Detection and localization of texts from natural scene images using scale space and morphological operations

Detection and localization of texts from natural scene images is important and can provide a much truer form of content-based image analysis if it can be extracted and harnessed efficiently. This problem becomes challenging because of complex background, variations of text font, size and line orientation, non-uniform illumination. A new unsupervised text detection algorithm is proposed in this paper. In this approach scale space and morphological operations for the edge detection are utilized. The non-text components are efficiently filter out by using scale decomposition and 2D Gaussian low pass filter. They are extracted based on observation that the edge of a character can be extracted from the complex scenes by taking into consideration the high similarities in length and aspect ratio. The proposed method yielded high precision when experiments where evaluated in the ICDAR 2003 dataset.