A Scene-Text Synthesis Engine Achieved Through Learning from Decomposed Real-World Data

by   Zhengmi Tang, et al.

Scene-text image synthesis techniques aimed at naturally composing text instances on background scene images are very appealing for training deep neural networks because they can provide accurate and comprehensive annotation information. Prior studies have explored generating synthetic text images on two-dimensional and three-dimensional surfaces based on rules derived from real-world observations. Some of these studies have proposed generating scene-text images from learning; however, owing to the absence of a suitable training dataset, unsupervised frameworks have been explored to learn from existing real-world data, which may not result in a robust performance. To ease this dilemma and facilitate research on learning-based scene text synthesis, we propose DecompST, a real-world dataset prepared using public benchmarks, with three types of annotations: quadrilateral-level BBoxes, stroke-level text masks, and text-erased images. Using the DecompST dataset, we propose an image synthesis engine that includes a text location proposal network (TLPNet) and a text appearance adaptation network (TAANet). TLPNet first predicts the suitable regions for text embedding. TAANet then adaptively changes the geometry and color of the text instance according to the context of the background. Our comprehensive experiments verified the effectiveness of the proposed method for generating pretraining data for scene text detectors.


page 1

page 2

page 3

page 4

page 5

page 6

page 7

page 9


UnrealText: Synthesizing Realistic Scene Text Images from the Unreal World

Synthetic data has been a critical tool for training scene text detectio...

Scene Text Synthesis for Efficient and Effective Deep Network Training

A large amount of annotated training images is critical for training acc...

Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes

The requirement of large amounts of annotated images has become one gran...

Stroke-Based Scene Text Erasing Using Synthetic Data

Scene text erasing, which replaces text regions with reasonable content ...

Separate Scene Text Detector for Unseen Scripts is Not All You Need

Text detection in the wild is a well-known problem that becomes more cha...

A Human Eye-based Text Color Scheme Generation Method for Image Synthesis

Synthetic data used for scene text detection and recognition tasks have ...

Self-Supervised Text Erasing with Controllable Image Synthesis

Recent efforts on scene text erasing have shown promising results. Howev...

Please sign up or login with your details

Forgot password? Click here to reset