Detecting Text in the Wild with Deep Character Embedding Network

01/02/2019
by   Jiaming Liu, et al.
0

Most text detection methods hypothesize texts are horizontal or multi-oriented and thus define quadrangles as the basic detection unit. However, text in the wild is usually perspectively distorted or curved, which can not be easily tackled by existing approaches. In this paper, we propose a deep character embedding network (CENet) which simultaneously predicts the bounding boxes of characters and their embedding vectors, thus making text detection a simple clustering task in the character embedding space. The proposed method does not require strong assumptions of forming a straight line on general text detection, which provides flexibility on arbitrarily curved or perspectively distorted text. For character detection task, a dense prediction subnetwork is designed to obtain the confidence score and bounding boxes of characters. For character embedding task, a subnet is trained with contrastive loss to project detected characters into embedding space. The two tasks share a backbone CNN from which the multi-scale feature maps are extracted. The final text regions can be easily achieved by a thresholding process on character confidence and embedding distance of character pairs. We evaluated our method on ICDAR13, ICDAR15, MSRA-TD500, and Total-Text. The proposed method achieves state-of-the-art or comparable performance on all these datasets, and shows substantial improvement in the irregular-text datasets, i.e. Total-Text.

READ FULL TEXT

page 6

page 12

research
04/03/2019

Character Region Awareness for Text Detection

Scene text detection methods based on neural networks have emerged recen...
research
10/25/2021

Industrial Scene Text Detection with Refined Feature-attentive Network

Detecting the marking characters of industrial metal parts remains chall...
research
08/22/2017

WordSup: Exploiting Word Annotations for Character based Text Detection

Imagery texts are usually organized as a hierarchy of several visual ele...
research
10/17/2019

Convolutional Character Networks

Recent progress has been made on developing a unified framework for join...
research
09/25/2013

Characterness: An Indicator of Text in the Wild

Text in an image provides vital information for interpreting its content...
research
06/30/2023

Manga109Dialog A Large-scale Dialogue Dataset for Comics Speaker Detection

The expanding market for e-comics has spurred interest in the developmen...
research
10/09/2018

Selective Distillation of Weakly Annotated GTD for Vision-based Slab Identification System

This paper proposes an algorithm for recognizing slab identification num...

Please sign up or login with your details

Forgot password? Click here to reset