A study of multi-oriented text recognition in natural scene images

Abstract: The extraction of text in an image is a classical problem in the computer vision. With the increasing popularity of practical vision system text recognition in natural scenes becomes a critical task. Text data present in images and video contain useful information for automatic annotation, image indexing. But as natural scene images contain complex background, multiple fonts and orientations, and different alignments make the problem of automatic text extraction extremely challenging. This paper gives overview of work done for automatic detection of text from images and explains the methodology to extract and recognize multioriented text in natural scene images.

Keywords: Text Extraction, Text Recognition, K-means Clustering, Binarization, Sliding Window, OCR, Hidden Markov Model, Neural Networks.