Automatic text extraction and character segmentation using maximally stable extremal regions
This addresses text extraction for multilingual content in images, but it is incremental as it builds on existing region-based methods with limited novelty.
The paper tackles text detection and character segmentation in images by proposing an algorithm using Maximally Stable Extremal Regions as letter candidates, followed by thresholding and connected component analysis. It achieves good results for English and Russian character sets but is less accurate for Hindi and Urdu, with testing on various image formats and no training overhead.
Text detection and segmentation is an important prerequisite for many content based image analysis tasks. The paper proposes a novel text extraction and character segmentation algorithm using Maximally Stable Extremal Regions as basic letter candidates. These regions are then subjected to thresholding and thereafter various connected components are determined to identify separate characters. The algorithm is tested along a set of various JPEG, PNG and BMP images over four different character sets; English, Russian, Hindi and Urdu. The algorithm gives good results for English and Russian character set; however character segmentation in Urdu and Hindi language is not much accurate. The algorithm is simple, efficient, involves no overhead as required in training and gives good results for even low quality images. The paper also proposes various challenges in text extraction and segmentation for multilingual inputs.