RECOGNITION BY THE LOWENSTEIN LEAST DISTANCE METHOD
Abstract
Text recognition in images is an important task of machine learning, as it allows you to organize convenient interaction with data: editing, analysis, searching for words or phrases, etc.
In recent decades, thanks to the use of modern advances in computer technology, new methods of image processing and pattern recognition have been developed, which made it possible to create such industrial text recognition systems as, for example, FineReader, which satisfy the basic requirements of workflow automation systems. However, the creation of an application in this area is still a creative task and requires additional research due to the specific requirements for resolution, speed, recognition reliability and memory size that characterize each specific task.
References
Wakahara T. Shape machine using LAT and its application to hand- written character recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. –1994. – Vol. 16, ¹ 6. – June. P. 618-629. 9.
Lam L., Suen C.Y. An Evaluation of Parallel Thinning Algorithms for Character Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. – 1995. – Vol. 17, ¹ 9. P. 914–919. 10.
Plamondon R., Srinari S. On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence. – 2000. – Vol. 22, ¹ 1. – January. 11.
https://en.wikipedia.org/wiki/Optical_character_recognition
https://www.abbyy.com/ru/finereader/
https://ru.wikipedia.org/wiki/ПЗС
https://ru.wikipedia.org/wiki/Проект_«Гутенберг»
https://ru.wikipedia.org/wiki/%D0%A1%D0%B8%D0%B3%D0%BC%D0 %BE%D0%B8%D0%B4%D0%B0