Scene text localization and recognition in images and videos

Abstract

Scene Text Localization and Recognition methods nd all areas in an image or a video that would be considered as text by a human, mark boundaries of the areas and output a sequence of characters associated with its content. They are used to process images and videos taken by a digital camera or a mobile phone and to \read" the content of each text area into a digital format, typically a list of Unicode character sequences, that can be processed in further applications. Three di erent methods for Scene Text Localization and Recognition were proposed in the course of the research, each one advancing the state of the art and improving the accuracy. The rst method detects individual characters as Extremal Regions (ER), where the probability of each ER being a character is estimated using novel features with O(1) complexity and only ERs with locally maximal probability are selected across several image projections for the second stage, where the classi cation is improved using more computationally expensive features. The method was the rst published method to address the complete problem of scene text localization and recognition as a whole - all previous work in the literature focused solely on di erent subproblems. Secondly, a novel easy-to-implement stroke detector was proposed. The detector is signi cantly faster and produces signi cantly less false detections than the commonly used ER detector. The detector e ciently produces character strokes segmentations, which are exploited in a subsequent classi cation phase based on features e ectively calculated as part of the segmentation process. Additionally, an e cient text clustering algorithm based on text direction voting is proposed, which as well as the previous stages is scale- and rotation- invariant and supports wide variety of scripts and fonts. The third method exploits a deep-learning model, which is trained for both text detection and recognition in a single trainable pipeline. The method localizes and recognizes text in an image in a single feed-forward pass, it is trained purely on synthetic data so it does not require obtaining expensive human annotations for training and it achieves state-of-the-art accuracy in the end-to-end text recognition on two standard datasets, whilst being an order of magnitude faster than the previous methods - the whole pipeline runs at 10 frames per second.