The world we are living today is called as Information age. Knowledge comes from information. And, knowledge is power. This precisely brings out the importance of information in today’s world. The need of the hour is to efficiently process this information to achieve greater knowledge and improved decision making. The extraction of text in an image is a classical problem in the computer vision. Extraction involves detection, localization, tracking, extraction, enhancement and recognition of the text from the given image. However variation of text due to difference in size, style, orientation, alignment, low image contrast and complex background make the problem of automatic text extraction extremely challenging. Text within a camera grabbed image can contain a huge amount of meta data about that scene. Such meta data can be useful for identification, indexing and retrieval purposes.Here we will develop the system which will be able to recognize the pattern of the text data from the image file. Then we will extract that data and convert it into the text file. As memory used by image data is more than the text data having same text information. So this idea will save the memory used to store image file as compared to text file and will also allow user to edit, delete and add the extracted text of the image.
Department of Computer Engineering
Sardar Patel Institute of Technology