First International Workshop on
Robust Reading
(In conjunction with ACCV2014)

November 2, 2014

National University of Singapore, Singapore

Accepted Papers

Following 8 papers were accepted. These papers were selected from 13 submitted papers, which included ones directly submitted to IWRR (say, IWRR papers) and ones passed from ACCV (ACCV papers). Some of the latter were revised and re-submitted to IWRR before the IWRR submission due date, which were treated as IWRR papers. The acceptance rate was 8/13 = 61.5%.


A Machine Learning Approach to Hypothesis Decoding in Scene Text Recognition

Jindrich Libovicky (Charles University in Prague), Lukas Neumann (Czech Technical University in Prague), Pavel Pecina (Charles University in Prague) and Jiri Matas (Czech Technical University in Prague)


Scene Text Recognition: No Country for Old Men?

Lluis Gomez and Dimosthenis Karatzas (Computer Vision Center)


A Hybrid Approach to Detect Texts in Natural Scenes by Integration of a Connected-Component Method and a Sliding-Window Method

Yojiro Tonouchi, Kaoru Suzuki (Toshiba Corporation) and Kunio Osada (Toshiba Solutions Corporation)


Performance Improvement of Dot-Matrix Character Recognition by Variation Model Based Learning

Koji Endo, Wataru Ohyama, Tetsushi Wakabayashi and Fumitaka Kimura (Mie University)

IWRR #10

Perspective Scene Text Recognition with Feature Compression and Ranking

Yu Zhou, Shuang Liu, Yongzheng Zhang, Yipeng Wang (Chinese Academy of Sciences) and Weiyao Lin (Shanghai Jiao Tong University)

IWRR #12

Text Localization Based on Fast Feature Pyramids and Multi-Resolution Maximally Stable Extremal Regions

Alessandro Zamberletti, Lucia Noce and Ignazio Gallo (University of Insubria)

IWRR #13

Robust Text Segmentation in Low Quality Images via Adaptive Stroke Width Estimation and Stroke based Superpixel Grouping

Zhu Anna, Dong Yangbo and Wang Guoyou (Huazhong University of Science and Technology)

IWRR #14

Efficient Character Skew Rectification in Scene Text Images

Michal Busta, Lukas Neumann and Jiri Matas (Czech Technical University in Prague)