Conceptual Text Region Network: Cognition-Inspired Accurate Scene Text Detection

by   Chenwei Cui, et al.

Segmentation-based methods are widely used for scene text detection due to their superiority in describing arbitrary-shaped text instances. However, two major problems still exist: 1) current label generation techniques are mostly empirical and lack theoretical support, discouraging elaborate label design; 2) as a result, most methods rely heavily on text kernel segmentation which is unstable and requires deliberate tuning. To address these challenges, we propose a human cognition-inspired framework, termed, Conceptual Text Region Network (CTRNet). The framework utilizes Conceptual Text Regions (CTRs), which is a class of cognition-based tools inheriting good mathematical properties, allowing for sophisticated label design. Another component of CTRNet is an inference pipeline that, with the help of CTRs, completely omits the need for text kernel segmentation. Compared with previous segmentation-based methods, our approach is not only more interpretable but also more accurate. Experimental results show that CTRNet achieves state-of-the-art performance on benchmark CTW1500, Total-Text, MSRA-TD500, and ICDAR 2015 datasets, yielding performance gains of up to 2.0 is among the first detection models to achieve F-measures higher than 85.0 all four of the benchmarks, with remarkable consistency and stability.


page 2

page 3

page 4

page 6

page 9

page 11


ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network

Scene text detection and recognition has received increasing research at...

TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text

A crucial component for the scene text based reasoning required for Text...

Deformable Kernel Expansion Model for Efficient Arbitrary-shaped Scene Text Detection

Scene text detection is a challenging computer vision task due to the hi...

Adaptive Segmentation Network for Scene Text Detection

Inspired by deep convolution segmentation algorithms, scene text detecto...

All you need is a second look: Towards Tighter Arbitrary shape text detection

Deep learning-based scene text detection methods have progressed substan...

CBNet: A Plug-and-Play Network for Segmentation-based Scene Text Detection

Recently, segmentation-based methods are quite popular in scene text det...

Towards Robust Real-Time Scene Text Detection: From Semantic to Instance Representation Learning

Due to the flexible representation of arbitrary-shaped scene text and si...

Please sign up or login with your details

Forgot password? Click here to reset