Text-based Image Segmentation Methodology

In computer vision, segmentation is the process of partitioning a digital image into multiple segments (sets of pixels). Image segmentation is thus inevitable. Segmentation used for text-based images aim in retrieval of specific information from the entire image. This information can be a line or a word or even a character. This paper proposes various methodologies to segment a text based image at various levels of segmentation. This material serves as a guide and update for readers working on the text based segmentation area of Computer Vision. First, the need for segmentation is justified in the context of text based information retrieval. Then, the various factors affecting the segmentation process are discussed. Followed by the levels of text segmentation are explored. Finally, the available techniques with their superiorities and weaknesses are reviewed, along with directions for quick referral are suggested. Special attention is given to the handwriting recognition since this area requires more advanced techniques for efficient information extraction and to reach the ultimate goal of machine simulation of human reading.