Abstract:
There are numerous difficulties in recognizing the textual data from the images and requires great attention. Typical OCR (optical character recognition) systems provide this facility to detect the textual data from that of image data. The text can also be in handwritten format. In this paper we propose the methods or API’s that are used in Visual Studio to detect the text from that of images. As Visual Studio only supports MSDN libraries and for this reason the other operations to be performed like, in text recognition Optical Character recognition (OCR) simply cannot be implemented without any elaborated API. These API’s are basically based on different libraries that are to be introduced in Visual Studio in order to use the predefined functions of these mentioned libraries.
