Department of Computer Science and Engineering, Government College of Engineering, Amravati (Maharashtra), India
Online published on 24 October, 2013.
The complete design of Character localization and recognition application system for Smartphone with four modules are explained. Images taken from camera of mobile device will be browsed from gallery and pre-processed. The text of these images will be accurately localized within the device in a fraction of a second using special localization method called “Low Complexity Localization method”. Localized text sub-image will be fed for text extraction to the best OCR engine called “Tesseract”. The text output is then fed to web to search for web search results. The result will be displayed on browser of mobile.The system can be deployed on android operating system based smartphones. More exciting applications can be developed over the text extraction method with a high performance while also being computationally inexpensive. In this paper we have described all modules and explained localization module in detail. We have explained android architecture to be useful for deployment also explained Tesseract engine to be used. Finally we concluded with a good design for Smartphone OCR application.
Pre-process, Text localization, text extraction, OCR, android, Smartphone