F
Faisal Shafait
Researcher at University of the Sciences
Publications - 222
Citations - 10131
Faisal Shafait is an academic researcher from University of the Sciences. The author has contributed to research in topics: Deep learning & Optical character recognition. The author has an hindex of 41, co-authored 211 publications receiving 7810 citations. Previous affiliations of Faisal Shafait include National University of Science and Technology & German Research Centre for Artificial Intelligence.
Papers
More filters
Proceedings ArticleDOI
ICDAR 2015 competition on Robust Reading
Dimosthenis Karatzas,Lluis Gomez-Bigorda,Anguelos Nicolaou,Suman K. Ghosh,Andrew D. Bagdanov,Masakazu Iwamura,Jiri Matas,Lukas Neumann,Vijay Chandrasekhar,Shijian Lu,Faisal Shafait,Seiichi Uchida,Ernest Valveny +12 more
TL;DR: A new Challenge 4 on Incidental Scene Text has been added to the Challenges on Born-Digital Images, Focused Scene Images and Video Text and tasks assessing End-to-End system performance have been introduced to all Challenges.
Proceedings ArticleDOI
ICDAR 2013 Robust Reading Competition
Dimosthenis Karatzas,Faisal Shafait,Seiichi Uchida,Masakazu Iwamura,Lluís Gómez i Bigorda,Sergi Robles Mestre,Joan Mas,David Fernandez Mota,Jon Almazan,Lluís-Pere de las Heras +9 more
TL;DR: The datasets and ground truth specification are described, the performance evaluation protocols used are details, and the final results are presented along with a brief summary of the participating methods.
Proceedings ArticleDOI
ICDAR 2011 Robust Reading Competition Challenge 2: Reading Text in Scene Images
TL;DR: An overview of the approaches that the participants used, the evaluation measure, and the dataset used in the ICDAR 2011 Robust Reading Competition for detecting/recognizing text in natural scene images is presented.
Proceedings ArticleDOI
Efficient implementation of local adaptive thresholding techniques using integral images
TL;DR: A fast adaptive binarization algorithm that yields the same quality of Binarization as the Sauvola method but runs in time close to that of global thresholding methods (like Otsu's method), independent of the window size.
Proceedings ArticleDOI
Bayesian sparse representation for hyperspectral image super resolution
TL;DR: This work proposes a generic Bayesian sparse coding strategy to be used with Bayesian dictionaries learned with the Beta process and theoretically analyzes the proposed strategy for its accurate performance.