CVMar 12, 2016

Robust Scene Text Recognition with Automatic Rectification

arXiv:1603.03915v2627 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of text recognition in real-world images for applications like scene understanding, with incremental improvements in handling irregular shapes.

The paper tackles the problem of recognizing irregular text in natural images, such as perspective or curved text, by proposing RARE, a deep neural network that automatically rectifies images before recognition, achieving state-of-the-art or highly competitive performance on multiple benchmarks.

Recognizing text in natural images is a challenging task with many unsolved problems. Different from those in documents, words in natural images often possess irregular shapes, which are caused by perspective distortion, curved character placement, etc. We propose RARE (Robust text recognizer with Automatic REctification), a recognition model that is robust to irregular text. RARE is a specially-designed deep neural network, which consists of a Spatial Transformer Network (STN) and a Sequence Recognition Network (SRN). In testing, an image is firstly rectified via a predicted Thin-Plate-Spline (TPS) transformation, into a more "readable" image for the following SRN, which recognizes text through a sequence recognition approach. We show that the model is able to recognize several types of irregular text, including perspective text and curved text. RARE is end-to-end trainable, requiring only images and associated text labels, making it convenient to train and deploy the model in practical systems. State-of-the-art or highly-competitive performance achieved on several benchmarks well demonstrates the effectiveness of the proposed model.

Code Implementations5 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes