scholarly journals Amharic OCR: An End-to-End Learning

2020 ◽  
Vol 10 (3) ◽  
pp. 1117 ◽  
Author(s):  
Birhanu Belay ◽  
Tewodros Habtegebrial ◽  
Million Meshesha ◽  
Marcus Liwicki ◽  
Gebeyehu Belay ◽  
...  
Keyword(s):  
Recurrent Neural Networks ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
State Of The Art ◽  
Writing System ◽  
Recent Success ◽  
Optical Character ◽  
Proposed Model ◽  
Feature Extractor ◽  
End To End

In this paper, we introduce an end-to-end Amharic text-line image recognition approach based on recurrent neural networks. Amharic is an indigenous Ethiopic script which follows a unique syllabic writing system adopted from an ancient Geez script. This script uses 34 consonant characters with the seven vowel variants of each (called basic characters) and other labialized characters derived by adding diacritical marks and/or removing parts of the basic characters. These associated diacritics on basic characters are relatively smaller in size, visually similar, and challenging to distinguish from the derived characters. Motivated by the recent success of end-to-end learning in pattern recognition, we propose a model which integrates a feature extractor, sequence learner, and transcriber in a unified module and then trained in an end-to-end fashion. The experimental results, on a printed and synthetic benchmark Amharic Optical Character Recognition (OCR) database called ADOCR, demonstrated that the proposed model outperforms state-of-the-art methods by 6.98% and 1.05%, respectively.

CNN-based Rain Reduction in Street View Images

2020 ◽  
Vol 2020 (1) ◽  
pp. 78-81
Author(s):  
Simone Zini ◽  
Simone Bianco ◽  
Raimondo Schettini
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
State Of The Art ◽  
Weather Conditions ◽  
Specific Interest ◽  
Optical Character ◽  
Street View ◽  
In The Wild ◽  
Bad Weather ◽  
Detection And Recognition

Rain removal from pictures taken under bad weather conditions is a challenging task that aims to improve the overall quality and visibility of a scene. The enhanced images usually constitute the input for subsequent Computer Vision tasks such as detection and classification. In this paper, we present a Convolutional Neural Network, based on the Pix2Pix model, for rain streaks removal from images, with specific interest in evaluating the results of the processing operation with respect to the Optical Character Recognition (OCR) task. In particular, we present a way to generate a rainy version of the Street View Text Dataset (R-SVTD) for "text detection and recognition" evaluation in bad weather conditions. Experimental results on this dataset show that our model is able to outperform the state of the art in terms of two commonly used image quality metrics, and that it is capable to improve the performances of an OCR model to detect and recognise text in the wild.

Scribble-Scrabble Genius

2019 ◽  
pp. 37-73
Author(s):  
Yohei Igarashi
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Writing System ◽  
Optical Character ◽  
History Of ◽  
Recognition Software

Although Coleridge is mostly known for being a copious talker who was impossible to transcribe, this chapter recovers Coleridge’s role as transcriber, theorist of transcription practices, and inventor of his own idiosyncratic shorthand. Considering Coleridge’s time as a parliamentary reporter, his self-reflexive notebook entries, and the history of stenography, this chapter posits that Coleridge pursued an efficient writing system to record not speech but the flow of his own silent thoughts. Also discussing today’s optical character recognition software and the shorthand effect (when letters or words uncannily become illegible shapes, and non-linguistic shapes come to look like linguistic signs), this chapter culminates in a reading of the “signs” in “The Rime of the Ancient Mariner.”

Possible Approaches for Character Recognition With Existing Methodologies and State-of-the-Art Techniques

2019 ◽  
pp. 232-246
Author(s):  
Rashmi Welekar ◽  
Nileshsingh V. Thakur
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
State Of The Art ◽  
Industrial Applications ◽  
New Methods ◽  
Optical Character ◽  
The World ◽  
New Hypothesis ◽  
Key Questions ◽  
Art Techniques

The world started to talk about optical character recognition (OCR) around 1870. Then over another 25 years OCR systems were designed for industrial applications. And now the OCR software is easily available online for free, through products like Acrobat reader, WebOCR, etc. But still the research is on. Do we need to switch direction or introduce new hypothesis are some of the key questions? The purpose of this chapter is to answer the above questions and propose new methods for character recognition.

OPTICAL CHARACTER RECOGNITION — A SURVEY

1991 ◽  
Vol 05 (01n02) ◽  
pp. 1-24 ◽  
Author(s):  
S. IMPEDOVO ◽  
L. OTTAVIANO ◽  
S. OCCHINEGRO
Keyword(s):  
Feature Extraction ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
State Of The Art ◽  
The State ◽  
Historical Background ◽  
Optical Scanner ◽  
Optical Character ◽  
Recognition Systems

In order to highlight the interesting problems and actual results on the state of the art in optical character recognition (OCR), this paper describes and compares preprocessing, feature extraction and postprocessing techniques for commercial reading machines. Problems related to handwritten and printed character recognition are pointed out, and the functions and operations of the major components of an OCR system are described. Historical background on the development of character recognition is briefly given and the working of an optical scanner is explained. The specifications of several recognition systems that are commercially available are reported and compared.

scholarly journals End-to-End Optical Character Recognition for Bengali Handwritten Words

2021 ◽  
Author(s):  
Farisa Benta Safir ◽  
Abu Quwsar Ohi ◽  
M.F. Mridha ◽  
Muhammad Mostafa Monowar ◽  
Md. Abdul Hamid
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Optical Character ◽  
End To End

scholarly journals Evaluation of OCR free software applied to old books

2019 ◽  
Author(s):  
Pedro H. Barcha Correia ◽  
Gerberth Adín Ramírez Rivera
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
State Of The Art ◽  
Free Software ◽  
Data Input ◽  
Optical Character

This project compares state-of-the-art Free Software Optical Character Recognition (OCR) programs. Particularly, their results over old books pages were evaluated. Moreover, in order to optimize the recognition for this kind of data input, methods that are not implemented in the programs were proposed and their results were analyzed as well.

A One-Pass Approach for Slope and Slant Estimation of Tri-Script Handwritten Words

2018 ◽  
Vol 29 (1) ◽  
pp. 688-702 ◽  
Author(s):  
Suman Kumar Bera ◽  
Radib Kar ◽  
Souvik Saha ◽  
Akash Chakrabarty ◽  
Sagnik Lahiri ◽  
...  
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
State Of The Art ◽  
Ground Truth ◽  
Recognition System ◽  
Optical Character ◽  
Handwritten Word Recognition ◽  
Computationally Expensive ◽  
Word Images ◽  
Ground Truth Information

Abstract Handwritten words can never complement printed words because the former are mostly written in either skewed or slanted form or in both. This very nature of handwriting adds a huge overhead when converting word images into machine-editable format through an optical character recognition system. Therefore, slope and slant corrections are considered as the fundamental pre-processing tasks in handwritten word recognition. For solving this, researchers have followed a two-pass approach where the slope of the word is corrected first and then slant correction is carried out subsequently, thus making the system computationally expensive. To address this issue, we propose a novel one-pass method, based on fitting an oblique ellipse over the word images, to estimate both the slope and slant angles of the same. Furthermore, we have developed three databases considering word images of three popular scripts used in India, namely Bangla, Devanagari, and Roman, along with ground truth information. The experimental results revealed the effectiveness of the proposed method over some state-of-the-art methods used for the aforementioned problem.

Sign in / Sign up

Export Citation Format

Share Document