Robust Extraction of Text from Camera Images

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. Detection of coloured scene text is a new challenge for all camera based images. Common problems for text extraction from camera based images are the lack of prior knowledge of any kind of text features such as colour, font, size and orientation. In this paper we propose a new algorithm for the extraction of text from an image which can overcome these problems. In addition, problems due to an unconstrained complex background in the scene has also been addressed. Here a new technique is applied to determine the discrete edges around the text boundaries. A novel methodology is also proposed to extract the text exploiting its appearance in terms of colour and spatial distribution.

• Type: Journal
• Year: 2009
• Where: ICDAR
• Authors: Shyama Prosad Chowdhury, Soumyadeep Dhar, Amit Kumar Das, Bhabatosh Chanda, Karen McMenemy
• Keywords: Camera Based Images, Document Analysis, ICDAR 2009, Image, Meta Data