Detecting Oriented Text in Natural Images by Linking Segments
This addresses the need for fast and accurate text detection in real-world images, including non-Latin scripts, with significant improvements over prior methods.
The paper tackles the problem of detecting oriented text in natural images, which previous methods struggled with for non-horizontal or non-Latin text and real-time applications, by introducing Segment Linking (SegLink) that decomposes text into segments and links, achieving an f-measure of 75.0% on the ICDAR 2015 benchmark and running at over 20 FPS.
Most state-of-the-art text detection methods are specific to horizontal Latin text and are not fast enough for real-time applications. We introduce Segment Linking (SegLink), an oriented text detection method. The main idea is to decompose text into two locally detectable elements, namely segments and links. A segment is an oriented box covering a part of a word or text line; A link connects two adjacent segments, indicating that they belong to the same word or text line. Both elements are detected densely at multiple scales by an end-to-end trained, fully-convolutional neural network. Final detections are produced by combining segments connected by links. Compared with previous methods, SegLink improves along the dimensions of accuracy, speed, and ease of training. It achieves an f-measure of 75.0% on the standard ICDAR 2015 Incidental (Challenge 4) benchmark, outperforming the previous best by a large margin. It runs at over 20 FPS on 512x512 images. Moreover, without modification, SegLink is able to detect long lines of non-Latin text, such as Chinese.