Proceedings ArticleDOI
Text recognition of low-resolution document images
Charles E. Jacobs,Patrice Y. Simard,Paul A. Viola,James Russell Rinker +3 more
- pp 695-699
TLDR
This paper uses a machine learning approach based on a convolutional neural network to achieve maximum robustness in OCR, and when combined with a language model using dynamic programming, the overall performance is in the vicinity of 80-95% word accuracy on pages captured with a 1024/spl times/768 webcam and 10-point text.Abstract:
Cheap and versatile cameras make it possible to easily and quickly capture a wide variety of documents. However, low resolution cameras present a challenge to OCR because it is virtually impossible to do character segmentation independently from recognition. In this paper we solve these problems simultaneously by applying methods borrowed from cursive handwriting recognition. To achieve maximum robustness, we use a machine learning approach based on a convolutional neural network. When our system is combined with a language model using dynamic programming, the overall performance is in the vicinity of 80-95% word accuracy on pages captured with a 1024/spl times/768 webcam and 10-point text.read more
Citations
More filters
Proceedings ArticleDOI
PhotoOCR: Reading Text in Uncontrolled Conditions
TL;DR: This work describes Photo OCR, a system for text extraction from images that is capable of recognizing text in a variety of challenging imaging conditions where traditional OCR systems fail, notably in the presence of substantial blur, low resolution, low contrast, high image noise and other distortions.
Proceedings ArticleDOI
Studying Very Low Resolution Recognition Using Deep Networks
TL;DR: This work forms a dedicated deep learning method that allows for both the flexibility to combat the LR-HR domain mismatch, and the robustness to outliers, and achieves feature enhancement and recognition simultaneously.
Journal ArticleDOI
Scene Text Recognition Using Similarity and a Lexicon with Sparse Belief Propagation
TL;DR: A probabilistic model for scene text recognition is introduced that integrates similarity, language properties, and lexical decision and is fusing information sources in one model to eliminate unrecoverable errors that result from sequential processing, improving accuracy.
Posted Content
Studying Very Low Resolution Recognition Using Deep Networks
TL;DR: In this paper, a robust partially coupled networks (RPCN) was proposed to solve the very low resolution recognition (VLRR) problem using deep learning methods, taking advantage of techniques primarily in super resolution, domain adaptation and robust regression.
Book ChapterDOI
Large-lexicon attribute-consistent text recognition in natural images
TL;DR: A new model for the task of word recognition in natural images that simultaneously models visual and lexicon consistency of words in a single probabilistic model is proposed and outperforms state-of-the-art methods for cropped word recognition.
References
More filters
Book
Neural networks for pattern recognition
TL;DR: This is the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition, and is designed as a text, with over 100 exercises, to benefit anyone involved in the fields of neural computation and pattern recognition.
Book ChapterDOI
Neural Networks for Pattern Recognition
Suresh Kothari,Heekuck Oh +1 more
TL;DR: The chapter discusses two important directions of research to improve learning algorithms: the dynamic node generation, which is used by the cascade correlation algorithm; and designing learning algorithms where the choice of parameters is not an issue.
Proceedings ArticleDOI
Best practices for convolutional neural networks applied to visual document analysis
TL;DR: A set of concrete bestpractices that document analysis researchers can use to get good results with neural networks, including a simple "do-it-yourself" implementation of convolution with a flexible architecture suitable for many visual document problems.
Journal ArticleDOI
Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks
TL;DR: A shoulder strap retainer having a base to be positioned on the exterior shoulder portion of a garment with securing means attached to the undersurface of the base for removably securing the base to the exterior shoulders portion of the garment.
Journal ArticleDOI
Evaluation of binarization methods for document images
O.D. Trier,Torfinn Taxt +1 more
TL;DR: This paper presents an evaluation of eleven locally adaptive binarization methods for gray scale images with low contrast, variable background intensity and noise and Niblack's method with the addition of the postprocessing step of Yanowitz and Bruckstein's method (1989) performed the best and was also one of the fastest binarized methods.