ICFHR 2018
The 16th International Conference on
Frontiers in Handwriting Recognition

August 5 - 8, 2018   ●   Niagara Falls, USA

-Home -Register -Dates -Travel -Organization -Program

-Keynotes    -Talks    -Posters   -Tutorials   -Competitions
-Other Sessions    -Instructions for Presenters

Program

- Keynote Talks -

Deciphering Historical Manuscripts
Speaker: Kevin Knight

Session Chair: Venu Govindaraju

Abstract. European libraries and archives are filled with enciphered manuscripts from the early modern period. These include military and diplomatic correspondence, records of secret societies, private letters, and so on. Even though they are enciphered with older cryptographic methods, their contents are still unavailable to working historians. In this talk, we will describe such manuscripts and show how computer algorithms can help decipher them, both from digital transcriptions and from raw pixel images.

Short Biography. Kevin Knight is Dean's Professor of Computer Science at the University of Southern California (USC) and Chief Scientist for Natural Language Processing at Didi Chuxing. He is best known for his contributions to statistical machine translation, natural language generation, automata theory, and decipherment of historical manuscripts. Prof. Knight is a Fellow of ACL, AAAI, and ISI.
-Detailed Bio

 

Putting it all together: Partial Understanding, Intellectual Transformation and Cultural Evolution
Speaker: Gregory R. Crane

Session Chair: R. Manmatha

Abstract. Human society now interacts in real time on a global scale and the intensity of that interaction is only accelerating. We need to understand cultural practices whose roots evolved over thousands of years and in more languages than any human being can study, much less master. The response to this is to reimagine philology in a digital age, where philology essentially describes the application of all available methods to understanding the linguistic record of humanity. This talk considers how handwriting recognition fits within the larger framework of philology in general as well as how hybrid learning, involving machines as well as citizen scientists, redefines the goals, scope and importance of philology as an instrument to advance human culture.

Short Biography. Gregory R. Crane is the Alexander von Humboldt Professor of Digital Humanities at the University of Leipzig and Winnick Family Chair of Technology and Entrepeneurship at Tufts University. Greg owes his reputation as a pioneer of digital humanities to his development of the Perseus Digital Library, a comprehensive, freely accessible online library for antique source material. He has received, among other awards, the Google Digital Humanities Award 2010 for his work in the field.
-Detailed Bio

- Oral Sessions -

Monday, August 6th

Oral Session 1: Document Segmentation and Understanding
Session Chair: Umapada Pal
23  A CNN-based Approach to Detecting Text from Images of Whiteboards and Handwritten Notes
 Wei Jia, Lei Sun, Zhuoyao Zhong and Qiang Huo
34  dhSegment: A generic deep-learning approach for document segmentation
 Sofia Ares Oliveira, Benoit Seguin and Frederic Kaplan
80  Character and Text Recognition of Khmer Historical Palm Leaf Manuscripts
 Dona Valy, Michel Verleysen, Sophea Chhun and Jean-Christophe Burie
123  Automated Detection of Handwritten Whiteboard Content on Lecture Videos for Summarization
 Bhargava Urala Kota, Kenny Davila, Alexander Stone, Srirangaraj Setlur and Venu Govindaraju
142  Recognizing Challenging Handwritten Annotations with Fully Convolutional Networks
 Andreas Kölsch, Ashutosh Mishra, Saurabh Varshneya and Marcus Liwicki

Oral Session 2: Word/Object Spotting
Session Chair: Cheng-Lin Liu
45  Towards Spotting and Recognition of Handwritten Documents in Indic Scripts
 Kartik Dutta, Praveen Krishnan, Minesh Mathew and C V Jawahar
68  A Probabilistic Retrieval Model for Word Spotting based on Direct Attribute Prediction
 Eugen Rusakov, Leonard Rothacker, Hyunho Mo and Gernot Fink
115  Probabilistic Indexing and Search for Information Extraction on Handwritten German Parish Records
 Eva Lang, Joan Puigcerver, Alejandro Toselli and Enrique Vidal
124  Visual Search Engine for Handwritten and Typeset Math in Lecture Videos and LaTeX Notes
 Kenny Davila and Richard Zanibbi

Oral Session 3: Data Augmentation
Session Chair: Jean-Marc Ogier
60  Distilling GRU with Data Augmentation for Unconstrained Handwritten Text Recognition
 Manfei Liu, Zecheng Xie, Yaoxiong Huang, Lianwen Jin and Weiying Zhou
75  Memory-Augmented Attention Model for Scene Text Recognition
 Cong Wang, Fei Yin and Cheng-Lin Liu
81  Generating Handwritten Character Clones from an Incomplete Seed Character Set using Collaborative Filtering
 Kazuaki Nakamura, Eiji Miyazaki, Naoko Nitta and Noboru Babaguchi
106  Training an End-to-end Model for Offline Handwritten Japanese Text Recognition by Generated Synthetic Patterns
 Nam Tuan Ly, Cuong Tuan Nguyen and Masaki Nakagawa

Tuesday, August 7th

Oral Session 4: CNNs for Handwriting Recognition
Session Chair: Christian Viard-Gaudin
1  Improving CNN-RNN Hybrid Networks for Handwriting Recognition
 Kartik Dutta, Praveen Krishnan, Minesh Mathew and C V Jawahar
42  Fully Convolutional Networks for Handwriting Recognition
 Felipe Petroski Such, Dheeraj Kumar Peri, Frank Brockler, Paul Hutkowski and Raymond Ptucha
70  Introducing Local Distance-based Features to Temporal Convolutional Neural Networks
 Brian Kenji Iwana, Minoru Mori, Akisato Kimura and Seiichi Uchida
104  Discovering Class-wise Trends of Max-pooling in Subspace
 Yuchen Zheng, Brian Kenji Iwana and Seiichi Uchida

Oral Session 5: Recurrent Neural Networks for Character Recognition
Session Chair: Srirangaraj Setlur
76  DenseRAN for Offline Handwritten Chinese Character Recognition
 Wenchao Wang, Jianshu Zhang, Jun Du, Zi-Rui Wang and Yixing Zhu
99  Accelerating and Compressing LSTM based Model for Online Handwritten Chinese Character Recognition
 Yafeng Yang, Kaihuan Liang, Xuefeng Xiao, Zecheng Xie, Lianwen Jin, Jun Sun and Weiying Zhou
118  From HMMs to RNNs: Computer-assited Transcription of a Handwritten Notarial Records Collection
 Lorenzo Quirós, Vicente Bosch, Lluis Serrano, Alejandro Toselli and Enrique Vidal
120  Transcription Free LSTM OCR-Model Evaluation
 Martin Jenckel, Syed Saqib Bukhari and Andreas Dengel
122  Boosting the deep multidimensional long-short-term memory network for handwritten recognition systems
 Dayvid Castro, Byron L. D. Bezerra and Mêuser Valença

Wednesday, August 8th

Oral Session 6: Transfer Learning
Session Chair: Gernot Fink
8  Language Model Supervision for Handwriting Recognition Model Adaptation
 Christopher Tensmeyer, Curtis Wigington, Brian Davis, Seth Stewart, Tony Martinez and William Barrett
22  Building Compact CNN-DBLSTM based Character Models for Handwriting Recognition and OCR by Teacher-Student Learning
 Haisong Ding, Kai Chen, Wenping Hu, Meng Cai and Qiang Huo
54  Parsimonious HMMs for Offline Handwritten Chinese Text Recognition
 Wenchao Wang, Jun Du and Zi-Rui Wang
69  Deep Transfer Mapping for Unsupervised Writer Adaptation
 Hong-Ming Yang, Xu-Yao Zhang, Fei Yin, Jun Sun and Cheng-Lin Liu

Oral Session 7: Signature/Writer Verification
Session Chair: Michael Blumenstein
24  Robotic Arm Motion for Verifying Signatures
 Moises Diaz, Miguel Ferrer and Jose J. Quintana
25  Offline Signature Verification via Structural Methods: Graph Edit Distance and Inkball Models
 Paul Maergner, Nicholas R. Howe, Kaspar Riesen, Rolf Ingold and Andreas Fischer
58  Histogram-based matching of GMM encoded features for online signature verification
 Suresh Sundaram and Abhishek Sharma
65  Learning Discriminative Feature Hierarchies for Off-line Signature Verification
 Songxuan Lai and Lianwen Jin
77  Writer verification using CNN feature extraction
 Jun Chu, Mohammad Abuzar Shaikh, Mihir Chauhan, Lu Meng and Sargur Srihari
79  Hybrid Feature Learning for Handwriting Comparison
 Mohammad Abuzar Shaikh, Mihir Chauhan, Jun Chu and Sargur Srihari

- Poster Sessions -

Poster Session 1 - Monday, August 6th


Session Chairs: Elisa Barney-Smith and Shivakumara Palaiahnakote
18  Recognition of Chinese Text in Historical Documents with Page-Level Annotations
 Hailin Yang and Lianwen Jin
26  Rotation-free Handwritten Chinese Character Recognition Using Two-stage Convolutional Neural Network
 Zhe Li, Lianwen Jin and Songxuan Lai
28  Learning Features for Writer Retrieval and Identification using Triplet CNNs
 Manuel Keglevic and Stefan Fiel
30  Matching Table Structures of Historical Register Books using Association Graphs
 Florian Kleber, Markus Diem, Herve Dejean, Jean-Luc Meunier and Eva Lang
31  2DLDA-based Compound Distance for Similar Online Handwritten Tibetan Transliteration of the Sanskrit Character Recognition
 Zhengqi Cai and Weilan Wang
35  Improving Word Spotting System Performance Using Ensemble Classifier Combination Methods
 Muna Khayyat and Ching Suen
46  Localizing and Recognizing Text in Lecture Videos
 Kartik Dutta, Minesh Mathew, Praveen Krishnan and C V Jawahar
51  A Hybrid Method for Text Line Extraction in Handwritten Document Images
 Ehsan Kiumarsi and Alireza Alaei
52  Crowdsourcing Online Handwriting Acquisition to Develop and Deploy a Unicode Character Classifier
 Francisco Alvaro and Daniel Martín-Albo
55  Word Beam Search: A Connectionist Temporal Classification Decoding Algorithm
 Harald Scheidl, Stefan Fiel and Robert Sablatnig
73  A deep Convolutional Encoder-Decoder Network for Page Segmentation of Historical Handwritten Documents into Text Zones
 Panagiotis Kaddas and Basilis Gatos
74  Neural Text Line Segmentation of Multilingual Print and Handwriting with Recognition-Based Evaluation
 Patrick Schone, Christian Hargraves, Jon Morrey, Rachael Day and Mindy Jacox
86  Real-time analysis of hand-drawn sketches with extended bi-dimensional grammar
 Omar Krichen, Nathalie Girard, Eric Anquetil, Simon Corbillé and Mickaël Renault
87  Automated Grading of Handwritten Essays
 Annapurna Sharma and Dinesh Babu Jayagopi
97  Multi-perspective Multi-modal Trajectory Descriptions for Handwritten Strokes
 Mohammad Tanvir Parvez and Sardar Anisul Haque
101  Active learning in Handwritten Text Recognition using the derivational entropy
 Verónica Romero and Joan Andreu Sánchez
102  Training Schemes for the Transliteration of the Balinese Script into the Latin Script on Palm Leaf Manuscript Images
 Made Windu Antara Kesiman, Jean-Christophe Burie, Jean-Marc Ogier and Philippe Grange
107  Watermarking for Security Issue of Handwritten Documents with Fully Convolutional Networks
 Vinh Loc Cu, Jean-Christophe Burie and Jean-Marc Ogier
108  Separating Optical and Language Models through Encoder-Decoder Strategy for Transferable Handwriting Recognition
 Adeline Granet, Emmanuel Morin, Harold Mouchère, Solen Quiniou and Christian Viard-Gaudin
110  Compact Deep Decriptors for Keyword Spotting
 George Retsinas, Giorgos Sfikas, Georgios Louloudis, Nikolaos Stamatopoulos and Basilis Gatos
116  DNN-HMM based Large Vocabulary Online Handwritten Assamese Word Recognition System
 Subhasis Mandal, Himakshi Choudhury, S. R. Mahadeva Prasanna and Suresh Sundaram
119  Constrained and Parametric Dynamic Programming for Word Image retrieval
 Tanmoy Mondal
135  Identifying Cross Depicted Motifs in Historical Handwritten Documents
 Vinay Pondenkandath, Michele Alberti, Nicole Eichenberger, Rolf Ingold and Marcus Liwicki
138  An Investigative Analysis of Different LSTM Libraries for Supervised and Unsupervised Architectures of OCR Training
 Syed Saqib Bukhari, Sumam Francis and Andreas Dengel

Poster Session 2 - Tuesday, August 7th


Session Chair: B.B. Chaudhuri amd Volker Märgner
3  A Study on Idiosyncratic Handwriting with Impact on Writer Identification
 Chandranath Adak, Bidyut B. Chaudhuri and Michael Blumenstein
4  Extracting Stroke Errors from Digital Ink Characters by Beginning Learners of Chinese as A Foreign Language Based on Acurate Stroke Matching
 Hao Bai and Xi-Wen Zhang
7  An effective Binarization method for disturbed camera-captured document images
 Jinyuan Zhao, Cunzhao Shi, Fuxi Jia, Yanna Wang and Baihua Xiao
14  Zero-Shot Learning Based Approach For Medieval Word Recognition Using Deep-Learned Features
 Sukalpa Chanda, Jochem Baas, Daniël Haitink, Sebastien Hamel, Dominique Stutzmann and Lambert Schomaker
16  Tracking the Ballistic Trajectory in Complex and Long Handwritten Signatures
 Gioele Crispo, Moises Diaz, Angelo Marcelli and Miguel Angel Ferrer
29  Text Line Extraction Based on Distance Map Features and Dynamic Programming
 Vicente Bosch Campos, Verónica Romero, Alejandro Toselli and Enrique Vidal
32  Feature Descriptors for Spotting 3D Characters on Triangular Meshes
 Bartosz Bogacz and Hubert Mara
39  Writer Identification on Historical Documents Using Oriented Basic Image Features
 Abdeljalil Gattal, Chawki Djeddi, Imran Siddiqi and Somaya Al-Maadeed
41  Text Line Segmentation for Challenging Handwritten Document Images using Fully Convolutional Network
 Berat Barakat, Ahmad Droby, Majeed Kassis and Jihad El-Sana
43  Introducing the XXX Bangla Handwriting Dataset and an Efficient Offline Recognizer of Isolated Bangla Characters
 Nishatul Majid and Elisa Barney Smith
49  New RGB based Fusion for Forged IMEI Number Detection in Mobile Images
 Palaiahnakote Shivakumara, V. Basavaraja, Harsha S. Gowda, D. S. Guru, Umapada Pal and Tong Lu
50  Adaptive Multi-Gradient Kernels for Gender Identification
 B. J Navya, Shivakumara Palaiahnakote, G.C Shwetha, Sangheeta Roy, D. S. Guru, Umapada Pal and Tong Lu
59  A Hierarchical Codebook Descriptor Approach for Online Writer Identification
 Suresh Sundaram, Vivek Venugopal and Surbhi Pillai
63  A CNN Based Framework for Multi-Lingual Unistroke Numeral Recognition in Air-Writing
 Prasun Roy, Subhankar Ghosh and Umapada Pal
82  Exploring Sparse Representation for Improved Online Handwriting Recognition
 Subhasis Mandal, Sayed Shahnawazuddin, Rohit Sinha, S R Mahadeva Prasanna and Suresh Sundaram
83  Signature and Logo Detection using Deep Convolutional Neural Networks
 Nabin Sharma, Ranju Mandal, Rabi Sharma, Umapada Pal and Michael Blumenstein
94  DeepDIVA: A Highly-Functional Python Framework for Reproducible Experiments
 Michele Alberti, Vinay Pondenkandath, Marcel Würsch, Rolf Ingold and Marcus Liwicki
103  Boosting Handwriting Text Recognition in Small Databases with Transfer Learning
 José Carlos Aradillas Jaramillo, Juan José Murillo Fuentes and Pablo Martínez Olmos
105  Online Japanese Handwriting Recognizers using Recurrent Neural Networks
 Hung Tuan Nguyen, Cuong Tuan Nguyen and Masaki Nakagawa
128  CNN based Segmentation of Text-lines from Handwritten/Printed Document Images
 Arpita Dutta, Arpan Garai and Samit Biswas
131  Offline Text-Independent Writer Identification Based on Writer-Independent Model Using Conditional AutoEncoder
 Mariko Hosoe, Tomoki Yamada, Kunihito Kato and Kazuhiko Yamamoto
147  Angle Minimization and Graph Analysis for text line segmentation in handwritten documents
 Insaf Setitra and Abdelkrim Meziane
151  Multimodal acquisition and analysis of children handwriting for the study of the efficiency of their handwriting movements: the @MaGma challenge
 Remi Celine, Jimmy Nagau, Jean Vaillant, Alin Dorville and Réjean Plamondon
154  Segmentation and Stitching Improves Handwriting Recognition on Datasets with Few Samples
 Seth Stewart, Lucas Pinto and William Barrett

Poster Session 3 - Wednesday, August 8th

Session Chairs: Marcus Liwicki and Ioannis Pratikakis

COMP-1   ICFHR2018 Competition on Recognition of Historical Arabic Scientific Manuscripts - RASM2018
  Apostolos Antonacopoulos, Clausner Christian, Daniel Wilson-Nunn, Nora McGregor, Daniel Lowe and Bink Hallum
COMP-2   ICFHR 2018 Competition on Automated Text Recognition on a READ Dataset
  Tobias Strauß, Gundram Leifert, Roger Labahn, Tobias Hodel and Günter Mühlberger
COMP-3   ICFHR2018 Competition On Document Image Analysis Tasks for Southeast Asian Palm Leaf Manuscripts
  Jean-Christophe Burie, Made Windu Antara Kesiman, Dona Valy, Erick Paulus, Mira Suryani, Setiawan Hadi, Michel Verleysen, Sophea Chhun and Jean-Marc Ogier
COMP-4   ICFHR 2018 Handwritten Document Image Binarization COmpetition (H-DIBCO 2018)
  Ioannis Pratikakis, Konstantinos Zagoris, Panagiotis Kaddas and Basilis Gatos
COMP-5   ICFHR 2018 – Competition on Vietnamese Online Handwritten Text Recognition using HANDS-VNOnDB (VOHTR2018)
  Hung Tuan Nguyen, Cuong Tuan Nguyen and Masaki Nakagawa
COMP-6   ICFHR2018 competition on Thai Student Signature and Name Components Recognition and Verification Competition
  Hemmaphan Suwanwiwat, Abhijit Das, Umapada Pal and Michael Blumenstein
COMP-7   ICFHR2018 Competition on Multi-script Writer Identification Using LAMIS-MSHD, WDAD and CERUG Data sets
  Chawki Djeddi, Somaya Al-Maadeed, Imran Siddiqi, Abdeljalil Gattal, Sheng He and Younes Akbari

13  Pixel-level Reconstruction and Classification for Noisy Handwritten Bangla Characters
 Manohar Karki, Supratik Mukhopadhyay, Saikat Basu, Robert Dibiano and Qun Liu
20  A Benchmark Dataset of Online Handwritten Gurmukhi Script Words and Numerals
 Harjeet Singh, R.K. Sharma, Rajesh Kumar, Karun Verma, Ravinder Kumar and Munish Kumar
33  RNN - Based Online Handwritten Word Recognition in Devanagari Script
 Rajib Ghosh, Pooja Kesari and Prabhat Kumar
48  Handwritten Arabic character recognition using features extracted by blind source separation
 Mohamed Ali Souibgui, Samir Belaid and Wady Naanaa
56  New COLD Feature based Handwriting Analysis for Enthnicity/Nationality Identification
 Sauradip Nag, Palaiahnakote Shivakumara, Yirui Wu, Umapada Pal and Tong Lu
64  Word-Hunter: A Gamesourcing Experience to Validate the Transcription of Historical Manuscripts
 Jialuo Chen, Pau Riba, Alicia Fornés, Joan Mas, Josep Llados and Joana Maria Pujadas
66  Writer Identification for Historical Manuscripts: Analysis and Optimisation of a Classifier as an Easy-to-Use Tool for Scholars from the Humanities
 Hussein Mohammed, Volker Märgner and H. Siegfried Stiehl
71  A Fully Convolutional Network for Signature Segmentation
 Victor Kléber Santos Leite Melo and Byron Bezerra
78  Hand-Written and Machine-Printed Text Classification in Architecture, Engineering & Construction Documents
 Supriya Das
84  A Study of Data Augmentation for Handwritten Character Recognition Using Deep Learning
 Taihei Hayashi, Keiji Gyohten, Hidehiro Ohki and Toshiya Takami
90  Probabilistic Music-Symbols Spotting in handwritten scores
 Jorge Calvo-Zaragoza, Alejandro Toselli and Enrique Vidal
92  Data Driven Feature Extraction for Gender Classification using Multi-script Handwritten Texts
 Momina Moetesum, Imran Siddiqi, Chawki Djeddi, Yaacoub Hannad and Somaya Al-Maadeed
111  MultiSpectral Image Binarization using GMMs
 Fabian Hollaus, Markus Diem and Robert Sablatnig
114  Space Balancing in Online Handwriting Recognition Postprocessing Using Deep Bidirectional LSTM
 Olha Zubarieva, Ivan Deriuga, Vadym Holosko and Tetiana Ignatova
141  A New Template Matching Similarity Based On Shape Context Descriptor
 Nabil Aouadi and Afef Kacem
143  Hybrid two-dimensional recognizer based on the NSHP-HMM model
 Hanene Boukerma, Christophe Choisy, Abdallah Benouareth, Nadir Farah and Mohamed Cheriet
156  Finding the answer: techniques for locating students' answers in handwritten problem solutions
 Amirali Darvishzadeh, Negin Entezari and Thomas Stahovich

- Other Sessions -

Monday, August 6th

Welcome (9:00am)

Session Chairs: Richard Zanibbi, R. Manmatha and Venu Govindaraju  

Wednesday, August 8th

Panel Discussion: Handwriting Recognition in Industry and Academia (1:40pm)

Session Chair: David Doermann
Confirmed Participants: Francisco Álvaro (Wiris), Boris Daskalov (Hyperscience), Zsolt Wimmer (MyScript), (others TBD)

This panel will explore: 1) opportunities for work in handwriting recognition and related applications in the industrial setting, and 2) goals related to handwriting recognition that are of common interest to both academicians and industrial researchers.

Competition Teasers and Awards (2:40pm)

Session Chair: Nicholas R. Howe

COMP-1   ICFHR2018 Competition on Recognition of Historical Arabic Scientific Manuscripts - RASM2018
  Apostolos Antonacopoulos, Clausner Christian, Daniel Wilson-Nunn, Nora McGregor, Daniel Lowe and Bink Hallum
COMP-2   ICFHR 2018 Competition on Automated Text Recognition on a READ Dataset
  Tobias Strauß, Gundram Leifert, Roger Labahn, Tobias Hodel and Günter Mühlberger
COMP-3   ICFHR2018 Competition On Document Image Analysis Tasks for Southeast Asian Palm Leaf Manuscripts
  Jean-Christophe Burie, Made Windu Antara Kesiman, Dona Valy, Erick Paulus, Mira Suryani, Setiawan Hadi, Michel Verleysen, Sophea Chhun and Jean-Marc Ogier
COMP-4   ICFHR 2018 Handwritten Document Image Binarization COmpetition (H-DIBCO 2018)
  Ioannis Pratikakis, Konstantinos Zagoris, Panagiotis Kaddas and Basilis Gatos
COMP-5   ICFHR 2018 – Competition on Vietnamese Online Handwritten Text Recognition using HANDS-VNOnDB (VOHTR2018)
  Hung Tuan Nguyen, Cuong Tuan Nguyen and Masaki Nakagawa
COMP-6   ICFHR2018 competition on Thai Student Signature and Name Components Recognition and Verification Competition
  Hemmaphan Suwanwiwat, Abhijit Das, Umapada Pal and Michael Blumenstein
COMP-7   ICFHR2018 Competition on Multi-script Writer Identification Using LAMIS-MSHD, WDAD and CERUG Data sets
  Chawki Djeddi, Somaya Al-Maadeed, Imran Siddiqi, Abdeljalil Gattal, Sheng He and Younes Akbari

TC-11 Meeting: Bids to Host ICFHR 2022 (4:50pm)

Session Chair: Gernot Fink

Awards Presentation and Closing (5:20pm)

Session Chair: Richard Zanibbi

- Instructions for Presenters -

Important Notes Oral Presentations Poster Presentations

ICFHR 2018
August 5-8, 2018
Niagara Falls (USA)