A Model for Automatic Recognition of Vertical Texts in Natural Scene Images

Abstract

Text recognition plays an important role in recognizing texts presented in the images as they provide important information. Scene text recognition has been an active research topic with rapid growth of development to improve the performance of text recognition with better reliability and accuracy. However, scene text recognition is challenging due to images containing inconsistent lighting, low resolution and blurriness. In addition, scene texts are usually taken from outdoor signboards, signage and road signs, which contain various orientation and fancy font styles to attract attention. Various researchers have proposed methods for recognizing different orientations of scene texts, such as horizontal texts, curved texts and rotated texts. However, to data there is a lack of research in recognizing vertical texts in natural scene images. In this research, a model for effective automatic recognition of vertical texts in natural scene images has been proposed, consisting of two major processes which are text localization and segmentation and text recognition. This proposed model recognizes three different types of vertical scene texts, which are top-to-bottom vertical texts, bottom-to-top vertical texts and horizontal-stacked vertical texts.