Unconstrained Text Detection in Manga

10/07/2020
by   Julián Del Gobbo, et al.
0

The detection and recognition of unconstrained text is an open problem in research. Text in comic books has unusual styles that raise many challenges for text detection. This work aims to identify text characters at a pixel level in a comic genre with highly sophisticated text styles: Japanese manga. To overcome the lack of a manga dataset with individual character level annotations, we create our own. Most of the literature in text detection use bounding box metrics, which are unsuitable for pixel-level evaluation. Thus, we implemented special metrics to evaluate performance. Using these resources, we designed and evaluated a deep network model, outperforming current methods for text detection in manga in most metrics.

READ FULL TEXT

page 6

page 7

page 8

page 20

page 36

page 38

page 39

page 40

research
09/09/2020

Unconstrained Text Detection in Manga: a New Dataset and Baseline

The detection and recognition of unconstrained text is an open problem i...
research
04/01/2019

COCO_TS Dataset: Pixel-level Annotations Based on Weak Supervision for Scene Text Segmentation

The absence of large scale datasets with pixel-level supervisions is a s...
research
11/26/2020

SelfText Beyond Polygon: Unconstrained Text Detection with Box Supervision and Dynamic Self-Training

Although a polygon is a more accurate representation than an upright bou...
research
07/11/2016

Benchmark for License Plate Character Segmentation

Automatic License Plate Recognition (ALPR) has been the focus of many re...
research
05/25/2020

NENET: An Edge Learnable Network for Link Prediction in Scene Text

Text detection in scenes based on deep neural networks have shown promis...
research
04/12/2021

PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network

The reading of arbitrarily-shaped text has received increasing research ...
research
04/23/2016

Text Flow: A Unified Text Detection System in Natural Scene Images

The prevalent scene text detection approach follows four sequential step...

Please sign up or login with your details

Forgot password? Click here to reset