted for publication elsewhere. We strongly encourage submissions that include audio, video, and community content, which will be featured on the IEEE Computer Society Website along with the accepted papers. ============================================================================ ========== CBDAR 2015: Call for Papers ====================== (repost) ===== 6th Int. Workshop on Camera Based Document Analysis and Recognition ------------------------------------------------------------------- The 6th International Workshop on Camera Based Document Analysis and Recognition (CBDAR 2015) will be held in Gammarth, Tunisia, on August 22nd 2015 in conjunction with ICDAR 2015. http://www.cvc.uab.es/CBDAR2015 The pervasiveness and widespread availability of camera phones, hand-held digital still/video cameras and more recently wearable cameras have led the community to recognize camera captured images as a promising and growing field of research for document analysis and recognition. Document digitization techniques are gradually getting closer to camera based solutions, offering certain advantages (e.g. for scanning large scale or fragile documents), and presenting interesting new challenges and open problems which cannot be directly resolved by traditional techniques. Building on the success of the previous five CBDAR workshops in 2005 (Seoul, Korea), 2007 (Curitiba, Brazil), 2009 (Barcelona, Spain), 2011 (Beijing, China), and Washington DC (USA), CBDAR 2015 will be held in Gammarth, Tunisia in conjunction with ICDAR 2015. The aim of the workshop is to provide a natural link between document image analysis and the wider computer vision community by attracting cutting edge research on the topic. Topics of Interest: - camera based acquisition of written information - restoration of camera captured documents (dewarping, deblurring, etc.) - image degradation models for camera captured characters/documents - document image quality analysis - character segmentation / recognition from scene images - layout analysis for camera captured documents - text in video - document image retrieval - devices and algorithms for camera-based document analysis and recognition - device constrained techniques and algorithms - performance evaluation and metrics - applications such as translation, reading text for the blind, etc - human-document interaction Workshop Chairs: Dr Dimosthenis Karatzas (Computer Vision Centre - Spain) Dr Faisal Shafait (University of Western Australia -Australia) Program Committee: TBA Workshop Format: CBDAR is a 100% participation, one-day, single-track workshop featuring keynote talks, oral/poster presentations, a demo session, and a panel discussion. Publications: Electronic copies of the workshop proceedings containing all contributed papers will be distributed at the workshop. After the workshop, revised versions of selected papers will be published in Springer LNCS series as post-proceedings. Submission Information: CBDAR 2015 invites the submission of original, previously unpublished work and welcomes, with some restrictions, submissions which are closely related to work submitted to ICDAR 2015. This workshop employs single-blind review, in which referees remain anonymous for the authors throughout the process. Papers should not exceed 6 printed pages in IEEE CS format. Full details of the formatting instructions, a sample document and templates for LaTeX and MS-Word users will be available at the CBDAR 2015 homepage soon. Important Dates: Paper submission due: May 15, 2015 Author Notification: June 25, 2015 Camera-ready paper due: July 8, 2015 ============================================================================ ========== First Announcement: DAS 2016 ==================================== International Workshop on Document Ananlysis Systems, DAS 2016 -------------------------------------------------------------- We are pleased to announce that DAS2016 will be held on the island of Santorini in Greece between 11-14 April 2016. Put the date in your calendar and watch the workshop web site http://www.primaresearch.org/das2016 for further announcements and Call for Papers soon. Apostolos Antonacopoulos and Basilis Gatos - DAS 2016 General Chairs ============================================================================ ========== ICDAR 2015 Competitions: Overview =============================== Document Analysis Systems ------------------------- Recognition of Documents with Complex Layouts (RDCL-2015) [http://www.primaresearch.org/RDCL2015] The competition presents challenges for page segmentation, region classification, and text recognition in an end-to-end scenario. The dataset contains scanned pages from contemporary magazines and technical articles. Participants will be provided with know-how and tools that aid the development or extension of their page analysis systems. Text in Challenging Contexts ---------------------------- Robust Reading (RR-2015) [http://rrc.cvc.uab.es/] "Robust Reading" refers to the interpretation of written communication in unconstrained settings. The ICDAR 2015 Robust Reading competition will build upon the success of the previous editions and will introduce an "end-to-end" task aiming at simultaneous word localisation and recognition in scene images, born-digital images and scene videos as well as a new large dataset (in the thousands of images) on incidental scene text. Smartphone Document Capture and OCR (SmartDoc-2015) [http://l3i.univ-larochelle.fr/icdar2015smartdoc] Smartphones are replacing personal scanners. With more than 1.2 billion units sold in 2014, what was a trend is now an established use, and we all need reliable solutions for digitizing document images in a seamless way, to later search them, reuse their content, edit them, share them, and perform various other actions which we normally require on daily basis. This competition proposes 2 independant challenges in this topic: 1/ detect and segment page object in preview frames (to assist the user, and enable automated image enhancement); and 2/ extract and recognize text contained in mobile captured images (for indexation or editing purposes). Two new datasets will be released at this occasion. Text Reading in the Wild (TRW-2015) [http://icdar2015.imageplusplus.com/] We provide images annotated by tagged text lines. Example tags are "Translucent", which indicate that the text line does not have an opaque foreground color, and "Other", which include Chinese glyphs. Altogether there are four categories: Translucent English, Translucent Other, Non-Translucent English and Non-Translucent Other. Metrics are mostly compatible with 2013 ICDAR Robust Reading. Historical Documents -------------------- Historical Book Recognition (HBR-2015) [http://www.primaresearch.org/HBR2015] The competition presents challenges for page segmentation, region classification, and text recognition in an end-to-end scenario. The dataset contains scanned pages from a wide range of historical books with a variety of layouts and conditions. Participants will be provided with know-how and tools that aid the development or extension of their page analysis systems. Handwritten Text Recognition on the tranScriptorium Dataset (HTRtS-2015) [http://transcriptorium.eu/~htrcontest/] The goal of this competition is to promote the Handwriting Text Recognition in historical handwritten documents. A subset of the Bentham manuscripts researched in the tranScriptorium project will be used. It has more than 80,000 documents, most of them digitised, and more than 6,000 have been transcribed with in a crowd-sourcing initiative. In this edition of the contest, 796 images will be used. Text Line Detection in Historical Documents (ANDAR-TL-2015) [http://collections.ancestry.com/DART-2015-TextLines] Keyword Spotting for Handwritten Documents (KWS-2015) [http://transcriptorium.eu/~icdar15kws/] This competition aims to objectively compare different Keyword Spotting (KWS) approaches. In order to make the competition interesting for researchers from all backgrounds we consider: segmentation-free vs.segmentation-based, query-by-example vs. query-by-string and training-free vs. training-based systems, divided in two main tracks.All scenarios will be evaluated with the same data and metrics. Word Clustering of Segmented Historical Documents (ANDAR-WC-2015) [http://collections.ancestry.com/DART-2015-WordCluster] MultiSpectral Text Extraction Contest (MS-TEx-2015) [http://www.synchromedia.ca/competition/ICDAR/mstexicdar2015.html] The MS-TEx contest aims to promote recent development in state-of-the-art methodologies directed to segmentation and binarization of the original text on multispectral document images. The advantage of multispectral images is that they offer an opportunity to achieve better differentiation between the different document image patterns. Identification -------------- Signature Verification and Writer Identification Competitions for On- and Offline Skilled Forgeries (SigWIComp-2015) [http://www.dfki.uni-kl.de/afha2015/SigWiComp.html] Researchers and developers in the fields of signature verification and handwriting analysis are invited to participate in the SigWIComp2015. This will actually be a set of competitions with several tasks, covering different modalities (On- and Off-line), different scripts (Western and Indic), and different tasks (Signature Verification and Writer Identification). Participants are welcome to register for all, or any of the tasks they prefer. Writer Identification Competition using KHATT, AHTID/MW and IBHC Databases (WI-2015) [http://diuf.unifr.ch/diva/APTI/ICDAR2015WIComp.pdf] The scientific objectives of this competition are to measure the capacity of recognition systems to identify the writer using character, word, text-line and paragraph images. The main difficulty is probably in the similarity between the writer styles, the quality of the images as they are scanned on grey level and in the possibility to recognize the writer using one character, word, one line or one paragraph image. Multi-Script Writer Identification and Gender Classification (MS-WIGC-2015) [http://www.univ-tebessa.dz/ICDAR2015/default.htm] This competition is aimed at writer identification and gender classification from offline handwritten documents using the QUWI database. The most interesting aspect is the dataset with writing samples of the same individual in Arabic as well as English allowing not only to objectively compare different systems but also to investigate the performance of traditional script-dependent systems in a multi-script experimental setup. Specific Challenges ------------------- Handwritten CAPTCHA Evaluation Challenge (HCEC-2015) [http://www.cubs.buffalo.edu/icdar2015captchaevaluation] The two-fold objective of this competition is to evaluate the performance of our CAPTCHA generation process and to study the robustness of the current state-of-the-art handwriting recognition techniques to noise and distortion. Participants will be invited to submit their word recognition modules, where the module will be required to predict the handwritten text in the CAPTCHA images generated from the process described in our 2014 ICPR paper. Multi-Font and Multi-Size Digitally Represented Arabic Text (Arabic-2015) [http://diuf.unifr.ch/diva/APTI/competitionICDAR2015.html] The scientific objectives of this third edition are to measure the capacity of recognition systems to identify the font and the font-size using one Arabic word, and the impact of font and font-size on the text recognition performances. This will be evaluated in multi-font and multi-font contexts. The protocols will be defined to evaluate the capacity of recognition systems to handle different sizes and fonts using low-resolution images. Video Script Identification (CVSI-2015) [http://www.ict.griffith.edu.au/cvsi2015/] In multi-lingual and multi-script countries the use of two or more scripts is quite common for information communication through news and advertisement videos. The text present in videos plays an important role in automatic video indexing and retrieval, hence, OCR of multi-lingual video-text is crucial. The objective of the competition is to identify different scripts from the extracted video words. Scene Text Rectification (STR-2015) [http://ocrserv.ee.tsinghua.edu.cn/icdar2015_str/] Current rectification-related research mainly focused on document images, while distortion of natural scene text is seldom considered. Our competition tries to arouse interest of researchers and call for more scene text rectification algorithms as well as make a comparison of them. We would also provide a well-arranged generic dataset as the benchmark for later proposed methods. Text Image Super-Resolution (SR-2015) [http://liris.cnrs.fr/icdar-sr2015/] This competition aims to motivate research around Text Images Super-Resolution (SR). Simple interpolation techniques are very limited at improving OCR performance. SR approaches aim to enhance the reconstruction process by generating missing details, yielding better OCR performances. Evaluation is based on both OCR accuracy and PSNR improvement compared with a simple bicubic interpolation of the LR images. ============================================================================ ========== Call for Participation: ICDAR 2015 HTRtS Competition ============ ICDAR2015 Competition HTRtS: Handwritten Text Recognition on the tranScriptorium Dataset ----------------------------------------------------------- http://www.transcriptorium.eu/~htrcontest/ The "ICDAR2015 Competition HTRtS: Handwritten Text Recognition on the tranScriptorium Dataset" competition is organised in the framework of the ICDAR 2015 competitions by the Pattern Recognition and Human Language Technologies research centre with the collaboration of the tranScriptorium partners. This contest aims to bring together researchers working on off-line Handwritten Text Recognition (HTR) and provide them a suitable benchmark to compare their techniques on the task of transcribing typical historical handwritten documents. The first edition of this contest HTRtS2014 was organised in the ICFHR 2014. The proposed dataset consists of a series of documents from the Bentham collection, which has been prepared in the tranScriptorium project. This dataset includes manuscripts written by Jeremy Bentham (1748-1832) himself over a period of sixty years, as well as fair copies written by Bentham's secretarial staff. Handwriting in this collection is complex enough to challenge the HTR software: manuscripts written by secretarial staff will provide variety, while Bentham's manuscripts are often complicated by deletions, marginalia, interlineal additions and other features. The data used in this contest is closely related to the data used in the ICDAR2015 Competition on Keyword Spotting for Handwritten Documents (http://transcriptorium.eu/~icdar15kws/). The dataset for this competition is composed of 796 pages; most of the pages consist of a single block with many difficulties for line detection and extraction (see page samples below). The dataset is divided into 3 batches for the competition: 2 batches for training (batch 1 and batch 2) and 1 batch for test (batch 3). The number of writers is unknown (see web pages for detail). DESCRIPTION AND GOALS The systems entering this contest should try to obtain the most accurate recognition results in the test partition. The available data for batch 1 will consist of: 1. The original images of all the training pages 2. The PAGE file corresponding to each page image. For each text line in this image, the PAGE file contains a bounding polygon and the corresponding correct transcript. 3. The preprocessed and extracted line images for all the lines of the training and validation sets in grayscale (see examples below) 4. A sequence of feature vectors for each line. 5. The corresponding transcripts of each of these lines. Items 1 and 2 are redundant with items 3 and 5 and are provided for those who wish to try improving results by using specific image preprocessing and line extraction tools. Item 4 is provided for those who do not wish to try improving results at pre-processing and feature extraction level. The available data for the batch 2 will consist of: 1. The original images of all the training pages 2. The PAGE file corresponding to each page image. The PAGE file contains the bounding polygon for the text regions, not for the line regions 3. For the text regions, a separated file with the corresponding correct transcripts will be provided The test images (batch 3), with the transcript fields empty, will be eventually provided in the same (redundant) formats as first batch for evaluation purposes (see schedule below). A baseline system based on HTK hidden Markov models and SRILM language modelling will be provided, including a set of scripts to perform a basic training and test experiment (using batch 1). The participants can use this baseline system as an initial approach to their own systems, where they will be allowed to improve this baseline by changing one or several of the following steps: - page-level pre-processing and line extraction - line pre-processing and normalisation - feature extraction - recognition system and/or approach - types of character, lexical and/or language models - etc. Several submissions per participant will be allowed and all the results will be considered when presenting the competition results. In each submission, the participant must provide a brief description of the characteristics of the submitted system, emphasising the main characteristics of the submitted system. The final goal is to analyse the different proposals of the participants. EVALUATION MODALITIES The evaluation will be performed on the transcription results provided by each recognition system. The evaluation metric will be the Word Error Rate (WER) between the reference transcript and the transcript provided by the system from each line. The winner will be the system which obtains the least WER on the test set. A web-based platform will be available for the participants to check their test results. Two tracks are planned in this competition: - Restricted track: in this track the participants can use only the data provided by the organisers for training and tuning their systems - Unrestricted track: in this track the participants can use any data of their choice The baseline system will be prepared only for the restricted track. It is mandatory that the entrants participating in the "Unrestricted track" participate in the "Restricted track". The idea of this obligation is to be able to compare several systems in analogous training conditions. REGISTRATION AND ACCESS TO DATA To register in this contest send an e-mail to jandreu_AT_dsic_DOT_upv_DOT_es with the subject ICDAR 2015 HTRtS competition registration (see details in the web page). SCHEDULE - 19 Jan 2015 Competition opens, start of inscription period, training data available, baseline system available. - 31 March 2015 Registration deadline (no more participants would be admitted). - 31 March 2015 Test data available - 7 Apr 2015 Deadline for systems results - 15 Apr 2015 Deadline for sending short description of the submitted systems ORGANISERS Joan Andreu Sanchez Veronica Romero Alejandro H. Toselli Enrique Vidal Pattern Recognition and Human Language Technologies research centre Universitat Politecnica de Valencia ============================================================================ ========== Call for Participation: ICDAR 2015 HTRtS Competition ============ ICDAR'15 SMARTPHONE DOCUMENT CAPTURE AND OCR COMPETITION (SmartDoc) The sample datasets for ICDAR'15 SmartDoc have just been released. There are two challenges. For the first one you will have to detect and segment a document from 150 mobile captured videos. The goal of the second one is to extract the text from 12000 document pictures taken with a mobile phone. To make things interesting, both challenges include varying capture conditions and distorsions. We even used some very new techniques to make some of the material... You can check our facebook to learn more: https://www.facebook.com/Smartdoc2015 Feel free to visit the website http://l3i.univ-larochelle.fr/icdar2015smartdoc to get more information about the competition and its challenges. Any participation is welcome. Important dates 01 March 2015 Registration to competition close 23 March 2015 Test dataset available 01 April 2015 Deadline for participants to submit the results and description of methods. For each challenge, submit the following: i. a maximum one A4 page detailed description and ii. a maximum 200 words short description for competition report ============================================================================ ========== CfP: ICDAR 2015 Robust Reading Competition ======= (repost) ===== ICDAR 2015 Robust Reading Competition ------------------------------------- http://rrc.cvc.uab.es "Robust Reading" refers to the research area dealing with the interpretation of written communication in unconstrained settings. Robust Reading is at the meeting point between camera based document analysis and scene interpretation. The ICDAR Robust Reading Competition is organized around challenges selected to cover a wide range of real-world situations, which are in turn set up around different research tasks. The ICDAR 2015 Robust Reading competition will build upon the success of the previous editions and will introduce two key changes. First, a new "end-to-end" task is introduced aiming at simultaneous word localisation and recognition in images and videos. Second, a Challenge on incidental text is introduced based on a new large dataset (in the thousands of images), the focus of this challenge is on text that appears in the scene without the user having taken any specific prior action to cause its appearance or improve its positioning / quality in the image. Participation is welcome in any Task and Challenge in an open mode (submission of results over a provided test set). Lead Organizers: Dimosthenis Karatzas (Computer Vision Centre, Barcelona, Spain) Seiichi Uchida (Kyushu University, Fukuoka, Japan) Masakazu Iwamura (Osaka Prefecture University, Osaka, Japan) Faisal Shafait (University of Western Australia) Collaborators: Vijay Chadrasekhar (Institute for Infocomm Research, Singapore) Jiri Matas (Czech Technical University, Czech Republic) Lukas Neumann (Czech Technical University, Czech Republic) Lu Shijan (Institute for Infocomm Research, Singapore) Lluis Gomez (Computer Vision Centre, Barcelona, Spain) Suman Ghosh (Computer Vision Centre, Barcelona, Spain) Anguelos Nicolaou (Computer Vision Centre, Barcelona, Spain) Ernest Valveny (Computer Vision Centre, Barcelona, Spain) Important Dates: - Registration of interest: until 31 March - Datasets available: 28 February - Submission of results due: 31 March - Method descriptions due: 3 April - Announcement of Results: 22 August ============================================================================ ========== Call for Dataset Submissions ==================================== We would like to remind you that the TC10 and TC11 welcome contributions of new datasets or other resources related to the community. We would like to particularly encourage authors of articles that introduce new datasets, software or other material to submit such material to TC11 for hosting. Please check the TC11 site on information about how to submit datasets for archiving ( http://www.iapr-tc11.org/mediawiki/index.php/Datasets) also feel free to contact Marcus Liwicki, the TC11 dataset curator, for any doubts you might have on the process. Marcus Liwicki, TC-11 Dataset Curator liwicki@dfki.uni-kl.de ============================================================================ ========== Call for Contributions ========================================== This newsletter needs your support in order to provide useful information to the TC11 community. Therefore, please contribute relevant news by sending a short notice to the newsletter editor Gernot A. Fink . Such news could be the obvious announcements of conferences and workshops, job opportunities, reports on past conferences, book reviews, or anything that might be of interest to a wider audience involved in the construction of reading systems. ============================================================================ ========== Subscription Information ======================================== This newsletter is sent to subscribers of the IAPR TC11 mailing list. To manage your subscription, please visit the mailing list homepage at: https://www.jiscmail.ac.uk/cgi-bin/webadmin?A0=IAPR-TC11 The homepage for IAPR TC11 is http://www.iapr-tc11.org ============================================================================