Proceedings ArticleDOI
OCR for bilingual documents using language modeling
Anupama Ray,Sai Rajeswar,Santanu Chaudhury +2 more
- pp 1256-1260
TLDR
A unified framework of language model and multiple preprocessing hypotheses for word recognition from bilingual document images and uses a language model to verify each alternative and choose the best recognized sequence is presented.Abstract:
Script based features are highly discriminative for text segmentation and recognition. Thus they are widely used in Optical Character Recognition(OCR) problems. But usage of script dependent features restricts the adaptation of such architectures directly for another script. With script independent systems, this problem can be solved to a certain extent for monolingual documents. But the problem aggravates in case of multilingual documents as it is very difficult for a single classifier to learn many scripts. Generally a script identification module identifies text segments and accordingly the script-dependent classifier is selected. This paper presents a unified framework of language model and multiple preprocessing hypotheses for word recognition from bilingual document images. Prior to text recognition, preprocessing steps such as binarization and segmentation are required for ease of recognition. But these steps induce huge combinatorial error propagating to final recognition accuracy. In this paper we use multiple preprocessing routines as alternate hypotheses and use a language model to verify each alternative and choose the best recognized sequence. We test this architecture for word recognition of Kannada-English and Telugu-English bilingual documents and achieved better recognition rates than single methods using same classifier.read more
Citations
More filters
Journal ArticleDOI
Advanced Applications on Bilingual Document Analysis and Processing Systems
Shalini Puri,Satya Prakash Singh +1 more
TL;DR: A journey of bilingual NLP and image-based document classification systems is discussed and an overview of their methods, feature extraction techniques, document sets, classifiers, and accuracy for English-Hindi and other language pairs is provided.
Journal ArticleDOI
A Unified Multilingual Handwriting Recognition System using multigrams sub-lexical units
TL;DR: This work considers language models based on sub-lexical units, called multigrams, and proposes an end-to-end unified multilingual recognition system where both a single optical model and a single language model are trained on all the languages.
Proceedings ArticleDOI
Multilingual Text Detection and Identification from Indian Signage Boards
TL;DR: A language identification technique using tree bagging algorithm is also integrated along with SWT algorithm for text detection to detect and identify text belonging to Kannada, Hindi and English.
Book ChapterDOI
Recognition of Handwritten Meitei Mayek and English Alphabets Using Combination of Spatial Features
TL;DR: Spatial features based recognition of handwritten Manipuri and English alphabets is presented and the highest accuracy achieved in the proposed methodology is 92.40%.
Dissertation
Understanding Text in Scene Images
TL;DR: This thesis proposes a robust text segmentation (binarization) technique, and uses it to improve the recognition performance of scene text and presents an energy minimization framework that exploits both bottom-up and top-down cues for recognizing words extracted from street images.
References
More filters
Posted Content
Efficient Estimation of Word Representations in Vector Space
TL;DR: This paper proposed two novel model architectures for computing continuous vector representations of words from very large data sets, and the quality of these representations is measured in a word similarity task and the results are compared to the previously best performing techniques based on different types of neural networks.
Proceedings Article
Learning Word Vectors for Sentiment Analysis
TL;DR: This work presents a model that uses a mix of unsupervised and supervised techniques to learn word vectors capturing semantic term--document information as well as rich sentiment content, and finds it out-performs several previously introduced methods for sentiment classification.
Proceedings Article
Framewise phoneme classification with bidirectional LSTM and other neural network architectures
Alex Graves,Jürgen Schmidhuber +1 more
TL;DR: In this article, a modified, full gradient version of the LSTM learning algorithm was used for framewise phoneme classification, using the TIMIT database, and the results support the view that contextual information is crucial to speech processing, and suggest that bidirectional networks outperform unidirectional ones.
Journal ArticleDOI
2005 Special Issue: Framewise phoneme classification with bidirectional LSTM and other neural network architectures
Alex Graves,Jürgen Schmidhuber +1 more
TL;DR: In this article, a modified, full gradient version of the LSTM learning algorithm was used for framewise phoneme classification, using the TIMIT database, and the results support the view that contextual information is crucial to speech processing, and suggest that bidirectional networks outperform unidirectional ones.
Journal ArticleDOI
Adaptive document image binarization
Jaakko Sauvola,Matti Pietikäinen +1 more
TL;DR: A new method is presented for adaptive document image binarization, where the page is considered as a collection of subcomponents such as text, background and picture, which adapts and performs well in each case qualitatively and quantitatively.