An Approach for Text Detection in Images
Sandeep Sharma, Jai Prakash, Mohan Malaviya · 2012
We present a novel text detection technique for the application of image in databases of consumer pictures and videos. Images are annotated using information only from the picture itself. It needs to be fast, efficient and robust in order to feed an OCR classifier with the correct input. In other words, segmented regions must correspond to the actual text. A lot of work has been done for detecting text in images and a lot has to be done. This paper gives detailed survey on image to text detection mechanism. This paper gives the description of work has been done for automatically detection of text from images, localize and extract horizontally aligned text in images (and digital videos) with complex backgrounds is presented.