Optical optical character recognition for text translation using tesseract and leptonica on android

Nowadays human needs about information is become a primary need, along with the development of technology, with technology people can easily get the information. For Travelers language barrier always be crucial problem. Like Christoper Elliot says on his article which was written in The Washington Post. Good travel advisers offer their clients advice, access, advocacy and accountability. You might find a agent or a consumer advocate with passable language skills, but then there�s the issue of influence. Belonging to a well-recognized consumer group or travel agency network definitely has its advantages; otherwise, an intransigent travel company may not care that you�re upset about the service you received, or didn�t. The other option: Go it alone, even if you don�t understand the language. For a more precise interpretation, you can try a service like VerbalizeIt, which uses a network of human translators to translate text or interpret speech in real time. Rates start at $2 a minute for live interpretation and 17 cents a word for document translation, all of which can add up quickly. But when you need to capture every nuance of a foreign language, and when hundreds or thousands of dollars are at stake, paying extra for a translator may be a sound investment. For that reason, in this research the author intent to implement OCR(Optical Character Recognition) technology, OCR converts images of handwritten or printed text captured by camera or scanner into editable text .In this research the author will implement OCR into android device and use it to capture a image which contain a text and translate the text inside into a text that user could recognize. In this research, author try to combine OCR technology and implement it in the dictionary application which will run on android Smartphone. According to article in here Tesseract is probably the most accurate open source OCR engine available. So the author determine to use Leptonica to capture pattern of the text inside an image, then use Tesseract to process the pattern and Microsoft API translator to translate the text. In the end of research the author hope that implementation of Optical Character Recognition could help the user in translate the words that they cannot understan