Quantitative Web History Methods

Total Page:16

File Type:pdf, Size:1020Kb

Quantitative Web History Methods 11 Quantitative Web History Methods Anthony Cocciolo INTRODUCTION as a decreased use of text on the web in favor of image-based content, such as video and This chapter explores how historical research photographs. I was particularly interested in questions, including research questions about what seemed like an erosion of written con- the history of the web, can be addressed tent online in favor of a form of communica- through quantitative research methods applied tion that seemed to share commonalities with to web archives. At a basic level, quantitative children’s books, where photographs were methods involve applying a variety of math- accompanied with small amounts of text. In ematical or statistical analysis on numerical seeing what looked like a movement away data. These mathematical techniques can be from the written word, I was reminded of the as simple as adding up the occurrence of work of Walter Ong who noted the tenacity of some word, to more sophisticated techniques orality, or a tendency to attempt to return to such as analysis of variance (ANOVA), which an oral culture despite the success and obvi- will be described in more depth in this chap- ous benefits of literacy (Ong, 2002). An oral ter. Through the use of web archives, quanti- culture is one without knowledge of literacy, tative methods can be used to show patterns where information, knowledge, and culture and changes over time, thus having utility in is communicated and passed down through addressing historical research questions. means other than the written word, such as In this chapter, a personal use of quantita- through oral storytelling, music, and other tive research methods with web archives will non-written means. Was the internet, with its be discussed as a way of illustrating how they newfound ability to easily stream video and can be used more broadly (Cocciolo, 2015). high-resolution imagery, allowing for Ong’s In 2014, I was interested in what I perceived return to orality? BK-SAGE-BRUGGER_MILLIGAN-180264-Chp11.indd 138 8/20/18 8:18 PM QUANTITATIVE WEB HISTORY METHODS 139 Although I realized that I could not make The aim of this chapter is to offer a starting such sweeping arguments in an academic point for historians interested in applying study – reviewers would be none too pleased – quantitative research methods to web archives I was still interested in developing a sound to answer historical research questions, using method for determining changes in the amount personal experience as an illustration. of text delivered to users over time. To study However, before the stages are discussed, this, web archives are essential because they relevant literature on using quantitative contain copies of webpages from the past. research methods with web archives will be Although some countries have extensive web introduced. archives of their national domain or other collecting areas, in the United States – which was my main study site – the most extensive web archive is the one kept by the Internet RELEVANT LITERATURE Archive that it displays through its WayBack Machine. Thus, I knew that if I was to study Using quantitative research methods with changes in the presentation of text over web- web archives may be somewhat new to histo- sites used by people in the United States, the rians. In a traditional sense, historical research web archives kept by Internet Archive would involves the close examination of textual be an essential resource. records to address historical research ques- Before I discuss how I applied web tions. The question of whether to use quanti- archives in my research, I will outline the tative or qualitative research methods is not general steps for engaging in quantitative generally directed at the historian but rather at research using web archives. Each of these the social scientist, such as the psychologist, steps will be described in more detail in the sociologist, and education researcher. following sections and will draw on this per- Quantitative and qualitative research – when sonal example. These steps are: referred to by social scientists – typically involves studying living people, which may or 1 Developing a research question – First, a research may not be the case for historians. In social question should be developed that can be science, qualitative research methods such as addressed in full or in part through web archives. interviews and focus groups are often used to Types of questions that can be explored through get at people’s understanding of something such methods will be explored, as well as those that is not well understood, such as motiva- that are better suited for other methods. 2 Securing a corpus – Second, the corpus of web tions or opinions on some topic. Quantitative archived content that provides coverage of the research can be used to study an issue or topic areas appropriate to the research question ought that may be better understood. However, there to be secured, and ways to gain access to such is greater interest in seeing how wide or gen- corpora will be discussed. eralizable a given view is. Whereas qualitative 3 Numerical translation – Third, the corpus of text research may involve analysis of data such as needs to be translated into numerical data based interview transcripts, quantitative research on the research question. may involve analysis of numerical data such 4 Analysis – Fourth, using the numerical datasets as that generated from a survey. In this paper, created in the earlier step, mathematical or ‘quantitative research’ is used to refer to per- statistical analysis techniques can be employed. forming analysis using numerical and statisti- This can be as simple as mathematical functions such as summation, average, standard deviation, cal techniques on data, specifically web to more complex analysis, including statistical archives. While this method may not be com- techniques such as analysis of variance (ANOVA). monly used by historians, it can be used to 5 Drawing conclusions – Fifth, like all research, con- help address historical research questions in clusions should be drawn based on the analysis. conjunction with other sources of evidence. BK-SAGE-BRUGGER_MILLIGAN-180264-Chp11.indd 139 8/20/18 8:18 PM 140 THE SAGE HANDBOOK OF WEB HISTORY Studying webpages and web-based phe- opportunities for historical and longitudinal nomena using quantitative methods is not analysis are increasingly possible. new as it is captured in the research subfield In the field of communication and media of information science known as webomet- studies, researchers have begun to use web rics. According to Thelwall and Vaughan, archives to create web histories, which ‘Webometrics encompasses all quantitative Brügger defines as ‘a necessary condition studies of web-related phenomenon’ (2004: for the understanding of the Internet of the 1213). Thelwall (2009) notes that webomet- present as well as of new, emerging Internet rics can be used for studying a variety of web- forms’ (2011: 24). Web histories can include based phenomena, such as issues relating to studies of multiple facets of the web, such as election websites, online academic commu- national domains, which may look at factors nication, bloggers as amateur journalists, and such as volume, space, structure, content, social networking. The methods can be used among others (Brügger, 2014). for understanding aspects like web impact assessment, citation impact, trend detec- tion, and search engine optimization, among other possible uses. Webometrics grows out STAge 1 – DEVELOPING A RESEARCH of the subfield of information science known QUESTION OR QUESTIONS as bibliometrics, which uses quantitative analysis to make measurements related to Before progressing further, I must make a published books and articles, such as citation quick note on language used in this article as analysis to determine impact. Related sub- it varies to some degree by country. By fields include infometrics, which is the quan- ‘homepage’, I am referring to the start page titative study of information and can combine or initial page of a website. I also use the analysis of information in whatever form it term website, which refers to an entire col- may occur. lection of webpages under a given domain. Björneborn and Ingwersen (2004) high- For example, the website ‘pepsi.com’ is light four main areas of webometric research: composed of a homepage and other web- 1) webpage content analysis; 2) web link pages that are hyperlinked together to form structure analysis; 3) web usage analysis; and the website. 4) web technology analysis. Notably missing When engaging in quantitative research from this list is a longitudinal or time-based using web archives, it is necessary to have dimension. However, webometrics research- a research question that lends itself to such ers highlight the possibilities opened up by methods. For my project mentioned in the web archives. Björneborn and Ingwersen introduction, my research questions are the highlight that ‘Web archaeology… could following: in this webometric context be important for recovering historical Web developments, for Is the use of text on the World Wide Web declin- ing? If so, when did it start declining, and by how example, by means of the Internet Archive much has it declined? (www.archive.org)’ (2004: 1217). When webometrics was in its early development in The above research questions are well suited the 2000s, web archives such as the Internet for quantitative methods using web archives. Archive only contained a few years of con- The first reason why is that the question is tent, making them less appealing for long- essentially quantitative in nature: a ‘decline’ term, longitudinal analysis. However, as web and by ‘how much’ is something that can be archives have persisted, and notable web readily measured numerically by comparing archives such as the Internet Archive have data from some specific year in the past and surpassed 20 years of crawling websites, new measuring it against a more recent year.
Recommended publications
  • KYC) Platform
    Design and Prototypical Implementation of an Open Source and Smart Contract-based Know Your Customer (KYC) Platform Sebastian Emmanuel Allemann Zurich, Switzerland Student ID: 14-721-807 – Communication Systems Group, Prof. Dr. Burkhard Stiller HESIS T Supervisor: Sina Rafati, Eder John Scheid ACHELOR Date of Submission: January 31, 2019 B University of Zurich Department of Informatics (IFI) Binzmühlestrasse 14, CH-8050 Zurich, Switzerland ifi Bachelor Thesis Communication Systems Group (CSG) Department of Informatics (IFI) University of Zurich Binzmühlestrasse 14, CH-8050 Zurich, Switzerland URL: http://www.csg.uzh.ch/ Zusammenfassung Fur¨ Finanzinstitutionen ist es eine Notwendigkeit, ihre Kunden zu kennen. Know Your Customer (KYC) Prozesse wurden zu diesem Zweck entwickelt. Mit der Zunahme der Blockchain Technologie, wird es immer wichtiger die Identit¨aten von Personen best¨atigen zu k¨onnen, da man nur der Technologie, ohne kontrollierende Drittpartei, vertraut. Perso- nen mussen¨ bei jeder Bank, mit welcher sie eine Gesch¨aftsbeziehung aufnehmen m¨ochten, aufs Neue einen KYC Prozess durchlaufen. Dies ist wenig effizient und kostet viel Zeit und Geld. Es sollte daher m¨oglich sein, eine Plattform aufzubauen, welche KYC Prozesse als Dienstleistung anbietet. Diese k¨onnte durch Smart Contracts identifizierte Personen best¨atigen und dadurch die Effizienz steigern. Das Ziel dieser Arbeit ist es, ein solches System in Form eines Prototypen zu entwickeln. Der Video Identifikationsprozess ist von der Eidgen¨ossischen Finanzmarktaufsicht FINMA reguliert und definiert die Anforderungen, die zu berucksichtigen¨ sind. Das Resultat des Identifikationsprozesses liefert einen Beweis fur¨ die Identit¨at in Form eines einzigartigen Schlussels.¨ Zus¨atzlich verarbeitet ein erfolgreich entwickelter Smart Contract alle Anfra- gen von externen Plattformen, die den soeben genannten Schlussel¨ verifizieren m¨ochten, wenn ein Kunde sich mit dem Schlussel¨ registriert.
    [Show full text]
  • Technological Advances in Corpus Sampling Methodology
    Technological Advances in Corpus Sampling Methodology Stephen Michael Wattam, BSc (Hons), MRes Mathematics and Statistics School of Computing and Communications Lancaster University Submitted for the degree of Doctor of Philosophy August 2015 Abstract Current efforts in corpus linguistics and natural language processing make heavy use of corpora— large language samples that are intended to describe a wide population of language users. The first modern corpora were manually constructed, transcribed from published texts and other non-digital sources into a machine-readable format. In part due to their hard-won nature, larger corpora have become widely shared and re-used: this has significant benefits for the scientific community, yet also leads to a stagnation of sampling methods and designs. The rise of Web as Corpus (WaC), and the use of computers to author documents, has provided us with the tools needed to build corpora automatically, or with little supervision. This offers an avenue to re-examine and, in places, exceed the limitations of conventional corpus sampling methods. Even so, many corpora are compared against conventional ones due to their status as a de-facto gold standard of representativeness. Such practices place undue trust in aging sample designs and the expert opinion therein. In this thesis I argue for the development of new sampling procedures guided less by concepts of linguistic balance and more by statistical sampling theory. This is done by presenting three different areas of potential study, along with exploratory results and publicly-available tools and methods that allow for further investigation. The first of these is an examination of temporal bias in sampling online.
    [Show full text]
  • STEFANN: Scene Text Editor Using Font Adaptive Neural Network
    STEFANN: Scene Text Editor using Font Adaptive Neural Network Prasun Roy1∗, Saumik Bhattacharya2∗, Subhankar Ghosh1∗, and Umapada Pal1 1Indian Statistical Institute, Kolkata, India 2Indian Institute of Technology, Kharagpur, India https://prasunroy.github.io/stefann Abstract Textual information in a captured scene plays an im- portant role in scene interpretation and decision making. Though there exist methods that can successfully detect and interpret complex text regions present in a scene, to the best of our knowledge, there is no significant prior work that aims to modify the textual information in an image. The ability to edit text directly on images has several advan- tages including error correction, text restoration and image reusability. In this paper, we propose a method to modify text in an image at character-level. We approach the prob- lem in two stages. At first, the unobserved character (tar- get) is generated from an observed character (source) be- ing modified. We propose two different neural network ar- chitectures – (a) FANnet to achieve structural consistency (a) (b) with source font and (b) Colornet to preserve source color. Figure 1. Examples of text editing using STEFANN: (a) Original Next, we replace the source character with the generated images from ICDAR dataset; (b) Edited images. It can be ob- character maintaining both geometric and visual consis- served that STEFANN can edit multiple characters in a word (top tency with neighboring characters. Our method works as row) as well as an entire word (bottom row) in a text region. a unified platform for modifying text in images. We present the effectiveness of our method on COCO-Text and ICDAR the conventional text editors.
    [Show full text]
  • OSINT Handbook September 2020
    OPEN SOURCE INTELLIGENCE TOOLS AND RESOURCES HANDBOOK 2020 OPEN SOURCE INTELLIGENCE TOOLS AND RESOURCES HANDBOOK 2020 Aleksandra Bielska Noa Rebecca Kurz, Yves Baumgartner, Vytenis Benetis 2 Foreword I am delighted to share with you the 2020 edition of the OSINT Tools and Resources Handbook. Once again, the Handbook has been revised and updated to reflect the evolution of this discipline, and the many strategic, operational and technical challenges OSINT practitioners have to grapple with. Given the speed of change on the web, some might question the wisdom of pulling together such a resource. What’s wrong with the Top 10 tools, or the Top 100? There are only so many resources one can bookmark after all. Such arguments are not without merit. My fear, however, is that they are also shortsighted. I offer four reasons why. To begin, a shortlist betrays the widening spectrum of OSINT practice. Whereas OSINT was once the preserve of analysts working in national security, it now embraces a growing class of professionals in fields as diverse as journalism, cybersecurity, investment research, crisis management and human rights. A limited toolkit can never satisfy all of these constituencies. Second, a good OSINT practitioner is someone who is comfortable working with different tools, sources and collection strategies. The temptation toward narrow specialisation in OSINT is one that has to be resisted. Why? Because no research task is ever as tidy as the customer’s requirements are likely to suggest. Third, is the inevitable realisation that good tool awareness is equivalent to good source awareness. Indeed, the right tool can determine whether you harvest the right information.
    [Show full text]
  • Business Intelligence Resources 2018
    Business Intelligence Resources 2018 By Marcus P. Zillman, M.S., A.M.H.A. Executive Director – Virtual Private Library [email protected] Business Intelligence Resources 2018 on the Internet is a comprehensive listing of business intelligence (BI) resources and sites on the Internet. The below list of sources is taken from my Subject Tracer™ Information Blog titled Business Intelligence Resources and is constantly updated with Subject Tracer™ bots at the following URL: http://www.BIResources.info/ These resources and sources will help you to discover the many pathways available to you through the Internet to find the latest business intelligence resources and sites. Figure 1: Business Intelligence Resources 2018 Subject Tracer™ Information Blog 1 [Updated: June 1, 2018] Business Intelligence Resources 2018 White Paper Link Compilation http://www.BIResources.info/ [email protected] eVoice: 800-858-1462 © 2005, 2006 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016. 2017, 2018 Marcus P. Zillman, M.S., A.M.H.A. Business Intelligence Resources 2018: 7-Zip - File Archiver With a High Compression Ratio http://7-zip.org/ 12Manage - The Executive Fast Track https://www.12manage.com/ 20+ Free VPN's Rated Side By Side 2018 List by Paul Bischoff https://www.comparitech.com/blog/vpn-privacy/free-vpn/ 40 Top Open Source and Free Business Intelligence Software http://www.predictiveanalyticstoday.com/open-source-free-business-intelligence- solutions/ 101+ Open Source Intelligence (OSINT) Resources for Investigators
    [Show full text]
  • The Web Is for Reading? the Rise and Fall of Text on the Web Anthony Cocciolo ABSTRACT Introduction. This Study Looks to Addres
    The Web is for Reading? The Rise and Fall of Text on the Web Anthony Cocciolo ABSTRACT Introduction. This study looks to address the research questions: Is the use of text on the World Wide Web declining? If so, when did it start declining, and by how much has it declined? Method. Web pages are downloaded from the Internet Archive for the years 1999, 2002, 2005, 2008, 2011 and 2014, producing 600 captures for 100 prominent and popular webpages in the United States from a variety of sectors. Analysis. Captured webpages were analysed to uncover if the amount of text they present to users has declined over the past fifteen years using a computer vision algorithm, which deciphers text from non-text. Percentage of text per webpage is computed as well mean percentage of text per year, and a one-way ANOVA is used to uncover if the percentage of text on webpages is reliant on the year the website was produced. Results. Results reveal that the percentage of text on webpages climbed from the late 1990s to 2005 where it peaked (with 32.4% of the webpage), and has been on the decline ever since. Websites in 2014 have 5.5% less text than 2005 on average, or 26.9% text. This is more text than in the late 1990s, with webpages having only 22.4% text. Conclusion. Because of reduction in text lengths, the World Wide Web is becoming a less likely place where extensive reading will occur. The value of this study is that it confirms using a systematic approach what many have observed anecdotally: that the amount of text on webpages is decreasing.
    [Show full text]
  • 100 Tech Hacks [PDF]
    100 Tech Hacks Full details with images at http://carlcheo.com/tech-life-hacks. 1. Need to jot down something quickly? Open a temporary notepad in your browser by typing data:text/html, <html contenteditable> into the address bar. 2. Ambient music to boost your productivity. http://www.rainymood.com/ http://endlessvideo.com/watch?v=HMnrl0t md3k http://endlessvideo.com/watch?v=DIx3aM RDUL4 https://coffitivity.com/ (optional) 3. At website login pages, you can view masked passwords by changing the password input type as text. 4. Test battery easily by dropping it few inches from the ground. A fully charged battery bounces very https://www.youtube.com/watch?v=nwfFB little, whereas a dead battery bounces around. UVxpac 5. Broken keyboard feet? Replace them with binder clips. 6. Find expensive stuff for cheap on Craigslist using the following search terms: divorce, wife, husband, new baby, pcs, Kia, health, surgery, moving 7. In Windows, create a new folder and name it Control Panel Shortcuts.{ed7ba470-8e54-465e-825c- 99712043e01c}. Access any control settings in the folder. 8. In Chrome, go to Settings -> Extensions -> Allow Adblock Plus in incognito 9. Goo gle [food] vs [food] to compare nutritional values. 10. Use wall hooks to attach iPad to the wall. http://cdn4.carlcheo.com/wp- content/uploads/2015/05/Wall-mount- iPad.jpg 11. Amplify iPad speaker with tennis ball. http://cdn4.carlcheo.com/wp- content/uploads/2015/05/Amplify-iPad- speaker-with-tennis-ball.jpg 12. On calculator, the C (clear) button is to clear all entry, whereas the CE (clear entry) button is to clear the most recent entry only.
    [Show full text]
  • The Rise and Fall of Text on the Web: a Quantitative Study of Web Archives
    Forthcoming in Information Research 1 The Rise and Fall of Text on the Web: A Quantitative Study of Web Archives Anthony Cocciolo Pratt Institute School of Information and Library Science ABSTRACT Introduction. This study looks to address the research questions: Is the use of text on the World Wide Web declining? If so, when did it start declining, and by how much has it declined? Method. Web pages are downloaded from the Internet Archive for the years 1999, 2002, 2005, 2008, 2011 and 2014, producing 600 captures for 100 prominent and popular webpages in the United States from a variety of sectors. Analysis. Captured webpages were analysed to uncover if the percentage of text they present to users has declined over the past fifteen years using a computer vision algorithm, which deciphers text from non-text. Percentage of text per webpage is computed as well mean percentage of text per year, and a one-way ANOVA is used to uncover if the percentage of text on webpages is reliant on the year the website was produced. Results. Results reveal that the percentage of text on webpages climbed from the late 1990s to 2005 where it peaked (with 32.4% of the webpage), and has been on the decline ever since. Websites in 2014 have 5.5% less text than 2005 on average, or 26.9% text. This is more text than in the late 1990s, with webpages having only 22.4% text. Conclusion. The value of this study is that it confirms using a systematic approach what many have observed anecdotally: that the percentage of text on webpages is decreasing.
    [Show full text]
  • Tandem 2.0: Image and Text Data Generation Application
    City University of New York (CUNY) CUNY Academic Works All Dissertations, Theses, and Capstone Projects Dissertations, Theses, and Capstone Projects 2-2017 Tandem 2.0: Image and Text Data Generation Application Christopher J. Vitale The Graduate Center, City University of New York How does access to this work benefit ou?y Let us know! More information about this work at: https://academicworks.cuny.edu/gc_etds/1870 Discover additional works at: https://academicworks.cuny.edu This work is made publicly available by the City University of New York (CUNY). Contact: [email protected] TANDEM 2.0: IMAGE AND TEXT DATA GENERATION APPLICATION by CHRISTOPHER VITALE A capstone project submitted to the Graduate Faculty in Liberal Studies in partial fulfillment of the requirements for the degree of Master of Arts, The City University of New York. 2017 © 2017 CHRISTOPHER VITALE All Rights Reserved TANDEM 2.0: Image and Text Data Generation Application: A Case Study by Christopher Vitale ii This manuscript has been read and accepted for the Graduate Faculty in Liberal Studies in satisfaction of the thesis requirement for the degree of Master of Arts. ____________________ ______________________________ Date Dr. Matthew K. Gold Thesis Advisor ____________________ ______________________________ Date Dr. Elizabeth Macaulay-Lewis Acting Executive Officer THE CITY UNIVERSITY OF NEW YORK iii ABSTRACT TANDEM 2.0: Image and Text Data Generation Application: A Case Study by Christopher Vitale Advisor: Dr. Matthew Gold First created as part of the Digital Humanities Praxis course in the spring of 2012 at the CUNY Graduate Center, Tandem explores the generation of datasets comprised of text and image data by leveraging Optical Character Recognition (OCR), Natural Language Processing (NLP) and Computer Vision (CV).
    [Show full text]
  • Megabyteact-GSA-2016.Pdf
    This document is made available through the declassification efforts and research of John Greenewald, Jr., creator of: The Black Vault The Black Vault is the largest online Freedom of Information Act (FOIA) document clearinghouse in the world. The research efforts here are responsible for the declassification of hundreds of thousands of pages released by the U.S. Government & Military. Discover the Truth at: http://www.theblackvault.com Office of Administrative Services Freedom of Information Act Office December 8, 2016 Mr. John Greenewald The Black Vault Dear Mr. Greenewald: This letter is in response to your U.S. General Services Administration Freedom of Information Act (FOIA) request, (GSA-2017-000141), submitted on November 7, 2016, in which you requested: “Records pertaining to a copy of records, electronic or otherwise, of the most recent inventory of software licenses at your agency.” Enclosed please find the records responsive to your request. You should find the following file named 20161101-Summary Report.csv. This completes our action on this request. Should you have any press-related questions, please contact Ashley Nash-Hahn, GSA Press Secretary, by email at [email protected]. You may also contact the GSA FOIA Public Liaison, Audrey Brooks, at (202) 205-5912 or by email at [email protected] for any additional assistance and to discuss any aspect of your FOIA request. Sincerely, Travis Lewis Program Manager Enclosure U.S General Services Administration 1800 F. Street, Northwest Washington, DC 20405 Telephone: (202) 501-0800
    [Show full text]
  • Open Source Intelligence Tools and Resources Handbook 2020
    OPEN SOURCE INTELLIGENCE TOOLS AND RESOURCES HANDBOOK 2020 OPEN SOURCE INTELLIGENCE TOOLS AND RESOURCES HANDBOOK 2020 Aleksandra Bielska Noa Rebecca Kurz, Yves Baumgartner, Vytenis Benetis 2 Foreword I am delighted to share with you the 2020 edition of the OSINT Tools and Resources Handbook. Once again, the Handbook has been revised and updated to reflect the evolution of this discipline, and the many strategic, operational and technical challenges OSINT practitioners have to grapple with. Given the speed of change on the web, some might question the wisdom of pulling together such a resource. What’s wrong with the Top 10 tools, or the Top 100? There are only so many resources one can bookmark after all. Such arguments are not without merit. My fear, however, is that they are also shortsighted. I offer four reasons why. To begin, a shortlist betrays the widening spectrum of OSINT practice. Whereas OSINT was once the preserve of analysts working in national security, it now embraces a growing class of professionals in fields as diverse as journalism, cybersecurity, investment research, crisis management and human rights. A limited toolkit can never satisfy all of these constituencies. Second, a good OSINT practitioner is someone who is comfortable working with different tools, sources and collection strategies. The temptation toward narrow specialisation in OSINT is one that has to be resisted. Why? Because no research task is ever as tidy as the customer’s requirements are likely to suggest. Third, is the inevitable realisation that good tool awareness is equivalent to good source awareness. Indeed, the right tool can determine whether you harvest the right information.
    [Show full text]
  • STEFANN: Scene Text Editor Using Font Adaptive Neural Network
    STEFANN: Scene Text Editor using Font Adaptive Neural Network Prasun Roy1∗, Saumik Bhattacharya2∗, Subhankar Ghosh1∗, and Umapada Pal1 1Indian Statistical Institute, Kolkata, India 2Indian Institute of Technology, Kharagpur, India https://prasunroy.github.io/stefann Abstract Textual information in a captured scene plays an im- portant role in scene interpretation and decision making. Though there exist methods that can successfully detect and interpret complex text regions present in a scene, to the best of our knowledge, there is no significant prior work that aims to modify the textual information in an image. The ability to edit text directly on images has several advan- tages including error correction, text restoration and image reusability. In this paper, we propose a method to modify text in an image at character-level. We approach the prob- lem in two stages. At first, the unobserved character (tar- get) is generated from an observed character (source) be- ing modified. We propose two different neural network ar- chitectures – (a) FANnet to achieve structural consistency (a) (b) with source font and (b) Colornet to preserve source color. Figure 1. Examples of text editing using STEFANN: (a) Original Next, we replace the source character with the generated images from ICDAR dataset; (b) Edited images. It can be ob- character maintaining both geometric and visual consis- served that STEFANN can edit multiple characters in a word (top tency with neighboring characters. Our method works as row) as well as an entire word (bottom row) in a text region. a unified platform for modifying text in images. We present the effectiveness of our method on COCO-Text and ICDAR the conventional text editors.
    [Show full text]