Android Based Text Reader

Abstract

This report anticipates strategy for planning and execution of OCR (Optical Character Recognition) framework for Android based gadgets for renditions 2.2 or more. Particular range of this proposal is archive comprehension and acknowledgment which is a branch of PC vision and in turns a sub-class of Artificial Intelligence. Optical character acknowledgment is the interpretation of optically checked bitmaps of printed or manually written content into digitally editable information records. OCR (Optical Character Recognition, otherwise called picture to-content) is a delicacy on PCs; the innovation itself has propelled a wide margin, yet the cost of this innovation is still out of the range of numerous. The great, quality OCR programs on Windows cost a lot while the less expensive OCR projects are crappy. OCR applications have not yet entered the Android biological community and also one may think. There are just a modest bunch of utilizations out there, and on Android it is not great. Try not to anticipate that your telephone will exceed your PC in performing OCR, as in mobiles we have restricted memory, power and speed when contrasted with your PC. Content to Speech (TTS) which is otherwise called (Speech union) is the manufactured generation of human discourse. The PC framework used to accomplish this is known as a discourse motor. The programmed pitch mirrors the importance of the content, as for delays, breath gatherings, accentuation and connection. Content to Speech changes any content into discourse continuously. It actually peruses so everyone can hear any composed data with a smooth and characteristic sounding voice. The framework peruses the content in a manner that it appears like a genuine individual is talking. It takes delays, inhales and takes after the accentuation present in the content given to it.