Insights on the Use of Convolutional Neural Networks for Document Image Binarization
作者： J. Pastor-Pellicer , S. España-Boquera , F. Zamora-Martínez , M. Zeshan Afzal , Maria Jose Castro-Bleda
DOI: 10.1007/978-3-319-19222-2_10
关键词:
摘要: Convolutional Neural Networks have systematically shown good performance in Computer Vision and Handwritten Text Recognition tasks. This paper proposes the use of these models for document image binarization. The main idea is to classify each pixel into foreground background from a sliding window centered at be classified. An experimental analysis on effect sensitive parameters some working topologies are proposed using two different corpora, very properties: DIBCO Santgall.
springer.com
sci-hub.se 参考文章(28)
Matthew D. Zeiler, ADADELTA: An Adaptive Learning Rate Method arXiv: Learning. ,(2012)
José Luis Hidalgo, Salvador España, María José Castro, José Alberto Pérez, Enhancement and Cleaning of Handwritten Data by Using Neural Networks Pattern Recognition and Image Analysis. pp. 376- 383 ,(2005) , 10.1007/11492429_46
Wayne Niblack, An introduction to digital image processing ,(1986)
Amjad Rehman, Tanzila Saba, Neural networks for document image preprocessing: state of the art Artificial Intelligence Review. ,vol. 42, pp. 253- 273 ,(2014) , 10.1007/S10462-012-9337-Z
Ioannis Pratikakis, Basilis Gatos, Konstantinos Ntirogiannis, None, ICFHR 2012 Competition on Handwritten Document Image Binarization (H-DIBCO 2012) international conference on frontiers in handwriting recognition. pp. 817- 822 ,(2012) , 10.1109/ICFHR.2012.216
J. Kittler, J. Illingworth, On threshold selection using clustering criteria systems man and cybernetics. ,vol. 15, pp. 652- 655 ,(1985) , 10.1109/TSMC.1985.6313443
Le Kang, Jayant Kumar, Peng Ye, Yi Li, David Doermann, Convolutional Neural Networks for Document Image Classification international conference on pattern recognition. pp. 3168- 3172 ,(2014) , 10.1109/ICPR.2014.546
Andreas Fischer, Volkmar Frinken, Alicia Fornés, Horst Bunke, Transcription alignment of Latin manuscripts using hidden Markov models Proceedings of the 2011 Workshop on Historical Document Imaging and Processing. pp. 29- 36 ,(2011) , 10.1145/2037342.2037348
E. Badekas, N. Papamarkos, Optimal combination of document binarization techniques using a self-organizing map neural network Engineering Applications of Artificial Intelligence. ,vol. 20, pp. 11- 24 ,(2007) , 10.1016/J.ENGAPPAI.2006.04.003
Bolan Su, Shijian Lu, Chew Lim Tan, Combination of Document Image Binarization Techniques international conference on document analysis and recognition. pp. 22- 26 ,(2011) , 10.1109/ICDAR.2011.14